From 88bc243a3f22b9938c0b53c577dee28025cdb920 Mon Sep 17 00:00:00 2001
From: Anders Roxell <anders.roxell@linaro.org>
Date: Fri, 24 Aug 2018 14:49:41 +0200
Subject: selftests: android: move config up a level

'make kselftest-merge' assumes that the config files for the tests are
located under the 'main' test dir, like tools/testing/selftests/android/
and not in a subdir to android.

Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/android/config     | 5 +++++
 tools/testing/selftests/android/ion/config | 5 -----
 2 files changed, 5 insertions(+), 5 deletions(-)
 create mode 100644 tools/testing/selftests/android/config
 delete mode 100644 tools/testing/selftests/android/ion/config

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/android/config b/tools/testing/selftests/android/config
new file mode 100644
index 000000000000..b4ad748a9dd9
--- /dev/null
+++ b/tools/testing/selftests/android/config
@@ -0,0 +1,5 @@
+CONFIG_ANDROID=y
+CONFIG_STAGING=y
+CONFIG_ION=y
+CONFIG_ION_SYSTEM_HEAP=y
+CONFIG_DRM_VGEM=y
diff --git a/tools/testing/selftests/android/ion/config b/tools/testing/selftests/android/ion/config
deleted file mode 100644
index b4ad748a9dd9..000000000000
--- a/tools/testing/selftests/android/ion/config
+++ /dev/null
@@ -1,5 +0,0 @@
-CONFIG_ANDROID=y
-CONFIG_STAGING=y
-CONFIG_ION=y
-CONFIG_ION_SYSTEM_HEAP=y
-CONFIG_DRM_VGEM=y
-- 
cgit 


From c31d02d1290e1e82a08015199e408228e152991f Mon Sep 17 00:00:00 2001
From: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Date: Tue, 24 Jul 2018 23:57:25 -0300
Subject: selftests: kselftest: Remove outdated comment

Commit 3c07aaef6598 ("selftests: kselftest: change KSFT_SKIP=4 instead of
KSFT_PASS") reverted commit 11867a77eb85 ("selftests: kselftest framework:
change skip exit code to 0") but missed removing the comment which that
commit added, so do that now.

Signed-off-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/kselftest.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h
index 15e6b75fc3a5..a3edb2c8e43d 100644
--- a/tools/testing/selftests/kselftest.h
+++ b/tools/testing/selftests/kselftest.h
@@ -19,7 +19,6 @@
 #define KSFT_FAIL  1
 #define KSFT_XFAIL 2
 #define KSFT_XPASS 3
-/* Treat skip as pass */
 #define KSFT_SKIP  4
 
 /* counters */
-- 
cgit 


From b5d83fec732dc98e37b22e8b20a7943aa0bb55d9 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Tue, 28 Aug 2018 09:10:45 -0700
Subject: bpf: sockmap test remove shutdown() calls

Currently, we do a shutdown(sk, SHUT_RDWR) on both peer sockets and
a shutdown on the sender as well. However, this is incorrect and can
occasionally cause issues if you happen to have bad timing. First
peer1 or peer2 may still be in use depending on the test and timing.
Second we really should only be closing the read side and/or write
side depending on if the test is receiving or sending.

But, really none of this is needed just remove the shutdown calls.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_sockmap.c | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 0c7d9e556b47..a0e77c6bb0cf 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -469,8 +469,6 @@ static int sendmsg_test(struct sockmap_options *opt)
 			fprintf(stderr,
 				"msg_loop_rx: iov_count %i iov_buf %i cnt %i err %i\n",
 				iov_count, iov_buf, cnt, err);
-		shutdown(p2, SHUT_RDWR);
-		shutdown(p1, SHUT_RDWR);
 		if (s.end.tv_sec - s.start.tv_sec) {
 			sent_Bps = sentBps(s);
 			recvd_Bps = recvdBps(s);
@@ -500,7 +498,6 @@ static int sendmsg_test(struct sockmap_options *opt)
 			fprintf(stderr,
 				"msg_loop_tx: iov_count %i iov_buf %i cnt %i err %i\n",
 				iov_count, iov_buf, cnt, err);
-		shutdown(c1, SHUT_RDWR);
 		if (s.end.tv_sec - s.start.tv_sec) {
 			sent_Bps = sentBps(s);
 			recvd_Bps = recvdBps(s);
-- 
cgit 


From 7d2c6cfc5411207f1094e7ca5e63e711dc76d1ff Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Tue, 28 Aug 2018 09:10:50 -0700
Subject: bpf: use --cgroup in test_suite if supplied

If the user supplies a --cgroup value in the arguments when running
the test_suite go ahaead and run the self tests there. I use this
to test with multiple cgroup users.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_sockmap.c | 53 +++++++++++++++++-------------
 1 file changed, 31 insertions(+), 22 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index a0e77c6bb0cf..ac7de38e5c63 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -1345,9 +1345,9 @@ static int populate_progs(char *bpf_file)
 	return 0;
 }
 
-static int __test_suite(char *bpf_file)
+static int __test_suite(int cg_fd, char *bpf_file)
 {
-	int cg_fd, err;
+	int err, cleanup = cg_fd;
 
 	err = populate_progs(bpf_file);
 	if (err < 0) {
@@ -1355,22 +1355,24 @@ static int __test_suite(char *bpf_file)
 		return err;
 	}
 
-	if (setup_cgroup_environment()) {
-		fprintf(stderr, "ERROR: cgroup env failed\n");
-		return -EINVAL;
-	}
-
-	cg_fd = create_and_get_cgroup(CG_PATH);
 	if (cg_fd < 0) {
-		fprintf(stderr,
-			"ERROR: (%i) open cg path failed: %s\n",
-			cg_fd, optarg);
-		return cg_fd;
-	}
+		if (setup_cgroup_environment()) {
+			fprintf(stderr, "ERROR: cgroup env failed\n");
+			return -EINVAL;
+		}
+
+		cg_fd = create_and_get_cgroup(CG_PATH);
+		if (cg_fd < 0) {
+			fprintf(stderr,
+				"ERROR: (%i) open cg path failed: %s\n",
+				cg_fd, optarg);
+			return cg_fd;
+		}
 
-	if (join_cgroup(CG_PATH)) {
-		fprintf(stderr, "ERROR: failed to join cgroup\n");
-		return -EINVAL;
+		if (join_cgroup(CG_PATH)) {
+			fprintf(stderr, "ERROR: failed to join cgroup\n");
+			return -EINVAL;
+		}
 	}
 
 	/* Tests basic commands and APIs with range of iov values */
@@ -1391,20 +1393,24 @@ static int __test_suite(char *bpf_file)
 
 out:
 	printf("Summary: %i PASSED %i FAILED\n", passed, failed);
-	cleanup_cgroup_environment();
-	close(cg_fd);
+	if (cleanup < 0) {
+		cleanup_cgroup_environment();
+		close(cg_fd);
+	}
 	return err;
 }
 
-static int test_suite(void)
+static int test_suite(int cg_fd)
 {
 	int err;
 
-	err = __test_suite(BPF_SOCKMAP_FILENAME);
+	err = __test_suite(cg_fd, BPF_SOCKMAP_FILENAME);
 	if (err)
 		goto out;
-	err = __test_suite(BPF_SOCKHASH_FILENAME);
+	err = __test_suite(cg_fd, BPF_SOCKHASH_FILENAME);
 out:
+	if (cg_fd > -1)
+		close(cg_fd);
 	return err;
 }
 
@@ -1417,7 +1423,7 @@ int main(int argc, char **argv)
 	int test = PING_PONG;
 
 	if (argc < 2)
-		return test_suite();
+		return test_suite(-1);
 
 	while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:",
 				  long_options, &longindex)) != -1) {
@@ -1483,6 +1489,9 @@ int main(int argc, char **argv)
 		}
 	}
 
+	if (argc <= 3 && cg_fd)
+		return test_suite(cg_fd);
+
 	if (!cg_fd) {
 		fprintf(stderr, "%s requires cgroup option: --cgroup <path>\n",
 			argv[0]);
-- 
cgit 


From 31e7490741566d6f72be3a68bf9259a3bc2bc21d Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sun, 1 Jul 2018 05:48:46 -0700
Subject: torture: Stop overwriting Make.out file with obsolete version

The old approach placed all the build products into the b* directories,
which meant that some of these build products needed to be copied to
the proper directory in the res hierarchy.  The new approach leaves
things like .config and the .o files in the b1 directory, but directs
build output and diagnostics directly to the proper directory in the
res hierarchy.  Unfortunately, one of the copies was still carried out,
which could (and sometimes did) overwrite the build output and diagnostics
with obsolete output remaining in the b1 directory.

This commit therefore removes the offending "cp" command.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh | 1 -
 1 file changed, 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index f7247ee00514..58ca758a5786 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -120,7 +120,6 @@ then
 	parse-build.sh $resdir/Make.out $title
 else
 	# Build failed.
-	cp $builddir/Make*.out $resdir
 	cp $builddir/.config $resdir || :
 	echo Build failed, not running KVM, see $resdir.
 	if test -f $builddir.wait
-- 
cgit 


From a52d14addf06c00cfca4f1698e254955942be754 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sat, 7 Jul 2018 10:30:28 -0700
Subject: rcutorture: Remove TREE06 and TREE08 from the default test list

Now that there is only one RCU flavor to rule them all, the TREE06
and TREE08 test scenarios are redundant.  This commit therefore removes
them.  Later changes will rebalance and renumber the tests.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 tools/testing/selftests/rcutorture/configs/rcu/CFLIST | 2 --
 1 file changed, 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST
index 6a0b9f69faad..c3c1fb5a9e1f 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST
+++ b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST
@@ -3,9 +3,7 @@ TREE02
 TREE03
 TREE04
 TREE05
-TREE06
 TREE07
-TREE08
 TREE09
 SRCU-N
 SRCU-P
-- 
cgit 


From 02c7f38b7ace9f1b2ddb7a88139127eef4cf8706 Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Tue, 28 Aug 2018 11:36:20 -0700
Subject: selftests/net: add ip_defrag selftest

This test creates a raw IPv4 socket, fragments a largish UDP
datagram and sends the fragments out of order.

Then repeats in a loop with different message and fragment lengths.

Then does the same with overlapping fragments (with overlapping
fragments the expectation is that the recv times out).

Tested:

root@<host># time ./ip_defrag.sh
ipv4 defrag
PASS
ipv4 defrag with overlaps
PASS

real    1m7.679s
user    0m0.628s
sys     0m2.242s

A similar test for IPv6 is to follow.

Signed-off-by: Peter Oskolkov <posk@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/.gitignore   |   1 +
 tools/testing/selftests/net/Makefile     |   4 +-
 tools/testing/selftests/net/ip_defrag.c  | 313 +++++++++++++++++++++++++++++++
 tools/testing/selftests/net/ip_defrag.sh |  28 +++
 4 files changed, 344 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/net/ip_defrag.c
 create mode 100755 tools/testing/selftests/net/ip_defrag.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 78b24cf76f40..8cf22b3c2563 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -14,3 +14,4 @@ udpgso_bench_rx
 udpgso_bench_tx
 tcp_inq
 tls
+ip_defrag
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 9cca68e440a0..cccdb2295567 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -5,13 +5,13 @@ CFLAGS =  -Wall -Wl,--no-as-needed -O2 -g
 CFLAGS += -I../../../../usr/include/
 
 TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
-TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh
+TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh
 TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
 TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd
-TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx
+TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
 TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
 
diff --git a/tools/testing/selftests/net/ip_defrag.c b/tools/testing/selftests/net/ip_defrag.c
new file mode 100644
index 000000000000..55fdcdc78eef
--- /dev/null
+++ b/tools/testing/selftests/net/ip_defrag.c
@@ -0,0 +1,313 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <linux/in.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/udp.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+#include <unistd.h>
+
+static bool		cfg_do_ipv4;
+static bool		cfg_do_ipv6;
+static bool		cfg_verbose;
+static bool		cfg_overlap;
+static unsigned short	cfg_port = 9000;
+
+const struct in_addr addr4 = { .s_addr = __constant_htonl(INADDR_LOOPBACK + 2) };
+
+#define IP4_HLEN	(sizeof(struct iphdr))
+#define IP6_HLEN	(sizeof(struct ip6_hdr))
+#define UDP_HLEN	(sizeof(struct udphdr))
+
+static int msg_len;
+static int max_frag_len;
+
+#define MSG_LEN_MAX	60000	/* Max UDP payload length. */
+
+#define IP4_MF		(1u << 13)  /* IPv4 MF flag. */
+
+static uint8_t udp_payload[MSG_LEN_MAX];
+static uint8_t ip_frame[IP_MAXPACKET];
+static uint16_t ip_id = 0xabcd;
+static int msg_counter;
+static int frag_counter;
+static unsigned int seed;
+
+/* Receive a UDP packet. Validate it matches udp_payload. */
+static void recv_validate_udp(int fd_udp)
+{
+	ssize_t ret;
+	static uint8_t recv_buff[MSG_LEN_MAX];
+
+	ret = recv(fd_udp, recv_buff, msg_len, 0);
+	msg_counter++;
+
+	if (cfg_overlap) {
+		if (ret != -1)
+			error(1, 0, "recv: expected timeout; got %d; seed = %u",
+				(int)ret, seed);
+		if (errno != ETIMEDOUT && errno != EAGAIN)
+			error(1, errno, "recv: expected timeout: %d; seed = %u",
+				 errno, seed);
+		return;  /* OK */
+	}
+
+	if (ret == -1)
+		error(1, errno, "recv: msg_len = %d max_frag_len = %d",
+			msg_len, max_frag_len);
+	if (ret != msg_len)
+		error(1, 0, "recv: wrong size: %d vs %d", (int)ret, msg_len);
+	if (memcmp(udp_payload, recv_buff, msg_len))
+		error(1, 0, "recv: wrong data");
+}
+
+static uint32_t raw_checksum(uint8_t *buf, int len, uint32_t sum)
+{
+	int i;
+
+	for (i = 0; i < (len & ~1U); i += 2) {
+		sum += (u_int16_t)ntohs(*((u_int16_t *)(buf + i)));
+		if (sum > 0xffff)
+			sum -= 0xffff;
+	}
+
+	if (i < len) {
+		sum += buf[i] << 8;
+		if (sum > 0xffff)
+			sum -= 0xffff;
+	}
+
+	return sum;
+}
+
+static uint16_t udp_checksum(struct ip *iphdr, struct udphdr *udphdr)
+{
+	uint32_t sum = 0;
+
+	sum = raw_checksum((uint8_t *)&iphdr->ip_src, 2 * sizeof(iphdr->ip_src),
+				IPPROTO_UDP + (uint32_t)(UDP_HLEN + msg_len));
+	sum = raw_checksum((uint8_t *)udp_payload, msg_len, sum);
+	sum = raw_checksum((uint8_t *)udphdr, UDP_HLEN, sum);
+	return htons(0xffff & ~sum);
+}
+
+static void send_fragment(int fd_raw, struct sockaddr *addr, socklen_t alen,
+				struct ip *iphdr, int offset)
+{
+	int frag_len;
+	int res;
+
+	if (msg_len - offset <= max_frag_len) {
+		/* This is the last fragment. */
+		frag_len = IP4_HLEN + msg_len - offset;
+		iphdr->ip_off = htons((offset + UDP_HLEN) / 8);
+	} else {
+		frag_len = IP4_HLEN + max_frag_len;
+		iphdr->ip_off = htons((offset + UDP_HLEN) / 8 | IP4_MF);
+	}
+	iphdr->ip_len = htons(frag_len);
+	memcpy(ip_frame + IP4_HLEN, udp_payload + offset,
+		 frag_len - IP4_HLEN);
+
+	res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen);
+	if (res < 0)
+		error(1, errno, "send_fragment");
+	if (res != frag_len)
+		error(1, 0, "send_fragment: %d vs %d", res, frag_len);
+
+	frag_counter++;
+}
+
+static void send_udp_frags_v4(int fd_raw, struct sockaddr *addr, socklen_t alen)
+{
+	struct ip *iphdr = (struct ip *)ip_frame;
+	struct udphdr udphdr;
+	int res;
+	int offset;
+	int frag_len;
+
+	/* Send the UDP datagram using raw IP fragments: the 0th fragment
+	 * has the UDP header; other fragments are pieces of udp_payload
+	 * split in chunks of frag_len size.
+	 *
+	 * Odd fragments (1st, 3rd, 5th, etc.) are sent out first, then
+	 * even fragments (0th, 2nd, etc.) are sent out.
+	 */
+	memset(iphdr, 0, sizeof(*iphdr));
+	iphdr->ip_hl = 5;
+	iphdr->ip_v = 4;
+	iphdr->ip_tos = 0;
+	iphdr->ip_id = htons(ip_id++);
+	iphdr->ip_ttl = 0x40;
+	iphdr->ip_p = IPPROTO_UDP;
+	iphdr->ip_src.s_addr = htonl(INADDR_LOOPBACK);
+	iphdr->ip_dst = addr4;
+	iphdr->ip_sum = 0;
+
+	/* Odd fragments. */
+	offset = 0;
+	while (offset < msg_len) {
+		send_fragment(fd_raw, addr, alen, iphdr, offset);
+		offset += 2 * max_frag_len;
+	}
+
+	if (cfg_overlap) {
+		/* Send an extra random fragment. */
+		offset = rand() % (UDP_HLEN + msg_len - 1);
+		/* sendto() returns EINVAL if offset + frag_len is too small. */
+		frag_len = IP4_HLEN + UDP_HLEN + rand() % 256;
+		iphdr->ip_off = htons(offset / 8 | IP4_MF);
+		iphdr->ip_len = htons(frag_len);
+		res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen);
+		if (res < 0)
+			error(1, errno, "sendto overlap");
+		if (res != frag_len)
+			error(1, 0, "sendto overlap: %d vs %d", (int)res, frag_len);
+		frag_counter++;
+	}
+
+	/* Zeroth fragment (UDP header). */
+	frag_len = IP4_HLEN + UDP_HLEN;
+	iphdr->ip_len = htons(frag_len);
+	iphdr->ip_off = htons(IP4_MF);
+
+	udphdr.source = htons(cfg_port + 1);
+	udphdr.dest = htons(cfg_port);
+	udphdr.len = htons(UDP_HLEN + msg_len);
+	udphdr.check = 0;
+	udphdr.check = udp_checksum(iphdr, &udphdr);
+
+	memcpy(ip_frame + IP4_HLEN, &udphdr, UDP_HLEN);
+	res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen);
+	if (res < 0)
+		error(1, errno, "sendto UDP header");
+	if (res != frag_len)
+		error(1, 0, "sendto UDP header: %d vs %d", (int)res, frag_len);
+	frag_counter++;
+
+	/* Even fragments. */
+	offset = max_frag_len;
+	while (offset < msg_len) {
+		send_fragment(fd_raw, addr, alen, iphdr, offset);
+		offset += 2 * max_frag_len;
+	}
+}
+
+static void run_test(struct sockaddr *addr, socklen_t alen)
+{
+	int fd_tx_udp, fd_tx_raw, fd_rx_udp;
+	struct timeval tv = { .tv_sec = 0, .tv_usec = 10 * 1000 };
+	int idx;
+
+	/* Initialize the payload. */
+	for (idx = 0; idx < MSG_LEN_MAX; ++idx)
+		udp_payload[idx] = idx % 256;
+
+	/* Open sockets. */
+	fd_tx_udp = socket(addr->sa_family, SOCK_DGRAM, 0);
+	if (fd_tx_udp == -1)
+		error(1, errno, "socket tx_udp");
+
+	fd_tx_raw = socket(addr->sa_family, SOCK_RAW, IPPROTO_RAW);
+	if (fd_tx_raw == -1)
+		error(1, errno, "socket tx_raw");
+
+	fd_rx_udp = socket(addr->sa_family, SOCK_DGRAM, 0);
+	if (fd_rx_udp == -1)
+		error(1, errno, "socket rx_udp");
+	if (bind(fd_rx_udp, addr, alen))
+		error(1, errno, "bind");
+	/* Fail fast. */
+	if (setsockopt(fd_rx_udp, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
+		error(1, errno, "setsockopt rcv timeout");
+
+	for (msg_len = 1; msg_len < MSG_LEN_MAX; msg_len += (rand() % 4096)) {
+		if (cfg_verbose)
+			printf("msg_len: %d\n", msg_len);
+		max_frag_len = addr->sa_family == AF_INET ? 8 : 1280;
+		for (; max_frag_len < 1500 && max_frag_len <= msg_len;
+				max_frag_len += 8) {
+			send_udp_frags_v4(fd_tx_raw, addr, alen);
+			recv_validate_udp(fd_rx_udp);
+		}
+	}
+
+	/* Cleanup. */
+	if (close(fd_tx_raw))
+		error(1, errno, "close tx_raw");
+	if (close(fd_tx_udp))
+		error(1, errno, "close tx_udp");
+	if (close(fd_rx_udp))
+		error(1, errno, "close rx_udp");
+
+	if (cfg_verbose)
+		printf("processed %d messages, %d fragments\n",
+			msg_counter, frag_counter);
+
+	fprintf(stderr, "PASS\n");
+}
+
+
+static void run_test_v4(void)
+{
+	struct sockaddr_in addr = {0};
+
+	addr.sin_family = AF_INET;
+	addr.sin_port = htons(cfg_port);
+	addr.sin_addr = addr4;
+
+	run_test((void *)&addr, sizeof(addr));
+}
+
+static void run_test_v6(void)
+{
+	fprintf(stderr, "NOT IMPL.\n");
+	exit(1);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	int c;
+
+	while ((c = getopt(argc, argv, "46ov")) != -1) {
+		switch (c) {
+		case '4':
+			cfg_do_ipv4 = true;
+			break;
+		case '6':
+			cfg_do_ipv6 = true;
+			break;
+		case 'o':
+			cfg_overlap = true;
+			break;
+		case 'v':
+			cfg_verbose = true;
+			break;
+		default:
+			error(1, 0, "%s: parse error", argv[0]);
+		}
+	}
+}
+
+int main(int argc, char **argv)
+{
+	parse_opts(argc, argv);
+	seed = time(NULL);
+	srand(seed);
+
+	if (cfg_do_ipv4)
+		run_test_v4();
+	if (cfg_do_ipv6)
+		run_test_v6();
+
+	return 0;
+}
diff --git a/tools/testing/selftests/net/ip_defrag.sh b/tools/testing/selftests/net/ip_defrag.sh
new file mode 100755
index 000000000000..78743adcca9e
--- /dev/null
+++ b/tools/testing/selftests/net/ip_defrag.sh
@@ -0,0 +1,28 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a couple of IP defragmentation tests.
+
+set +x
+set -e
+
+echo "ipv4 defrag"
+
+run_v4() {
+sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null
+sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null
+./ip_defrag -4
+}
+export -f run_v4
+
+./in_netns.sh "run_v4"
+
+echo "ipv4 defrag with overlaps"
+run_v4o() {
+sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null
+sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null
+./ip_defrag -4o
+}
+export -f run_v4o
+
+./in_netns.sh "run_v4o"
-- 
cgit 


From 25a8238f4cc8425d4aade4f9041be468d0e8aa2e Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 29 Aug 2018 10:22:34 +0200
Subject: tc-testing: add test-cases for numeric and invalid control action

Only the police action allows us to specify an arbitrary numeric value
for the control action. This change introduces an explicit test case
for the above feature and then leverage it for testing the kernel behavior
for invalid control actions (reject).

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../tc-testing/tc-tests/actions/police.json        | 48 ++++++++++++++++++++++
 1 file changed, 48 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
index f03763d81617..30f9b54bd666 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
@@ -312,6 +312,54 @@
             "$TC actions flush action police"
         ]
     },
+    {
+        "id": "6aaf",
+        "name": "Add police actions with conform-exceed control pass/pipe [with numeric values]",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed 0/3 index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action police index 1",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 3Mbit burst 250Kb mtu 2Kb action pass/pipe",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "29b1",
+        "name": "Add police actions with conform-exceed control <invalid>/drop",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed 10/drop index 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 3Mbit burst 250Kb mtu 2Kb action ",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
     {
         "id": "c26f",
         "name": "Add police action with invalid peakrate value",
-- 
cgit 


From 6493ebf7242d9b9a2c50db91b9baeb0543990736 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Wed, 29 Aug 2018 14:43:14 -0700
Subject: tools/bpf: add bpffs percpu map pretty print tests in test_btf

The bpf selftest test_btf is extended to test bpffs
percpu map pretty print for percpu array, percpu hash and
percpu lru hash.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_btf.c | 179 ++++++++++++++++++++++++++-------
 1 file changed, 144 insertions(+), 35 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 6b5cfeb7a9cc..f42b3396d622 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -4,6 +4,7 @@
 #include <linux/bpf.h>
 #include <linux/btf.h>
 #include <linux/err.h>
+#include <linux/kernel.h>
 #include <bpf/bpf.h>
 #include <sys/resource.h>
 #include <libelf.h>
@@ -45,7 +46,6 @@ static int count_result(int err)
 	return err;
 }
 
-#define min(a, b) ((a) < (b) ? (a) : (b))
 #define __printf(a, b)	__attribute__((format(printf, a, b)))
 
 __printf(1, 2)
@@ -130,6 +130,7 @@ struct btf_raw_test {
 	bool map_create_err;
 	bool ordered_map;
 	bool lossless_map;
+	bool percpu_map;
 	int hdr_len_delta;
 	int type_off_delta;
 	int str_off_delta;
@@ -2157,6 +2158,7 @@ static struct btf_pprint_test_meta {
 	const char *map_name;
 	bool ordered_map;
 	bool lossless_map;
+	bool percpu_map;
 } pprint_tests_meta[] = {
 {
 	.descr = "BTF pretty print array",
@@ -2164,6 +2166,7 @@ static struct btf_pprint_test_meta {
 	.map_name = "pprint_test_array",
 	.ordered_map = true,
 	.lossless_map = true,
+	.percpu_map = false,
 },
 
 {
@@ -2172,6 +2175,7 @@ static struct btf_pprint_test_meta {
 	.map_name = "pprint_test_hash",
 	.ordered_map = false,
 	.lossless_map = true,
+	.percpu_map = false,
 },
 
 {
@@ -2180,30 +2184,83 @@ static struct btf_pprint_test_meta {
 	.map_name = "pprint_test_lru_hash",
 	.ordered_map = false,
 	.lossless_map = false,
+	.percpu_map = false,
+},
+
+{
+	.descr = "BTF pretty print percpu array",
+	.map_type = BPF_MAP_TYPE_PERCPU_ARRAY,
+	.map_name = "pprint_test_percpu_array",
+	.ordered_map = true,
+	.lossless_map = true,
+	.percpu_map = true,
+},
+
+{
+	.descr = "BTF pretty print percpu hash",
+	.map_type = BPF_MAP_TYPE_PERCPU_HASH,
+	.map_name = "pprint_test_percpu_hash",
+	.ordered_map = false,
+	.lossless_map = true,
+	.percpu_map = true,
+},
+
+{
+	.descr = "BTF pretty print lru percpu hash",
+	.map_type = BPF_MAP_TYPE_LRU_PERCPU_HASH,
+	.map_name = "pprint_test_lru_percpu_hash",
+	.ordered_map = false,
+	.lossless_map = false,
+	.percpu_map = true,
 },
 
 };
 
 
-static void set_pprint_mapv(struct pprint_mapv *v, uint32_t i)
+static void set_pprint_mapv(struct pprint_mapv *v, uint32_t i,
+			    int num_cpus, int rounded_value_size)
 {
-	v->ui32 = i;
-	v->si32 = -i;
-	v->unused_bits2a = 3;
-	v->bits28 = i;
-	v->unused_bits2b = 3;
-	v->ui64 = i;
-	v->aenum = i & 0x03;
+	int cpu;
+
+	for (cpu = 0; cpu < num_cpus; cpu++) {
+		v->ui32 = i + cpu;
+		v->si32 = -i;
+		v->unused_bits2a = 3;
+		v->bits28 = i;
+		v->unused_bits2b = 3;
+		v->ui64 = i;
+		v->aenum = i & 0x03;
+		v = (void *)v + rounded_value_size;
+	}
 }
 
+static int check_line(const char *expected_line, int nexpected_line,
+		      int expected_line_len, const char *line)
+{
+	if (CHECK(nexpected_line == expected_line_len,
+		  "expected_line is too long"))
+		return -1;
+
+	if (strcmp(expected_line, line)) {
+		fprintf(stderr, "unexpected pprint output\n");
+		fprintf(stderr, "expected: %s", expected_line);
+		fprintf(stderr, "    read: %s", line);
+		return -1;
+	}
+
+	return 0;
+}
+
+
 static int do_test_pprint(void)
 {
 	const struct btf_raw_test *test = &pprint_test_template;
 	struct bpf_create_map_attr create_attr = {};
+	bool ordered_map, lossless_map, percpu_map;
+	int err, ret, num_cpus, rounded_value_size;
+	struct pprint_mapv *mapv = NULL;
 	unsigned int key, nr_read_elems;
-	bool ordered_map, lossless_map;
 	int map_fd = -1, btf_fd = -1;
-	struct pprint_mapv mapv = {};
 	unsigned int raw_btf_size;
 	char expected_line[255];
 	FILE *pin_file = NULL;
@@ -2212,7 +2269,6 @@ static int do_test_pprint(void)
 	char *line = NULL;
 	uint8_t *raw_btf;
 	ssize_t nread;
-	int err, ret;
 
 	fprintf(stderr, "%s......", test->descr);
 	raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types,
@@ -2261,9 +2317,18 @@ static int do_test_pprint(void)
 	if (CHECK(err, "bpf_obj_pin(%s): errno:%d.", pin_path, errno))
 		goto done;
 
+	percpu_map = test->percpu_map;
+	num_cpus = percpu_map ? bpf_num_possible_cpus() : 1;
+	rounded_value_size = round_up(sizeof(struct pprint_mapv), 8);
+	mapv = calloc(num_cpus, rounded_value_size);
+	if (CHECK(!mapv, "mapv allocation failure")) {
+		err = -1;
+		goto done;
+	}
+
 	for (key = 0; key < test->max_entries; key++) {
-		set_pprint_mapv(&mapv, key);
-		bpf_map_update_elem(map_fd, &key, &mapv, 0);
+		set_pprint_mapv(mapv, key, num_cpus, rounded_value_size);
+		bpf_map_update_elem(map_fd, &key, mapv, 0);
 	}
 
 	pin_file = fopen(pin_path, "r");
@@ -2286,33 +2351,74 @@ static int do_test_pprint(void)
 	ordered_map = test->ordered_map;
 	lossless_map = test->lossless_map;
 	do {
+		struct pprint_mapv *cmapv;
 		ssize_t nexpected_line;
 		unsigned int next_key;
+		int cpu;
 
 		next_key = ordered_map ? nr_read_elems : atoi(line);
-		set_pprint_mapv(&mapv, next_key);
-		nexpected_line = snprintf(expected_line, sizeof(expected_line),
-					  "%u: {%u,0,%d,0x%x,0x%x,0x%x,{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s}\n",
-					  next_key,
-					  mapv.ui32, mapv.si32,
-					  mapv.unused_bits2a, mapv.bits28, mapv.unused_bits2b,
-					  mapv.ui64,
-					  mapv.ui8a[0], mapv.ui8a[1], mapv.ui8a[2], mapv.ui8a[3],
-					  mapv.ui8a[4], mapv.ui8a[5], mapv.ui8a[6], mapv.ui8a[7],
-					  pprint_enum_str[mapv.aenum]);
-
-		if (CHECK(nexpected_line == sizeof(expected_line),
-			  "expected_line is too long")) {
-			err = -1;
-			goto done;
+		set_pprint_mapv(mapv, next_key, num_cpus, rounded_value_size);
+		cmapv = mapv;
+
+		for (cpu = 0; cpu < num_cpus; cpu++) {
+			if (percpu_map) {
+				/* for percpu map, the format looks like:
+				 * <key>: {
+				 *	cpu0: <value_on_cpu0>
+				 *	cpu1: <value_on_cpu1>
+				 *	...
+				 *	cpun: <value_on_cpun>
+				 * }
+				 *
+				 * let us verify the line containing the key here.
+				 */
+				if (cpu == 0) {
+					nexpected_line = snprintf(expected_line,
+								  sizeof(expected_line),
+								  "%u: {\n",
+								  next_key);
+
+					err = check_line(expected_line, nexpected_line,
+							 sizeof(expected_line), line);
+					if (err == -1)
+						goto done;
+				}
+
+				/* read value@cpu */
+				nread = getline(&line, &line_len, pin_file);
+				if (nread < 0)
+					break;
+			}
+
+			nexpected_line = snprintf(expected_line, sizeof(expected_line),
+						  "%s%u: {%u,0,%d,0x%x,0x%x,0x%x,"
+						  "{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s}\n",
+						  percpu_map ? "\tcpu" : "",
+						  percpu_map ? cpu : next_key,
+						  cmapv->ui32, cmapv->si32,
+						  cmapv->unused_bits2a,
+						  cmapv->bits28,
+						  cmapv->unused_bits2b,
+						  cmapv->ui64,
+						  cmapv->ui8a[0], cmapv->ui8a[1],
+						  cmapv->ui8a[2], cmapv->ui8a[3],
+						  cmapv->ui8a[4], cmapv->ui8a[5],
+						  cmapv->ui8a[6], cmapv->ui8a[7],
+						  pprint_enum_str[cmapv->aenum]);
+
+			err = check_line(expected_line, nexpected_line,
+					 sizeof(expected_line), line);
+			if (err == -1)
+				goto done;
+
+			cmapv = (void *)cmapv + rounded_value_size;
 		}
 
-		if (strcmp(expected_line, line)) {
-			err = -1;
-			fprintf(stderr, "unexpected pprint output\n");
-			fprintf(stderr, "expected: %s", expected_line);
-			fprintf(stderr, "    read: %s", line);
-			goto done;
+		if (percpu_map) {
+			/* skip the last bracket for the percpu map */
+			nread = getline(&line, &line_len, pin_file);
+			if (nread < 0)
+				break;
 		}
 
 		nread = getline(&line, &line_len, pin_file);
@@ -2334,6 +2440,8 @@ static int do_test_pprint(void)
 	err = 0;
 
 done:
+	if (mapv)
+		free(mapv);
 	if (!err)
 		fprintf(stderr, "OK");
 	if (*btf_log_buf && (err || args.always_log))
@@ -2361,6 +2469,7 @@ static int test_pprint(void)
 		pprint_test_template.map_name = pprint_tests_meta[i].map_name;
 		pprint_test_template.ordered_map = pprint_tests_meta[i].ordered_map;
 		pprint_test_template.lossless_map = pprint_tests_meta[i].lossless_map;
+		pprint_test_template.percpu_map = pprint_tests_meta[i].percpu_map;
 
 		err |= count_result(do_test_pprint());
 	}
-- 
cgit 


From 72ce30dd1f9bdbd6913ba868d0d2ca55c268eff3 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sat, 7 Jul 2018 10:24:23 -0700
Subject: rcu: Stop testing RCU-bh and RCU-sched

Now that the RCU-bh and RCU-sched update-side functions are simple
wrappers around their RCU counterparts, there isn't a whole lot of
point in testing them.  This commit therefore removes the self-test
capability and removes the corresponding kernel-boot parameters.
It also updates the various rcutorture .boot files to remove the
kernel boot parameters that call for testing RCU-bh and RCU-sched.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 Documentation/admin-guide/kernel-parameters.txt    |  6 ----
 kernel/rcu/update.c                                | 38 +---------------------
 .../selftests/rcutorture/configs/rcu/TINY02.boot   |  2 --
 .../selftests/rcutorture/configs/rcu/TREE01.boot   |  2 +-
 .../selftests/rcutorture/configs/rcu/TREE04.boot   |  2 +-
 .../selftests/rcutorture/configs/rcu/TREE05.boot   |  2 --
 .../selftests/rcutorture/configs/rcu/TREE06.boot   |  2 --
 .../selftests/rcutorture/configs/rcu/TREE08.boot   |  2 --
 8 files changed, 3 insertions(+), 53 deletions(-)

(limited to 'tools/testing')

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 9871e649ffef..aa96e669bcb8 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3863,12 +3863,6 @@
 	rcupdate.rcu_self_test= [KNL]
 			Run the RCU early boot self tests
 
-	rcupdate.rcu_self_test_bh= [KNL]
-			Run the RCU bh early boot self tests
-
-	rcupdate.rcu_self_test_sched= [KNL]
-			Run the RCU sched early boot self tests
-
 	rdinit=		[KNL]
 			Format: <full_path>
 			Run specified binary instead of /init from the ramdisk,
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 9ea87d0aa386..ee366faecea6 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -203,11 +203,7 @@ void rcu_test_sync_prims(void)
 	if (!IS_ENABLED(CONFIG_PROVE_RCU))
 		return;
 	synchronize_rcu();
-	synchronize_rcu_bh();
-	synchronize_sched();
 	synchronize_rcu_expedited();
-	synchronize_rcu_bh_expedited();
-	synchronize_sched_expedited();
 }
 
 #if !defined(CONFIG_TINY_RCU) || defined(CONFIG_SRCU)
@@ -870,15 +866,10 @@ static void __init rcu_tasks_bootup_oddness(void)
 #ifdef CONFIG_PROVE_RCU
 
 /*
- * Early boot self test parameters, one for each flavor
+ * Early boot self test parameters.
  */
 static bool rcu_self_test;
-static bool rcu_self_test_bh;
-static bool rcu_self_test_sched;
-
 module_param(rcu_self_test, bool, 0444);
-module_param(rcu_self_test_bh, bool, 0444);
-module_param(rcu_self_test_sched, bool, 0444);
 
 static int rcu_self_test_counter;
 
@@ -895,30 +886,12 @@ static void early_boot_test_call_rcu(void)
 	call_rcu(&head, test_callback);
 }
 
-static void early_boot_test_call_rcu_bh(void)
-{
-	static struct rcu_head head;
-
-	call_rcu_bh(&head, test_callback);
-}
-
-static void early_boot_test_call_rcu_sched(void)
-{
-	static struct rcu_head head;
-
-	call_rcu_sched(&head, test_callback);
-}
-
 void rcu_early_boot_tests(void)
 {
 	pr_info("Running RCU self tests\n");
 
 	if (rcu_self_test)
 		early_boot_test_call_rcu();
-	if (rcu_self_test_bh)
-		early_boot_test_call_rcu_bh();
-	if (rcu_self_test_sched)
-		early_boot_test_call_rcu_sched();
 	rcu_test_sync_prims();
 }
 
@@ -931,15 +904,6 @@ static int rcu_verify_early_boot_tests(void)
 		early_boot_test_counter++;
 		rcu_barrier();
 	}
-	if (rcu_self_test_bh) {
-		early_boot_test_counter++;
-		rcu_barrier_bh();
-	}
-	if (rcu_self_test_sched) {
-		early_boot_test_counter++;
-		rcu_barrier_sched();
-	}
-
 	if (rcu_self_test_counter != early_boot_test_counter) {
 		WARN_ON(1);
 		ret = -1;
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot b/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot
index 6c1a292a65fb..b39f1553a478 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot
@@ -1,3 +1 @@
 rcupdate.rcu_self_test=1
-rcupdate.rcu_self_test_bh=1
-rcutorture.torture_type=rcu_bh
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot
index 9f3a4d28e508..ea47da95374b 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot
@@ -1,4 +1,4 @@
-rcutorture.torture_type=rcu_bh maxcpus=8 nr_cpus=43
+maxcpus=8 nr_cpus=43
 rcutree.gp_preinit_delay=3
 rcutree.gp_init_delay=3
 rcutree.gp_cleanup_delay=3
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot
index e6071bb96c7d..5adc6756792a 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot
@@ -1 +1 @@
-rcutorture.torture_type=rcu_bh rcutree.rcu_fanout_leaf=4 nohz_full=1-7
+rcutree.rcu_fanout_leaf=4 nohz_full=1-7
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot
index c7fd050dfcd9..779f1aed4606 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot
@@ -1,5 +1,3 @@
-rcutorture.torture_type=sched
-rcupdate.rcu_self_test_sched=1
 rcutree.gp_preinit_delay=3
 rcutree.gp_init_delay=3
 rcutree.gp_cleanup_delay=3
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot
index ad18b52a2cad..055f4aa79077 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot
@@ -1,6 +1,4 @@
 rcupdate.rcu_self_test=1
-rcupdate.rcu_self_test_bh=1
-rcupdate.rcu_self_test_sched=1
 rcutree.rcu_fanout_exact=1
 rcutree.gp_preinit_delay=3
 rcutree.gp_init_delay=3
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot
index 1bd8efc4141e..22478fd3a865 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot
@@ -1,5 +1,3 @@
-rcutorture.torture_type=sched
 rcupdate.rcu_self_test=1
-rcupdate.rcu_self_test_sched=1
 rcutree.rcu_fanout_exact=1
 rcu_nocbs=0-7
-- 
cgit 


From 55cda2290bf9d8510fbe7c1939a36680476c69c4 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 14 Aug 2018 09:19:05 -0700
Subject: rcutorture: Test early boot call_srcu()

Now that SRCU permits call_srcu() to be invoked at early boot, this
commit ensures that the rcutorture scripting tests early boot call_srcu().

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot | 1 +
 tools/testing/selftests/rcutorture/configs/rcu/SRCU-u.boot | 1 +
 tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot | 1 +
 3 files changed, 3 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot
index 84a7d51b7481..ce48c7b82673 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot
@@ -1 +1,2 @@
 rcutorture.torture_type=srcud
+rcupdate.rcu_self_test=1
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u.boot
index 84a7d51b7481..ce48c7b82673 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u.boot
@@ -1 +1,2 @@
 rcutorture.torture_type=srcud
+rcupdate.rcu_self_test=1
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot
index c7fd050dfcd9..dfebc82932ca 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot
@@ -3,3 +3,4 @@ rcupdate.rcu_self_test_sched=1
 rcutree.gp_preinit_delay=3
 rcutree.gp_init_delay=3
 rcutree.gp_cleanup_delay=3
+rcupdate.rcu_self_test=1
-- 
cgit 


From 9746b1ee2edcabfb8f40d5311f23ac2f01f152ed Mon Sep 17 00:00:00 2001
From: "Nikita V. Shirokov" <tehnerd@fb.com>
Date: Fri, 31 Aug 2018 09:43:47 -0700
Subject: bpf: add selftest for bpf's (set|get)_sockopt for SAVE_SYN

adding selftest for feature, introduced in commit 9452048c79404 ("bpf:
add TCP_SAVE_SYN/TCP_SAVED_SYN options for bpf_(set|get)sockopt").

Signed-off-by: Nikita V. Shirokov <tehnerd@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_tcpbpf_kern.c | 38 ++++++++++++++++++++++++--
 tools/testing/selftests/bpf/test_tcpbpf_user.c | 31 ++++++++++++++++++++-
 2 files changed, 65 insertions(+), 4 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
index 4b7fd540cea9..74f73b33a7b0 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf_kern.c
+++ b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
@@ -5,6 +5,7 @@
 #include <linux/if_ether.h>
 #include <linux/if_packet.h>
 #include <linux/ip.h>
+#include <linux/ipv6.h>
 #include <linux/types.h>
 #include <linux/socket.h>
 #include <linux/tcp.h>
@@ -17,6 +18,13 @@ struct bpf_map_def SEC("maps") global_map = {
 	.type = BPF_MAP_TYPE_ARRAY,
 	.key_size = sizeof(__u32),
 	.value_size = sizeof(struct tcpbpf_globals),
+	.max_entries = 4,
+};
+
+struct bpf_map_def SEC("maps") sockopt_results = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(int),
 	.max_entries = 2,
 };
 
@@ -45,11 +53,14 @@ int _version SEC("version") = 1;
 SEC("sockops")
 int bpf_testcb(struct bpf_sock_ops *skops)
 {
-	int rv = -1;
-	int bad_call_rv = 0;
+	char header[sizeof(struct ipv6hdr) + sizeof(struct tcphdr)];
+	struct tcphdr *thdr;
 	int good_call_rv = 0;
-	int op;
+	int bad_call_rv = 0;
+	int save_syn = 1;
+	int rv = -1;
 	int v = 0;
+	int op;
 
 	op = (int) skops->op;
 
@@ -82,6 +93,21 @@ int bpf_testcb(struct bpf_sock_ops *skops)
 		v = 0xff;
 		rv = bpf_setsockopt(skops, SOL_IPV6, IPV6_TCLASS, &v,
 				    sizeof(v));
+		if (skops->family == AF_INET6) {
+			v = bpf_getsockopt(skops, IPPROTO_TCP, TCP_SAVED_SYN,
+					   header, (sizeof(struct ipv6hdr) +
+						    sizeof(struct tcphdr)));
+			if (!v) {
+				int offset = sizeof(struct ipv6hdr);
+
+				thdr = (struct tcphdr *)(header + offset);
+				v = thdr->syn;
+				__u32 key = 1;
+
+				bpf_map_update_elem(&sockopt_results, &key, &v,
+						    BPF_ANY);
+			}
+		}
 		break;
 	case BPF_SOCK_OPS_RTO_CB:
 		break;
@@ -111,6 +137,12 @@ int bpf_testcb(struct bpf_sock_ops *skops)
 		break;
 	case BPF_SOCK_OPS_TCP_LISTEN_CB:
 		bpf_sock_ops_cb_flags_set(skops, BPF_SOCK_OPS_STATE_CB_FLAG);
+		v = bpf_setsockopt(skops, IPPROTO_TCP, TCP_SAVE_SYN,
+				   &save_syn, sizeof(save_syn));
+		/* Update global map w/ result of setsock opt */
+		__u32 key = 0;
+
+		bpf_map_update_elem(&sockopt_results, &key, &v, BPF_ANY);
 		break;
 	default:
 		rv = -1;
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c
index a275c2971376..e6eebda7d112 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf_user.c
+++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c
@@ -54,6 +54,26 @@ err:
 	return -1;
 }
 
+int verify_sockopt_result(int sock_map_fd)
+{
+	__u32 key = 0;
+	int res;
+	int rv;
+
+	/* check setsockopt for SAVE_SYN */
+	rv = bpf_map_lookup_elem(sock_map_fd, &key, &res);
+	EXPECT_EQ(0, rv, "d");
+	EXPECT_EQ(0, res, "d");
+	key = 1;
+	/* check getsockopt for SAVED_SYN */
+	rv = bpf_map_lookup_elem(sock_map_fd, &key, &res);
+	EXPECT_EQ(0, rv, "d");
+	EXPECT_EQ(1, res, "d");
+	return 0;
+err:
+	return -1;
+}
+
 static int bpf_find_map(const char *test, struct bpf_object *obj,
 			const char *name)
 {
@@ -70,11 +90,11 @@ static int bpf_find_map(const char *test, struct bpf_object *obj,
 int main(int argc, char **argv)
 {
 	const char *file = "test_tcpbpf_kern.o";
+	int prog_fd, map_fd, sock_map_fd;
 	struct tcpbpf_globals g = {0};
 	const char *cg_path = "/foo";
 	int error = EXIT_FAILURE;
 	struct bpf_object *obj;
-	int prog_fd, map_fd;
 	int cg_fd = -1;
 	__u32 key = 0;
 	int rv;
@@ -110,6 +130,10 @@ int main(int argc, char **argv)
 	if (map_fd < 0)
 		goto err;
 
+	sock_map_fd = bpf_find_map(__func__, obj, "sockopt_results");
+	if (sock_map_fd < 0)
+		goto err;
+
 	rv = bpf_map_lookup_elem(map_fd, &key, &g);
 	if (rv != 0) {
 		printf("FAILED: bpf_map_lookup_elem returns %d\n", rv);
@@ -121,6 +145,11 @@ int main(int argc, char **argv)
 		goto err;
 	}
 
+	if (verify_sockopt_result(sock_map_fd)) {
+		printf("FAILED: Wrong sockopt stats\n");
+		goto err;
+	}
+
 	printf("PASSED!\n");
 	error = 0;
 err:
-- 
cgit 


From 902b5417f28d955cdb4898df6ffaab15f56c5cff Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Thu, 30 Aug 2018 16:01:17 +0200
Subject: selftests: pmtu: maximum MTU for vti4 is 2^16-1-20

Since commit 82612de1c98e ("ip_tunnel: restore binding to ifaces with a
large mtu"), the maximum MTU for vti4 is based on IP_MAX_MTU instead of
the mysterious constant 0xFFF8.  This makes this selftest fail.

Fixes: 82612de1c98e ("ip_tunnel: restore binding to ifaces with a large mtu")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Stefano Brivio <sbrivio@redhat.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/pmtu.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index f8cc38afffa2..0ecf2609b9a4 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -334,7 +334,7 @@ test_pmtu_vti4_link_add_mtu() {
 	fail=0
 
 	min=68
-	max=$((65528 - 20))
+	max=$((65535 - 20))
 	# Check invalid values first
 	for v in $((min - 1)) $((max + 1)); do
 		${ns_a} ip link add vti4_a mtu ${v} type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10 2>/dev/null
-- 
cgit 


From c81c7012e0c769b5704c2b07bd5224965e76fb70 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Thu, 30 Aug 2018 16:01:18 +0200
Subject: selftests: pmtu: detect correct binary to ping ipv6 addresses

Some systems don't have the ping6 binary anymore, and use ping for
everything. Detect the absence of ping6 and try to use ping instead.

Fixes: d1f1b9cbf34c ("selftests: net: Introduce first PMTU test")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/pmtu.sh | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 0ecf2609b9a4..32a194e3e07a 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -46,6 +46,9 @@
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
 
+# Some systems don't have a ping6 binary anymore
+which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
+
 tests="
 	pmtu_vti6_exception		vti6: PMTU exceptions
 	pmtu_vti4_exception		vti4: PMTU exceptions
@@ -274,7 +277,7 @@ test_pmtu_vti6_exception() {
 	mtu "${ns_b}" veth_b 4000
 	mtu "${ns_a}" vti6_a 5000
 	mtu "${ns_b}" vti6_b 5000
-	${ns_a} ping6 -q -i 0.1 -w 2 -s 60000 ${vti6_b_addr} > /dev/null
+	${ns_a} ${ping6} -q -i 0.1 -w 2 -s 60000 ${vti6_b_addr} > /dev/null
 
 	# Check that exception was created
 	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" = "" ]; then
-- 
cgit 


From c2ad647c6442cf6730ffd86cbadbbce101dea937 Mon Sep 17 00:00:00 2001
From: Vakul Garg <vakul.garg@nxp.com>
Date: Wed, 29 Aug 2018 15:30:14 +0530
Subject: selftests/tls: Add test for recv(PEEK) spanning across multiple
 records

Added test case to receive multiple records with a single recvmsg()
operation with a MSG_PEEK set.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/tls.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index b3ebf2646e52..07daff076ce0 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -502,6 +502,28 @@ TEST_F(tls, recv_peek_multiple)
 	EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
 }
 
+TEST_F(tls, recv_peek_large_buf_mult_recs)
+{
+	char const *test_str = "test_read_peek_mult_recs";
+	char const *test_str_first = "test_read_peek";
+	char const *test_str_second = "_mult_recs";
+	int len;
+	char buf[64];
+
+	len = strlen(test_str_first);
+	EXPECT_EQ(send(self->fd, test_str_first, len, 0), len);
+
+	len = strlen(test_str_second) + 1;
+	EXPECT_EQ(send(self->fd, test_str_second, len, 0), len);
+
+	len = sizeof(buf);
+	memset(buf, 0, len);
+	EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1);
+
+	len = strlen(test_str) + 1;
+	EXPECT_EQ(memcmp(test_str, buf, len), 0);
+}
+
 TEST_F(tls, pollin)
 {
 	char const *test_str = "test_poll";
-- 
cgit 


From fbb0de795078190a9834b3409e4b009cfb18a6d4 Mon Sep 17 00:00:00 2001
From: Gerd Hoffmann <kraxel@redhat.com>
Date: Mon, 27 Aug 2018 11:34:44 +0200
Subject: Add udmabuf misc device

A driver to let userspace turn memfd regions into dma-bufs.

Use case:  Allows qemu create dmabufs for the vga framebuffer or
virtio-gpu ressources.  Then they can be passed around to display
those guest things on the host.  To spice client for classic full
framebuffer display, and hopefully some day to wayland server for
seamless guest window display.

qemu test branch:
  https://git.kraxel.org/cgit/qemu/log/?h=sirius/udmabuf

Cc: David Airlie <airlied@linux.ie>
Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/20180827093444.23623-1-kraxel@redhat.com
---
 Documentation/ioctl/ioctl-number.txt              |   1 +
 MAINTAINERS                                       |   8 +
 drivers/dma-buf/Kconfig                           |   8 +
 drivers/dma-buf/Makefile                          |   1 +
 drivers/dma-buf/udmabuf.c                         | 287 ++++++++++++++++++++++
 include/uapi/linux/udmabuf.h                      |  33 +++
 tools/testing/selftests/drivers/dma-buf/Makefile  |   5 +
 tools/testing/selftests/drivers/dma-buf/udmabuf.c |  96 ++++++++
 8 files changed, 439 insertions(+)
 create mode 100644 drivers/dma-buf/udmabuf.c
 create mode 100644 include/uapi/linux/udmabuf.h
 create mode 100644 tools/testing/selftests/drivers/dma-buf/Makefile
 create mode 100644 tools/testing/selftests/drivers/dma-buf/udmabuf.c

(limited to 'tools/testing')

diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 13a7c999c04a..f2ac672eb766 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -272,6 +272,7 @@ Code  Seq#(hex)	Include File		Comments
 't'	90-91	linux/toshiba.h		toshiba and toshiba_acpi SMM
 'u'	00-1F	linux/smb_fs.h		gone
 'u'	20-3F	linux/uvcvideo.h	USB video class host driver
+'u'	40-4f	linux/udmabuf.h		userspace dma-buf misc device
 'v'	00-1F	linux/ext2_fs.h		conflict!
 'v'	00-1F	linux/fs.h		conflict!
 'v'	00-0F	linux/sonypi.h		conflict!
diff --git a/MAINTAINERS b/MAINTAINERS
index a5b256b25905..9d9068ed4ee5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15343,6 +15343,14 @@ F:	arch/x86/um/
 F:	fs/hostfs/
 F:	fs/hppfs/
 
+USERSPACE DMA BUFFER DRIVER
+M:	Gerd Hoffmann <kraxel@redhat.com>
+S:	Maintained
+L:	dri-devel@lists.freedesktop.org
+F:	drivers/dma-buf/udmabuf.c
+F:	include/uapi/linux/udmabuf.h
+T:	git git://anongit.freedesktop.org/drm/drm-misc
+
 USERSPACE I/O (UIO)
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 S:	Maintained
diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig
index ed3b785bae37..338129eb126f 100644
--- a/drivers/dma-buf/Kconfig
+++ b/drivers/dma-buf/Kconfig
@@ -30,4 +30,12 @@ config SW_SYNC
 	  WARNING: improper use of this can result in deadlocking kernel
 	  drivers from userspace. Intended for test and debug only.
 
+config UDMABUF
+	bool "userspace dmabuf misc driver"
+	default n
+	depends on DMA_SHARED_BUFFER
+	help
+	  A driver to let userspace turn memfd regions into dma-bufs.
+	  Qemu can use this to create host dmabufs for guest framebuffers.
+
 endmenu
diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile
index c33bf8863147..0913a6ccab5a 100644
--- a/drivers/dma-buf/Makefile
+++ b/drivers/dma-buf/Makefile
@@ -1,3 +1,4 @@
 obj-y := dma-buf.o dma-fence.o dma-fence-array.o reservation.o seqno-fence.o
 obj-$(CONFIG_SYNC_FILE)		+= sync_file.o
 obj-$(CONFIG_SW_SYNC)		+= sw_sync.o sync_debug.o
+obj-$(CONFIG_UDMABUF)		+= udmabuf.o
diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
new file mode 100644
index 000000000000..8e24204526cc
--- /dev/null
+++ b/drivers/dma-buf/udmabuf.c
@@ -0,0 +1,287 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/miscdevice.h>
+#include <linux/dma-buf.h>
+#include <linux/highmem.h>
+#include <linux/cred.h>
+#include <linux/shmem_fs.h>
+#include <linux/memfd.h>
+
+#include <uapi/linux/udmabuf.h>
+
+struct udmabuf {
+	u32 pagecount;
+	struct page **pages;
+};
+
+static int udmabuf_vm_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct udmabuf *ubuf = vma->vm_private_data;
+
+	if (WARN_ON(vmf->pgoff >= ubuf->pagecount))
+		return VM_FAULT_SIGBUS;
+
+	vmf->page = ubuf->pages[vmf->pgoff];
+	get_page(vmf->page);
+	return 0;
+}
+
+static const struct vm_operations_struct udmabuf_vm_ops = {
+	.fault = udmabuf_vm_fault,
+};
+
+static int mmap_udmabuf(struct dma_buf *buf, struct vm_area_struct *vma)
+{
+	struct udmabuf *ubuf = buf->priv;
+
+	if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) == 0)
+		return -EINVAL;
+
+	vma->vm_ops = &udmabuf_vm_ops;
+	vma->vm_private_data = ubuf;
+	return 0;
+}
+
+static struct sg_table *map_udmabuf(struct dma_buf_attachment *at,
+				    enum dma_data_direction direction)
+{
+	struct udmabuf *ubuf = at->dmabuf->priv;
+	struct sg_table *sg;
+
+	sg = kzalloc(sizeof(*sg), GFP_KERNEL);
+	if (!sg)
+		goto err1;
+	if (sg_alloc_table_from_pages(sg, ubuf->pages, ubuf->pagecount,
+				      0, ubuf->pagecount << PAGE_SHIFT,
+				      GFP_KERNEL) < 0)
+		goto err2;
+	if (!dma_map_sg(at->dev, sg->sgl, sg->nents, direction))
+		goto err3;
+
+	return sg;
+
+err3:
+	sg_free_table(sg);
+err2:
+	kfree(sg);
+err1:
+	return ERR_PTR(-ENOMEM);
+}
+
+static void unmap_udmabuf(struct dma_buf_attachment *at,
+			  struct sg_table *sg,
+			  enum dma_data_direction direction)
+{
+	sg_free_table(sg);
+	kfree(sg);
+}
+
+static void release_udmabuf(struct dma_buf *buf)
+{
+	struct udmabuf *ubuf = buf->priv;
+	pgoff_t pg;
+
+	for (pg = 0; pg < ubuf->pagecount; pg++)
+		put_page(ubuf->pages[pg]);
+	kfree(ubuf->pages);
+	kfree(ubuf);
+}
+
+static void *kmap_udmabuf(struct dma_buf *buf, unsigned long page_num)
+{
+	struct udmabuf *ubuf = buf->priv;
+	struct page *page = ubuf->pages[page_num];
+
+	return kmap(page);
+}
+
+static void kunmap_udmabuf(struct dma_buf *buf, unsigned long page_num,
+			   void *vaddr)
+{
+	kunmap(vaddr);
+}
+
+static struct dma_buf_ops udmabuf_ops = {
+	.map_dma_buf	  = map_udmabuf,
+	.unmap_dma_buf	  = unmap_udmabuf,
+	.release	  = release_udmabuf,
+	.map		  = kmap_udmabuf,
+	.unmap		  = kunmap_udmabuf,
+	.mmap		  = mmap_udmabuf,
+};
+
+#define SEALS_WANTED (F_SEAL_SHRINK)
+#define SEALS_DENIED (F_SEAL_WRITE)
+
+static long udmabuf_create(struct udmabuf_create_list *head,
+			   struct udmabuf_create_item *list)
+{
+	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
+	struct file *memfd = NULL;
+	struct udmabuf *ubuf;
+	struct dma_buf *buf;
+	pgoff_t pgoff, pgcnt, pgidx, pgbuf;
+	struct page *page;
+	int seals, ret = -EINVAL;
+	u32 i, flags;
+
+	ubuf = kzalloc(sizeof(struct udmabuf), GFP_KERNEL);
+	if (!ubuf)
+		return -ENOMEM;
+
+	for (i = 0; i < head->count; i++) {
+		if (!IS_ALIGNED(list[i].offset, PAGE_SIZE))
+			goto err_free_ubuf;
+		if (!IS_ALIGNED(list[i].size, PAGE_SIZE))
+			goto err_free_ubuf;
+		ubuf->pagecount += list[i].size >> PAGE_SHIFT;
+	}
+	ubuf->pages = kmalloc_array(ubuf->pagecount, sizeof(struct page *),
+				    GFP_KERNEL);
+	if (!ubuf->pages) {
+		ret = -ENOMEM;
+		goto err_free_ubuf;
+	}
+
+	pgbuf = 0;
+	for (i = 0; i < head->count; i++) {
+		memfd = fget(list[i].memfd);
+		if (!memfd)
+			goto err_put_pages;
+		if (!shmem_mapping(file_inode(memfd)->i_mapping))
+			goto err_put_pages;
+		seals = memfd_fcntl(memfd, F_GET_SEALS, 0);
+		if (seals == -EINVAL ||
+		    (seals & SEALS_WANTED) != SEALS_WANTED ||
+		    (seals & SEALS_DENIED) != 0)
+			goto err_put_pages;
+		pgoff = list[i].offset >> PAGE_SHIFT;
+		pgcnt = list[i].size   >> PAGE_SHIFT;
+		for (pgidx = 0; pgidx < pgcnt; pgidx++) {
+			page = shmem_read_mapping_page(
+				file_inode(memfd)->i_mapping, pgoff + pgidx);
+			if (IS_ERR(page)) {
+				ret = PTR_ERR(page);
+				goto err_put_pages;
+			}
+			ubuf->pages[pgbuf++] = page;
+		}
+		fput(memfd);
+	}
+	memfd = NULL;
+
+	exp_info.ops  = &udmabuf_ops;
+	exp_info.size = ubuf->pagecount << PAGE_SHIFT;
+	exp_info.priv = ubuf;
+
+	buf = dma_buf_export(&exp_info);
+	if (IS_ERR(buf)) {
+		ret = PTR_ERR(buf);
+		goto err_put_pages;
+	}
+
+	flags = 0;
+	if (head->flags & UDMABUF_FLAGS_CLOEXEC)
+		flags |= O_CLOEXEC;
+	return dma_buf_fd(buf, flags);
+
+err_put_pages:
+	while (pgbuf > 0)
+		put_page(ubuf->pages[--pgbuf]);
+err_free_ubuf:
+	fput(memfd);
+	kfree(ubuf->pages);
+	kfree(ubuf);
+	return ret;
+}
+
+static long udmabuf_ioctl_create(struct file *filp, unsigned long arg)
+{
+	struct udmabuf_create create;
+	struct udmabuf_create_list head;
+	struct udmabuf_create_item list;
+
+	if (copy_from_user(&create, (void __user *)arg,
+			   sizeof(struct udmabuf_create)))
+		return -EFAULT;
+
+	head.flags  = create.flags;
+	head.count  = 1;
+	list.memfd  = create.memfd;
+	list.offset = create.offset;
+	list.size   = create.size;
+
+	return udmabuf_create(&head, &list);
+}
+
+static long udmabuf_ioctl_create_list(struct file *filp, unsigned long arg)
+{
+	struct udmabuf_create_list head;
+	struct udmabuf_create_item *list;
+	int ret = -EINVAL;
+	u32 lsize;
+
+	if (copy_from_user(&head, (void __user *)arg, sizeof(head)))
+		return -EFAULT;
+	if (head.count > 1024)
+		return -EINVAL;
+	lsize = sizeof(struct udmabuf_create_item) * head.count;
+	list = memdup_user((void __user *)(arg + sizeof(head)), lsize);
+	if (IS_ERR(list))
+		return PTR_ERR(list);
+
+	ret = udmabuf_create(&head, list);
+	kfree(list);
+	return ret;
+}
+
+static long udmabuf_ioctl(struct file *filp, unsigned int ioctl,
+			  unsigned long arg)
+{
+	long ret;
+
+	switch (ioctl) {
+	case UDMABUF_CREATE:
+		ret = udmabuf_ioctl_create(filp, arg);
+		break;
+	case UDMABUF_CREATE_LIST:
+		ret = udmabuf_ioctl_create_list(filp, arg);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+	return ret;
+}
+
+static const struct file_operations udmabuf_fops = {
+	.owner		= THIS_MODULE,
+	.unlocked_ioctl = udmabuf_ioctl,
+};
+
+static struct miscdevice udmabuf_misc = {
+	.minor          = MISC_DYNAMIC_MINOR,
+	.name           = "udmabuf",
+	.fops           = &udmabuf_fops,
+};
+
+static int __init udmabuf_dev_init(void)
+{
+	return misc_register(&udmabuf_misc);
+}
+
+static void __exit udmabuf_dev_exit(void)
+{
+	misc_deregister(&udmabuf_misc);
+}
+
+module_init(udmabuf_dev_init)
+module_exit(udmabuf_dev_exit)
+
+MODULE_AUTHOR("Gerd Hoffmann <kraxel@redhat.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/include/uapi/linux/udmabuf.h b/include/uapi/linux/udmabuf.h
new file mode 100644
index 000000000000..46b6532ed855
--- /dev/null
+++ b/include/uapi/linux/udmabuf.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_UDMABUF_H
+#define _UAPI_LINUX_UDMABUF_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#define UDMABUF_FLAGS_CLOEXEC	0x01
+
+struct udmabuf_create {
+	__u32 memfd;
+	__u32 flags;
+	__u64 offset;
+	__u64 size;
+};
+
+struct udmabuf_create_item {
+	__u32 memfd;
+	__u32 __pad;
+	__u64 offset;
+	__u64 size;
+};
+
+struct udmabuf_create_list {
+	__u32 flags;
+	__u32 count;
+	struct udmabuf_create_item list[];
+};
+
+#define UDMABUF_CREATE       _IOW('u', 0x42, struct udmabuf_create)
+#define UDMABUF_CREATE_LIST  _IOW('u', 0x43, struct udmabuf_create_list)
+
+#endif /* _UAPI_LINUX_UDMABUF_H */
diff --git a/tools/testing/selftests/drivers/dma-buf/Makefile b/tools/testing/selftests/drivers/dma-buf/Makefile
new file mode 100644
index 000000000000..4154c3d7aa58
--- /dev/null
+++ b/tools/testing/selftests/drivers/dma-buf/Makefile
@@ -0,0 +1,5 @@
+CFLAGS += -I../../../../../usr/include/
+
+TEST_GEN_PROGS := udmabuf
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/drivers/dma-buf/udmabuf.c b/tools/testing/selftests/drivers/dma-buf/udmabuf.c
new file mode 100644
index 000000000000..376b1d6730bd
--- /dev/null
+++ b/tools/testing/selftests/drivers/dma-buf/udmabuf.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <malloc.h>
+
+#include <sys/ioctl.h>
+#include <sys/syscall.h>
+#include <linux/memfd.h>
+#include <linux/udmabuf.h>
+
+#define TEST_PREFIX	"drivers/dma-buf/udmabuf"
+#define NUM_PAGES       4
+
+static int memfd_create(const char *name, unsigned int flags)
+{
+	return syscall(__NR_memfd_create, name, flags);
+}
+
+int main(int argc, char *argv[])
+{
+	struct udmabuf_create create;
+	int devfd, memfd, buf, ret;
+	off_t size;
+	void *mem;
+
+	devfd = open("/dev/udmabuf", O_RDWR);
+	if (devfd < 0) {
+		printf("%s: [skip,no-udmabuf]\n", TEST_PREFIX);
+		exit(77);
+	}
+
+	memfd = memfd_create("udmabuf-test", MFD_CLOEXEC);
+	if (memfd < 0) {
+		printf("%s: [skip,no-memfd]\n", TEST_PREFIX);
+		exit(77);
+	}
+
+	size = getpagesize() * NUM_PAGES;
+	ret = ftruncate(memfd, size);
+	if (ret == -1) {
+		printf("%s: [FAIL,memfd-truncate]\n", TEST_PREFIX);
+		exit(1);
+	}
+
+	memset(&create, 0, sizeof(create));
+
+	/* should fail (offset not page aligned) */
+	create.memfd  = memfd;
+	create.offset = getpagesize()/2;
+	create.size   = getpagesize();
+	buf = ioctl(devfd, UDMABUF_CREATE, &create);
+	if (buf >= 0) {
+		printf("%s: [FAIL,test-1]\n", TEST_PREFIX);
+		exit(1);
+	}
+
+	/* should fail (size not multiple of page) */
+	create.memfd  = memfd;
+	create.offset = 0;
+	create.size   = getpagesize()/2;
+	buf = ioctl(devfd, UDMABUF_CREATE, &create);
+	if (buf >= 0) {
+		printf("%s: [FAIL,test-2]\n", TEST_PREFIX);
+		exit(1);
+	}
+
+	/* should fail (not memfd) */
+	create.memfd  = 0; /* stdin */
+	create.offset = 0;
+	create.size   = size;
+	buf = ioctl(devfd, UDMABUF_CREATE, &create);
+	if (buf >= 0) {
+		printf("%s: [FAIL,test-3]\n", TEST_PREFIX);
+		exit(1);
+	}
+
+	/* should work */
+	create.memfd  = memfd;
+	create.offset = 0;
+	create.size   = size;
+	buf = ioctl(devfd, UDMABUF_CREATE, &create);
+	if (buf < 0) {
+		printf("%s: [FAIL,test-4]\n", TEST_PREFIX);
+		exit(1);
+	}
+
+	fprintf(stderr, "%s: ok\n", TEST_PREFIX);
+	close(buf);
+	close(memfd);
+	close(devfd);
+	return 0;
+}
-- 
cgit 


From b2d35fa5fc80c27e868e393dcab4c94a0d71737f Mon Sep 17 00:00:00 2001
From: Anders Roxell <anders.roxell@linaro.org>
Date: Tue, 4 Sep 2018 12:47:21 +0200
Subject: selftests: add headers_install to lib.mk

If the kernel headers aren't installed we can't build all the tests.
Add a new make target rule 'khdr' in the file lib.mk to generate the
kernel headers and that gets include for every test-dir Makefile that
includes lib.mk If the testdir in turn have its own sub-dirs the
top_srcdir needs to be set to the linux-rootdir to be able to generate
the kernel headers.

Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Reviewed-by: Fathi Boudra <fathi.boudra@linaro.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 Makefile                                                 | 14 +-------------
 scripts/subarch.include                                  | 13 +++++++++++++
 tools/testing/selftests/android/Makefile                 |  2 +-
 tools/testing/selftests/android/ion/Makefile             |  2 ++
 tools/testing/selftests/futex/functional/Makefile        |  1 +
 tools/testing/selftests/gpio/Makefile                    |  7 ++-----
 tools/testing/selftests/kvm/Makefile                     |  7 ++-----
 tools/testing/selftests/lib.mk                           | 12 ++++++++++++
 tools/testing/selftests/net/Makefile                     |  1 +
 tools/testing/selftests/networking/timestamping/Makefile |  1 +
 tools/testing/selftests/vm/Makefile                      |  4 ----
 11 files changed, 36 insertions(+), 28 deletions(-)
 create mode 100644 scripts/subarch.include

(limited to 'tools/testing')

diff --git a/Makefile b/Makefile
index 2b458801ba74..8b3fbdb2759b 100644
--- a/Makefile
+++ b/Makefile
@@ -299,19 +299,7 @@ KERNELRELEASE = $(shell cat include/config/kernel.release 2> /dev/null)
 KERNELVERSION = $(VERSION)$(if $(PATCHLEVEL),.$(PATCHLEVEL)$(if $(SUBLEVEL),.$(SUBLEVEL)))$(EXTRAVERSION)
 export VERSION PATCHLEVEL SUBLEVEL KERNELRELEASE KERNELVERSION
 
-# SUBARCH tells the usermode build what the underlying arch is.  That is set
-# first, and if a usermode build is happening, the "ARCH=um" on the command
-# line overrides the setting of ARCH below.  If a native build is happening,
-# then ARCH is assigned, getting whatever value it gets normally, and
-# SUBARCH is subsequently ignored.
-
-SUBARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
-				  -e s/sun4u/sparc64/ \
-				  -e s/arm.*/arm/ -e s/sa110/arm/ \
-				  -e s/s390x/s390/ -e s/parisc64/parisc/ \
-				  -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
-				  -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \
-				  -e s/riscv.*/riscv/)
+include scripts/subarch.include
 
 # Cross compiling and selecting different set of gcc/bin-utils
 # ---------------------------------------------------------------------------
diff --git a/scripts/subarch.include b/scripts/subarch.include
new file mode 100644
index 000000000000..650682821126
--- /dev/null
+++ b/scripts/subarch.include
@@ -0,0 +1,13 @@
+# SUBARCH tells the usermode build what the underlying arch is.  That is set
+# first, and if a usermode build is happening, the "ARCH=um" on the command
+# line overrides the setting of ARCH below.  If a native build is happening,
+# then ARCH is assigned, getting whatever value it gets normally, and
+# SUBARCH is subsequently ignored.
+
+SUBARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
+				  -e s/sun4u/sparc64/ \
+				  -e s/arm.*/arm/ -e s/sa110/arm/ \
+				  -e s/s390x/s390/ -e s/parisc64/parisc/ \
+				  -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
+				  -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \
+				  -e s/riscv.*/riscv/)
diff --git a/tools/testing/selftests/android/Makefile b/tools/testing/selftests/android/Makefile
index 72c25a3cb658..d9a725478375 100644
--- a/tools/testing/selftests/android/Makefile
+++ b/tools/testing/selftests/android/Makefile
@@ -6,7 +6,7 @@ TEST_PROGS := run.sh
 
 include ../lib.mk
 
-all:
+all: khdr
 	@for DIR in $(SUBDIRS); do		\
 		BUILD_TARGET=$(OUTPUT)/$$DIR;	\
 		mkdir $$BUILD_TARGET  -p;	\
diff --git a/tools/testing/selftests/android/ion/Makefile b/tools/testing/selftests/android/ion/Makefile
index e03695287f76..88cfe88e466f 100644
--- a/tools/testing/selftests/android/ion/Makefile
+++ b/tools/testing/selftests/android/ion/Makefile
@@ -10,6 +10,8 @@ $(TEST_GEN_FILES): ipcsocket.c ionutils.c
 
 TEST_PROGS := ion_test.sh
 
+KSFT_KHDR_INSTALL := 1
+top_srcdir = ../../../../..
 include ../../lib.mk
 
 $(OUTPUT)/ionapp_export: ionapp_export.c ipcsocket.c ionutils.c
diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile
index ff8feca49746..ad1eeb14fda7 100644
--- a/tools/testing/selftests/futex/functional/Makefile
+++ b/tools/testing/selftests/futex/functional/Makefile
@@ -18,6 +18,7 @@ TEST_GEN_FILES := \
 
 TEST_PROGS := run.sh
 
+top_srcdir = ../../../../..
 include ../../lib.mk
 
 $(TEST_GEN_FILES): $(HEADERS)
diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile
index 1bbb47565c55..4665cdbf1a8d 100644
--- a/tools/testing/selftests/gpio/Makefile
+++ b/tools/testing/selftests/gpio/Makefile
@@ -21,11 +21,8 @@ endef
 CFLAGS += -O2 -g -std=gnu99 -Wall -I../../../../usr/include/
 LDLIBS += -lmount -I/usr/include/libmount
 
-$(BINARIES): ../../../gpio/gpio-utils.o ../../../../usr/include/linux/gpio.h
+$(BINARIES):| khdr
+$(BINARIES): ../../../gpio/gpio-utils.o
 
 ../../../gpio/gpio-utils.o:
 	make ARCH=$(ARCH) CROSS_COMPILE=$(CROSS_COMPILE) -C ../../../gpio
-
-../../../../usr/include/linux/gpio.h:
-	make -C ../../../.. headers_install INSTALL_HDR_PATH=$(shell pwd)/../../../../usr/
-
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 03b0f551bedf..87d1a8488af8 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -37,9 +37,6 @@ $(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c
 $(OUTPUT)/libkvm.a: $(LIBKVM_OBJ)
 	$(AR) crs $@ $^
 
-$(LINUX_HDR_PATH):
-	make -C $(top_srcdir) headers_install
-
-all: $(STATIC_LIBS) $(LINUX_HDR_PATH)
+all: $(STATIC_LIBS)
 $(TEST_GEN_PROGS): $(STATIC_LIBS)
-$(TEST_GEN_PROGS) $(LIBKVM_OBJ): | $(LINUX_HDR_PATH)
+$(STATIC_LIBS):| khdr
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 17ab36605a8e..0a8e75886224 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -16,8 +16,20 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS))
 TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED))
 TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES))
 
+top_srcdir ?= ../../../..
+include $(top_srcdir)/scripts/subarch.include
+ARCH		?= $(SUBARCH)
+
 all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
 
+.PHONY: khdr
+khdr:
+	make ARCH=$(ARCH) -C $(top_srcdir) headers_install
+
+ifdef KSFT_KHDR_INSTALL
+$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES):| khdr
+endif
+
 .ONESHELL:
 define RUN_TEST_PRINT_RESULT
 	TEST_HDR_MSG="selftests: "`basename $$PWD`:" $$BASENAME_TEST";	\
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 9cca68e440a0..919aa2ac00af 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -15,6 +15,7 @@ TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
 TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
 
+KSFT_KHDR_INSTALL := 1
 include ../lib.mk
 
 $(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma
diff --git a/tools/testing/selftests/networking/timestamping/Makefile b/tools/testing/selftests/networking/timestamping/Makefile
index a728040edbe1..14cfcf006936 100644
--- a/tools/testing/selftests/networking/timestamping/Makefile
+++ b/tools/testing/selftests/networking/timestamping/Makefile
@@ -5,6 +5,7 @@ TEST_PROGS := hwtstamp_config rxtimestamp timestamping txtimestamp
 
 all: $(TEST_PROGS)
 
+top_srcdir = ../../../../..
 include ../../lib.mk
 
 clean:
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 9881876d2aa0..e94b7b14bcb2 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -26,10 +26,6 @@ TEST_PROGS := run_vmtests
 
 include ../lib.mk
 
-$(OUTPUT)/userfaultfd: ../../../../usr/include/linux/kernel.h
 $(OUTPUT)/userfaultfd: LDLIBS += -lpthread
 
 $(OUTPUT)/mlock-random-test: LDLIBS += -lcap
-
-../../../../usr/include/linux/kernel.h:
-	make -C ../../../.. headers_install
-- 
cgit 


From 53cf59d6c0ad3edc4f4449098706a8f8986258b6 Mon Sep 17 00:00:00 2001
From: Lei Yang <Lei.Yang@windriver.com>
Date: Wed, 5 Sep 2018 11:14:49 +0800
Subject: selftests/efivarfs: add required kernel configs

add config file

Signed-off-by: Lei Yang <Lei.Yang@windriver.com>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/efivarfs/config | 1 +
 1 file changed, 1 insertion(+)
 create mode 100644 tools/testing/selftests/efivarfs/config

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/efivarfs/config b/tools/testing/selftests/efivarfs/config
new file mode 100644
index 000000000000..4e151f1005b2
--- /dev/null
+++ b/tools/testing/selftests/efivarfs/config
@@ -0,0 +1 @@
+CONFIG_EFIVAR_FS=y
-- 
cgit 


From 4d85af102a66ee6aeefa596f273169e77fb2b48e Mon Sep 17 00:00:00 2001
From: Lei Yang <Lei.Yang@windriver.com>
Date: Wed, 5 Sep 2018 17:57:15 +0800
Subject: selftests: memory-hotplug: add required configs

add CONFIG_MEMORY_HOTREMOVE=y in config
without this config, /sys/devices/system/memory/memory*/removable
always return 0, I endup getting an early skip during test

Signed-off-by: Lei Yang <Lei.Yang@windriver.com>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/memory-hotplug/config | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/memory-hotplug/config b/tools/testing/selftests/memory-hotplug/config
index 2fde30191a47..a7e8cd5bb265 100644
--- a/tools/testing/selftests/memory-hotplug/config
+++ b/tools/testing/selftests/memory-hotplug/config
@@ -2,3 +2,4 @@ CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTPLUG_SPARSE=y
 CONFIG_NOTIFIER_ERROR_INJECTION=y
 CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m
+CONFIG_MEMORY_HOTREMOVE=y
-- 
cgit 


From 7035c568999d6774ff35459a0280eb33e0207168 Mon Sep 17 00:00:00 2001
From: Lei Yang <Lei.Yang@windriver.com>
Date: Thu, 6 Sep 2018 13:47:23 +0800
Subject: cgroup: kselftests: add test_core to .gitignore

Update .gitignore file.

Signed-off-by: Lei Yang <Lei.Yang@windriver.com>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/cgroup/.gitignore | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/cgroup/.gitignore b/tools/testing/selftests/cgroup/.gitignore
index 95eb3a53c381..adacda50a4b2 100644
--- a/tools/testing/selftests/cgroup/.gitignore
+++ b/tools/testing/selftests/cgroup/.gitignore
@@ -1 +1,2 @@
 test_memcontrol
+test_core
-- 
cgit 


From ad1242d8a063ceb8c6e1b9c1a63b73ec94fa0295 Mon Sep 17 00:00:00 2001
From: Mauricio Vasquez B <mauricio.vasquez@polito.it>
Date: Mon, 3 Sep 2018 18:05:27 +0200
Subject: selftests/bpf: add missing executables to .gitignore

Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/.gitignore | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 49938d72cf63..4d789c1e5167 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -19,3 +19,7 @@ test_btf
 test_sockmap
 test_lirc_mode2_user
 get_cgroup_id_user
+test_skb_cgroup_id_user
+test_socket_cookie
+test_cgroup_storage
+test_select_reuseport
-- 
cgit 


From f5bd3948eb07e76fcd73d0b8ab7b3265be226038 Mon Sep 17 00:00:00 2001
From: Mauricio Vasquez B <mauricio.vasquez@polito.it>
Date: Mon, 3 Sep 2018 19:01:59 +0200
Subject: selftests/bpf/test_progs: do not check errno == 0

The errno man page states: "The value in errno is significant only when
the return value of the call indicated an error..." then it is not correct
to check it, it could be different than zero even if the function
succeeded.

It causes some false positives if errno is set by a previous function.

Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_progs.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 0ef68204c84b..63a671803ed6 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -112,13 +112,13 @@ static void test_pkt_access(void)
 
 	err = bpf_prog_test_run(prog_fd, 100000, &pkt_v4, sizeof(pkt_v4),
 				NULL, NULL, &retval, &duration);
-	CHECK(err || errno || retval, "ipv4",
+	CHECK(err || retval, "ipv4",
 	      "err %d errno %d retval %d duration %d\n",
 	      err, errno, retval, duration);
 
 	err = bpf_prog_test_run(prog_fd, 100000, &pkt_v6, sizeof(pkt_v6),
 				NULL, NULL, &retval, &duration);
-	CHECK(err || errno || retval, "ipv6",
+	CHECK(err || retval, "ipv6",
 	      "err %d errno %d retval %d duration %d\n",
 	      err, errno, retval, duration);
 	bpf_object__close(obj);
@@ -153,14 +153,14 @@ static void test_xdp(void)
 	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
 				buf, &size, &retval, &duration);
 
-	CHECK(err || errno || retval != XDP_TX || size != 74 ||
+	CHECK(err || retval != XDP_TX || size != 74 ||
 	      iph->protocol != IPPROTO_IPIP, "ipv4",
 	      "err %d errno %d retval %d size %d\n",
 	      err, errno, retval, size);
 
 	err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6),
 				buf, &size, &retval, &duration);
-	CHECK(err || errno || retval != XDP_TX || size != 114 ||
+	CHECK(err || retval != XDP_TX || size != 114 ||
 	      iph6->nexthdr != IPPROTO_IPV6, "ipv6",
 	      "err %d errno %d retval %d size %d\n",
 	      err, errno, retval, size);
@@ -185,13 +185,13 @@ static void test_xdp_adjust_tail(void)
 	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
 				buf, &size, &retval, &duration);
 
-	CHECK(err || errno || retval != XDP_DROP,
+	CHECK(err || retval != XDP_DROP,
 	      "ipv4", "err %d errno %d retval %d size %d\n",
 	      err, errno, retval, size);
 
 	err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6),
 				buf, &size, &retval, &duration);
-	CHECK(err || errno || retval != XDP_TX || size != 54,
+	CHECK(err || retval != XDP_TX || size != 54,
 	      "ipv6", "err %d errno %d retval %d size %d\n",
 	      err, errno, retval, size);
 	bpf_object__close(obj);
@@ -254,14 +254,14 @@ static void test_l4lb(const char *file)
 
 	err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v4, sizeof(pkt_v4),
 				buf, &size, &retval, &duration);
-	CHECK(err || errno || retval != 7/*TC_ACT_REDIRECT*/ || size != 54 ||
+	CHECK(err || retval != 7/*TC_ACT_REDIRECT*/ || size != 54 ||
 	      *magic != MAGIC_VAL, "ipv4",
 	      "err %d errno %d retval %d size %d magic %x\n",
 	      err, errno, retval, size, *magic);
 
 	err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v6, sizeof(pkt_v6),
 				buf, &size, &retval, &duration);
-	CHECK(err || errno || retval != 7/*TC_ACT_REDIRECT*/ || size != 74 ||
+	CHECK(err || retval != 7/*TC_ACT_REDIRECT*/ || size != 74 ||
 	      *magic != MAGIC_VAL, "ipv6",
 	      "err %d errno %d retval %d size %d magic %x\n",
 	      err, errno, retval, size, *magic);
@@ -343,14 +343,14 @@ static void test_xdp_noinline(void)
 
 	err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v4, sizeof(pkt_v4),
 				buf, &size, &retval, &duration);
-	CHECK(err || errno || retval != 1 || size != 54 ||
+	CHECK(err || retval != 1 || size != 54 ||
 	      *magic != MAGIC_VAL, "ipv4",
 	      "err %d errno %d retval %d size %d magic %x\n",
 	      err, errno, retval, size, *magic);
 
 	err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v6, sizeof(pkt_v6),
 				buf, &size, &retval, &duration);
-	CHECK(err || errno || retval != 1 || size != 74 ||
+	CHECK(err || retval != 1 || size != 74 ||
 	      *magic != MAGIC_VAL, "ipv6",
 	      "err %d errno %d retval %d size %d magic %x\n",
 	      err, errno, retval, size, *magic);
-- 
cgit 


From 48c2bb0b9cf863e0ed78e269f188ce65b73e0fd1 Mon Sep 17 00:00:00 2001
From: Jay Kamat <jgkamat@fb.com>
Date: Fri, 7 Sep 2018 14:34:04 -0700
Subject: Fix cg_read_strcmp()

Fix a couple issues with cg_read_strcmp(), to improve correctness of
cgroup tests
- Fix cg_read_strcmp() always returning 0 for empty "needle" strings.
Previously, this function read to a size = 1 buffer when comparing
against empty strings, which would lead to cg_read_strcmp() comparing
two empty strings.
- Fix a memory leak in cg_read_strcmp()

Fixes: 84092dbcf901 ("selftests: cgroup: add memory controller self-tests")

Signed-off-by: Jay Kamat <jgkamat@fb.com>
Acked-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/cgroup/cgroup_util.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c
index 1c5d2b2a583b..f857def9a9e6 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/cgroup_util.c
@@ -89,17 +89,28 @@ int cg_read(const char *cgroup, const char *control, char *buf, size_t len)
 int cg_read_strcmp(const char *cgroup, const char *control,
 		   const char *expected)
 {
-	size_t size = strlen(expected) + 1;
+	size_t size;
 	char *buf;
+	int ret;
+
+	/* Handle the case of comparing against empty string */
+	if (!expected)
+		size = 32;
+	else
+		size = strlen(expected) + 1;
 
 	buf = malloc(size);
 	if (!buf)
 		return -1;
 
-	if (cg_read(cgroup, control, buf, size))
+	if (cg_read(cgroup, control, buf, size)) {
+		free(buf);
 		return -1;
+	}
 
-	return strcmp(expected, buf);
+	ret = strcmp(expected, buf);
+	free(buf);
+	return ret;
 }
 
 int cg_read_strstr(const char *cgroup, const char *control, const char *needle)
-- 
cgit 


From a987785dcd6c8ae2915460582aebd6481c81eb67 Mon Sep 17 00:00:00 2001
From: Jay Kamat <jgkamat@fb.com>
Date: Fri, 7 Sep 2018 14:34:05 -0700
Subject: Add tests for memory.oom.group

Add tests for memory.oom.group for the following cases:
- Killing all processes in a leaf cgroup, but leaving the
  parent untouched
- Killing all processes in a parent and leaf cgroup
- Keeping processes marked by OOM_SCORE_ADJ_MIN alive when considered
  for being killed by the group oom killer.

Signed-off-by: Jay Kamat <jgkamat@fb.com>
Acked-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/cgroup/cgroup_util.c     |  21 +++
 tools/testing/selftests/cgroup/cgroup_util.h     |   1 +
 tools/testing/selftests/cgroup/test_memcontrol.c | 205 +++++++++++++++++++++++
 3 files changed, 227 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c
index f857def9a9e6..14c9fe284806 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/cgroup_util.c
@@ -348,3 +348,24 @@ int is_swap_enabled(void)
 
 	return cnt > 1;
 }
+
+int set_oom_adj_score(int pid, int score)
+{
+	char path[PATH_MAX];
+	int fd, len;
+
+	sprintf(path, "/proc/%d/oom_score_adj", pid);
+
+	fd = open(path, O_WRONLY | O_APPEND);
+	if (fd < 0)
+		return fd;
+
+	len = dprintf(fd, "%d", score);
+	if (len < 0) {
+		close(fd);
+		return len;
+	}
+
+	close(fd);
+	return 0;
+}
diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h
index 1ff6f9f1abdc..9ac8b7958f83 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/cgroup_util.h
@@ -40,3 +40,4 @@ extern int get_temp_fd(void);
 extern int alloc_pagecache(int fd, size_t size);
 extern int alloc_anon(const char *cgroup, void *arg);
 extern int is_swap_enabled(void);
+extern int set_oom_adj_score(int pid, int score);
diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
index cf0bddc9d271..28d321ba311b 100644
--- a/tools/testing/selftests/cgroup/test_memcontrol.c
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -2,6 +2,7 @@
 #define _GNU_SOURCE
 
 #include <linux/limits.h>
+#include <linux/oom.h>
 #include <fcntl.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -202,6 +203,36 @@ static int alloc_pagecache_50M_noexit(const char *cgroup, void *arg)
 	return 0;
 }
 
+static int alloc_anon_noexit(const char *cgroup, void *arg)
+{
+	int ppid = getppid();
+
+	if (alloc_anon(cgroup, arg))
+		return -1;
+
+	while (getppid() == ppid)
+		sleep(1);
+
+	return 0;
+}
+
+/*
+ * Wait until processes are killed asynchronously by the OOM killer
+ * If we exceed a timeout, fail.
+ */
+static int cg_test_proc_killed(const char *cgroup)
+{
+	int limit;
+
+	for (limit = 10; limit > 0; limit--) {
+		if (cg_read_strcmp(cgroup, "cgroup.procs", "") == 0)
+			return 0;
+
+		usleep(100000);
+	}
+	return -1;
+}
+
 /*
  * First, this test creates the following hierarchy:
  * A       memory.min = 50M,  memory.max = 200M
@@ -964,6 +995,177 @@ cleanup:
 	return ret;
 }
 
+/*
+ * This test disables swapping and tries to allocate anonymous memory
+ * up to OOM with memory.group.oom set. Then it checks that all
+ * processes in the leaf (but not the parent) were killed.
+ */
+static int test_memcg_oom_group_leaf_events(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent, *child;
+
+	parent = cg_name(root, "memcg_test_0");
+	child = cg_name(root, "memcg_test_0/memcg_test_1");
+
+	if (!parent || !child)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_create(child))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (cg_write(child, "memory.max", "50M"))
+		goto cleanup;
+
+	if (cg_write(child, "memory.swap.max", "0"))
+		goto cleanup;
+
+	if (cg_write(child, "memory.oom.group", "1"))
+		goto cleanup;
+
+	cg_run_nowait(parent, alloc_anon_noexit, (void *) MB(60));
+	cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1));
+	cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1));
+	if (!cg_run(child, alloc_anon, (void *)MB(100)))
+		goto cleanup;
+
+	if (cg_test_proc_killed(child))
+		goto cleanup;
+
+	if (cg_read_key_long(child, "memory.events", "oom_kill ") <= 0)
+		goto cleanup;
+
+	if (cg_read_key_long(parent, "memory.events", "oom_kill ") != 0)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (child)
+		cg_destroy(child);
+	if (parent)
+		cg_destroy(parent);
+	free(child);
+	free(parent);
+
+	return ret;
+}
+
+/*
+ * This test disables swapping and tries to allocate anonymous memory
+ * up to OOM with memory.group.oom set. Then it checks that all
+ * processes in the parent and leaf were killed.
+ */
+static int test_memcg_oom_group_parent_events(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent, *child;
+
+	parent = cg_name(root, "memcg_test_0");
+	child = cg_name(root, "memcg_test_0/memcg_test_1");
+
+	if (!parent || !child)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_create(child))
+		goto cleanup;
+
+	if (cg_write(parent, "memory.max", "80M"))
+		goto cleanup;
+
+	if (cg_write(parent, "memory.swap.max", "0"))
+		goto cleanup;
+
+	if (cg_write(parent, "memory.oom.group", "1"))
+		goto cleanup;
+
+	cg_run_nowait(parent, alloc_anon_noexit, (void *) MB(60));
+	cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1));
+	cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1));
+
+	if (!cg_run(child, alloc_anon, (void *)MB(100)))
+		goto cleanup;
+
+	if (cg_test_proc_killed(child))
+		goto cleanup;
+	if (cg_test_proc_killed(parent))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (child)
+		cg_destroy(child);
+	if (parent)
+		cg_destroy(parent);
+	free(child);
+	free(parent);
+
+	return ret;
+}
+
+/*
+ * This test disables swapping and tries to allocate anonymous memory
+ * up to OOM with memory.group.oom set. Then it checks that all
+ * processes were killed except those set with OOM_SCORE_ADJ_MIN
+ */
+static int test_memcg_oom_group_score_events(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *memcg;
+	int safe_pid;
+
+	memcg = cg_name(root, "memcg_test_0");
+
+	if (!memcg)
+		goto cleanup;
+
+	if (cg_create(memcg))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.max", "50M"))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.swap.max", "0"))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.oom.group", "1"))
+		goto cleanup;
+
+	safe_pid = cg_run_nowait(memcg, alloc_anon_noexit, (void *) MB(1));
+	if (set_oom_adj_score(safe_pid, OOM_SCORE_ADJ_MIN))
+		goto cleanup;
+
+	cg_run_nowait(memcg, alloc_anon_noexit, (void *) MB(1));
+	if (!cg_run(memcg, alloc_anon, (void *)MB(100)))
+		goto cleanup;
+
+	if (cg_read_key_long(memcg, "memory.events", "oom_kill ") != 3)
+		goto cleanup;
+
+	if (kill(safe_pid, SIGKILL))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (memcg)
+		cg_destroy(memcg);
+	free(memcg);
+
+	return ret;
+}
+
+
 #define T(x) { x, #x }
 struct memcg_test {
 	int (*fn)(const char *root);
@@ -978,6 +1180,9 @@ struct memcg_test {
 	T(test_memcg_oom_events),
 	T(test_memcg_swap_max),
 	T(test_memcg_sock),
+	T(test_memcg_oom_group_leaf_events),
+	T(test_memcg_oom_group_parent_events),
+	T(test_memcg_oom_group_score_events),
 };
 #undef T
 
-- 
cgit 


From 9c98b13cc3bb5d90ee2ec047d591272b382468fd Mon Sep 17 00:00:00 2001
From: Petar Penkov <ppenkov@google.com>
Date: Fri, 14 Sep 2018 07:46:21 -0700
Subject: flow_dissector: implements eBPF parser

This eBPF program extracts basic/control/ip address/ports keys from
incoming packets. It supports recursive parsing for IP encapsulation,
and VLAN, along with IPv4/IPv6 and extension headers.  This program is
meant to show how flow dissection and key extraction can be done in
eBPF.

Link: http://vger.kernel.org/netconf2017_files/rx_hardening_and_udp_gso.pdf
Signed-off-by: Petar Penkov <ppenkov@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/Makefile   |   2 +-
 tools/testing/selftests/bpf/bpf_flow.c | 373 +++++++++++++++++++++++++++++++++
 2 files changed, 374 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/bpf_flow.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index fff7fb1285fc..e65f50f9185e 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -35,7 +35,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \
 	test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
 	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
-	test_skb_cgroup_id_kern.o
+	test_skb_cgroup_id_kern.o bpf_flow.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
diff --git a/tools/testing/selftests/bpf/bpf_flow.c b/tools/testing/selftests/bpf/bpf_flow.c
new file mode 100644
index 000000000000..5fb809d95867
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_flow.c
@@ -0,0 +1,373 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <limits.h>
+#include <stddef.h>
+#include <stdbool.h>
+#include <string.h>
+#include <linux/pkt_cls.h>
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/icmp.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/if_packet.h>
+#include <sys/socket.h>
+#include <linux/if_tunnel.h>
+#include <linux/mpls.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+int _version SEC("version") = 1;
+#define PROG(F) SEC(#F) int bpf_func_##F
+
+/* These are the identifiers of the BPF programs that will be used in tail
+ * calls. Name is limited to 16 characters, with the terminating character and
+ * bpf_func_ above, we have only 6 to work with, anything after will be cropped.
+ */
+enum {
+	IP,
+	IPV6,
+	IPV6OP,	/* Destination/Hop-by-Hop Options IPv6 Extension header */
+	IPV6FR,	/* Fragmentation IPv6 Extension Header */
+	MPLS,
+	VLAN,
+};
+
+#define IP_MF		0x2000
+#define IP_OFFSET	0x1FFF
+#define IP6_MF		0x0001
+#define IP6_OFFSET	0xFFF8
+
+struct vlan_hdr {
+	__be16 h_vlan_TCI;
+	__be16 h_vlan_encapsulated_proto;
+};
+
+struct gre_hdr {
+	__be16 flags;
+	__be16 proto;
+};
+
+struct frag_hdr {
+	__u8 nexthdr;
+	__u8 reserved;
+	__be16 frag_off;
+	__be32 identification;
+};
+
+struct bpf_map_def SEC("maps") jmp_table = {
+	.type = BPF_MAP_TYPE_PROG_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u32),
+	.max_entries = 8
+};
+
+static __always_inline void *bpf_flow_dissect_get_header(struct __sk_buff *skb,
+							 __u16 hdr_size,
+							 void *buffer)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *data = (void *)(long)skb->data;
+	__u16 nhoff = skb->flow_keys->nhoff;
+	__u8 *hdr;
+
+	/* Verifies this variable offset does not overflow */
+	if (nhoff > (USHRT_MAX - hdr_size))
+		return NULL;
+
+	hdr = data + nhoff;
+	if (hdr + hdr_size <= data_end)
+		return hdr;
+
+	if (bpf_skb_load_bytes(skb, nhoff, buffer, hdr_size))
+		return NULL;
+
+	return buffer;
+}
+
+/* Dispatches on ETHERTYPE */
+static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)
+{
+	struct bpf_flow_keys *keys = skb->flow_keys;
+
+	keys->n_proto = proto;
+	switch (proto) {
+	case bpf_htons(ETH_P_IP):
+		bpf_tail_call(skb, &jmp_table, IP);
+		break;
+	case bpf_htons(ETH_P_IPV6):
+		bpf_tail_call(skb, &jmp_table, IPV6);
+		break;
+	case bpf_htons(ETH_P_MPLS_MC):
+	case bpf_htons(ETH_P_MPLS_UC):
+		bpf_tail_call(skb, &jmp_table, MPLS);
+		break;
+	case bpf_htons(ETH_P_8021Q):
+	case bpf_htons(ETH_P_8021AD):
+		bpf_tail_call(skb, &jmp_table, VLAN);
+		break;
+	default:
+		/* Protocol not supported */
+		return BPF_DROP;
+	}
+
+	return BPF_DROP;
+}
+
+SEC("dissect")
+int dissect(struct __sk_buff *skb)
+{
+	if (!skb->vlan_present)
+		return parse_eth_proto(skb, skb->protocol);
+	else
+		return parse_eth_proto(skb, skb->vlan_proto);
+}
+
+/* Parses on IPPROTO_* */
+static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto)
+{
+	struct bpf_flow_keys *keys = skb->flow_keys;
+	void *data_end = (void *)(long)skb->data_end;
+	struct icmphdr *icmp, _icmp;
+	struct gre_hdr *gre, _gre;
+	struct ethhdr *eth, _eth;
+	struct tcphdr *tcp, _tcp;
+	struct udphdr *udp, _udp;
+
+	keys->ip_proto = proto;
+	switch (proto) {
+	case IPPROTO_ICMP:
+		icmp = bpf_flow_dissect_get_header(skb, sizeof(*icmp), &_icmp);
+		if (!icmp)
+			return BPF_DROP;
+		return BPF_OK;
+	case IPPROTO_IPIP:
+		keys->is_encap = true;
+		return parse_eth_proto(skb, bpf_htons(ETH_P_IP));
+	case IPPROTO_IPV6:
+		keys->is_encap = true;
+		return parse_eth_proto(skb, bpf_htons(ETH_P_IPV6));
+	case IPPROTO_GRE:
+		gre = bpf_flow_dissect_get_header(skb, sizeof(*gre), &_gre);
+		if (!gre)
+			return BPF_DROP;
+
+		if (bpf_htons(gre->flags & GRE_VERSION))
+			/* Only inspect standard GRE packets with version 0 */
+			return BPF_OK;
+
+		keys->nhoff += sizeof(*gre); /* Step over GRE Flags and Proto */
+		if (GRE_IS_CSUM(gre->flags))
+			keys->nhoff += 4; /* Step over chksum and Padding */
+		if (GRE_IS_KEY(gre->flags))
+			keys->nhoff += 4; /* Step over key */
+		if (GRE_IS_SEQ(gre->flags))
+			keys->nhoff += 4; /* Step over sequence number */
+
+		keys->is_encap = true;
+
+		if (gre->proto == bpf_htons(ETH_P_TEB)) {
+			eth = bpf_flow_dissect_get_header(skb, sizeof(*eth),
+							  &_eth);
+			if (!eth)
+				return BPF_DROP;
+
+			keys->nhoff += sizeof(*eth);
+
+			return parse_eth_proto(skb, eth->h_proto);
+		} else {
+			return parse_eth_proto(skb, gre->proto);
+		}
+	case IPPROTO_TCP:
+		tcp = bpf_flow_dissect_get_header(skb, sizeof(*tcp), &_tcp);
+		if (!tcp)
+			return BPF_DROP;
+
+		if (tcp->doff < 5)
+			return BPF_DROP;
+
+		if ((__u8 *)tcp + (tcp->doff << 2) > data_end)
+			return BPF_DROP;
+
+		keys->thoff = keys->nhoff;
+		keys->sport = tcp->source;
+		keys->dport = tcp->dest;
+		return BPF_OK;
+	case IPPROTO_UDP:
+	case IPPROTO_UDPLITE:
+		udp = bpf_flow_dissect_get_header(skb, sizeof(*udp), &_udp);
+		if (!udp)
+			return BPF_DROP;
+
+		keys->thoff = keys->nhoff;
+		keys->sport = udp->source;
+		keys->dport = udp->dest;
+		return BPF_OK;
+	default:
+		return BPF_DROP;
+	}
+
+	return BPF_DROP;
+}
+
+static __always_inline int parse_ipv6_proto(struct __sk_buff *skb, __u8 nexthdr)
+{
+	struct bpf_flow_keys *keys = skb->flow_keys;
+
+	keys->ip_proto = nexthdr;
+	switch (nexthdr) {
+	case IPPROTO_HOPOPTS:
+	case IPPROTO_DSTOPTS:
+		bpf_tail_call(skb, &jmp_table, IPV6OP);
+		break;
+	case IPPROTO_FRAGMENT:
+		bpf_tail_call(skb, &jmp_table, IPV6FR);
+		break;
+	default:
+		return parse_ip_proto(skb, nexthdr);
+	}
+
+	return BPF_DROP;
+}
+
+PROG(IP)(struct __sk_buff *skb)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	struct bpf_flow_keys *keys = skb->flow_keys;
+	void *data = (void *)(long)skb->data;
+	struct iphdr *iph, _iph;
+	bool done = false;
+
+	iph = bpf_flow_dissect_get_header(skb, sizeof(*iph), &_iph);
+	if (!iph)
+		return BPF_DROP;
+
+	/* IP header cannot be smaller than 20 bytes */
+	if (iph->ihl < 5)
+		return BPF_DROP;
+
+	keys->addr_proto = ETH_P_IP;
+	keys->ipv4_src = iph->saddr;
+	keys->ipv4_dst = iph->daddr;
+
+	keys->nhoff += iph->ihl << 2;
+	if (data + keys->nhoff > data_end)
+		return BPF_DROP;
+
+	if (iph->frag_off & bpf_htons(IP_MF | IP_OFFSET)) {
+		keys->is_frag = true;
+		if (iph->frag_off & bpf_htons(IP_OFFSET))
+			/* From second fragment on, packets do not have headers
+			 * we can parse.
+			 */
+			done = true;
+		else
+			keys->is_first_frag = true;
+	}
+
+	if (done)
+		return BPF_OK;
+
+	return parse_ip_proto(skb, iph->protocol);
+}
+
+PROG(IPV6)(struct __sk_buff *skb)
+{
+	struct bpf_flow_keys *keys = skb->flow_keys;
+	struct ipv6hdr *ip6h, _ip6h;
+
+	ip6h = bpf_flow_dissect_get_header(skb, sizeof(*ip6h), &_ip6h);
+	if (!ip6h)
+		return BPF_DROP;
+
+	keys->addr_proto = ETH_P_IPV6;
+	memcpy(&keys->ipv6_src, &ip6h->saddr, 2*sizeof(ip6h->saddr));
+
+	keys->nhoff += sizeof(struct ipv6hdr);
+
+	return parse_ipv6_proto(skb, ip6h->nexthdr);
+}
+
+PROG(IPV6OP)(struct __sk_buff *skb)
+{
+	struct ipv6_opt_hdr *ip6h, _ip6h;
+
+	ip6h = bpf_flow_dissect_get_header(skb, sizeof(*ip6h), &_ip6h);
+	if (!ip6h)
+		return BPF_DROP;
+
+	/* hlen is in 8-octets and does not include the first 8 bytes
+	 * of the header
+	 */
+	skb->flow_keys->nhoff += (1 + ip6h->hdrlen) << 3;
+
+	return parse_ipv6_proto(skb, ip6h->nexthdr);
+}
+
+PROG(IPV6FR)(struct __sk_buff *skb)
+{
+	struct bpf_flow_keys *keys = skb->flow_keys;
+	struct frag_hdr *fragh, _fragh;
+
+	fragh = bpf_flow_dissect_get_header(skb, sizeof(*fragh), &_fragh);
+	if (!fragh)
+		return BPF_DROP;
+
+	keys->nhoff += sizeof(*fragh);
+	keys->is_frag = true;
+	if (!(fragh->frag_off & bpf_htons(IP6_OFFSET)))
+		keys->is_first_frag = true;
+
+	return parse_ipv6_proto(skb, fragh->nexthdr);
+}
+
+PROG(MPLS)(struct __sk_buff *skb)
+{
+	struct mpls_label *mpls, _mpls;
+
+	mpls = bpf_flow_dissect_get_header(skb, sizeof(*mpls), &_mpls);
+	if (!mpls)
+		return BPF_DROP;
+
+	return BPF_OK;
+}
+
+PROG(VLAN)(struct __sk_buff *skb)
+{
+	struct bpf_flow_keys *keys = skb->flow_keys;
+	struct vlan_hdr *vlan, _vlan;
+	__be16 proto;
+
+	/* Peek back to see if single or double-tagging */
+	if (bpf_skb_load_bytes(skb, keys->nhoff - sizeof(proto), &proto,
+			       sizeof(proto)))
+		return BPF_DROP;
+
+	/* Account for double-tagging */
+	if (proto == bpf_htons(ETH_P_8021AD)) {
+		vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan);
+		if (!vlan)
+			return BPF_DROP;
+
+		if (vlan->h_vlan_encapsulated_proto != bpf_htons(ETH_P_8021Q))
+			return BPF_DROP;
+
+		keys->nhoff += sizeof(*vlan);
+	}
+
+	vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan);
+	if (!vlan)
+		return BPF_DROP;
+
+	keys->nhoff += sizeof(*vlan);
+	/* Only allow 8021AD + 8021Q double tagging and no triple tagging.*/
+	if (vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021AD) ||
+	    vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021Q))
+		return BPF_DROP;
+
+	return parse_eth_proto(skb, vlan->h_vlan_encapsulated_proto);
+}
+
+char __license[] SEC("license") = "GPL";
-- 
cgit 


From 50b3ed57dee9cd0e06c59826cec8af14b51bab3e Mon Sep 17 00:00:00 2001
From: Petar Penkov <ppenkov@google.com>
Date: Fri, 14 Sep 2018 07:46:22 -0700
Subject: selftests/bpf: test bpf flow dissection

Adds a test that sends different types of packets over multiple
tunnels and verifies that valid packets are dissected correctly.  To do
so, a tc-flower rule is added to drop packets on UDP src port 9, and
packets are sent from ports 8, 9, and 10. Only the packets on port 9
should be dropped. Because tc-flower relies on the flow dissector to
match flows, correct classification demonstrates correct dissection.

Also add support logic to load the BPF program and to inject the test
packets.

Signed-off-by: Petar Penkov <ppenkov@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/.gitignore             |   2 +
 tools/testing/selftests/bpf/Makefile               |   6 +-
 tools/testing/selftests/bpf/config                 |   1 +
 tools/testing/selftests/bpf/flow_dissector_load.c  | 140 ++++
 tools/testing/selftests/bpf/test_flow_dissector.c  | 782 +++++++++++++++++++++
 tools/testing/selftests/bpf/test_flow_dissector.sh | 115 +++
 tools/testing/selftests/bpf/with_addr.sh           |  54 ++
 tools/testing/selftests/bpf/with_tunnels.sh        |  36 +
 8 files changed, 1134 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/flow_dissector_load.c
 create mode 100644 tools/testing/selftests/bpf/test_flow_dissector.c
 create mode 100755 tools/testing/selftests/bpf/test_flow_dissector.sh
 create mode 100755 tools/testing/selftests/bpf/with_addr.sh
 create mode 100755 tools/testing/selftests/bpf/with_tunnels.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 4d789c1e5167..8a60c9b9892d 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -23,3 +23,5 @@ test_skb_cgroup_id_user
 test_socket_cookie
 test_cgroup_storage
 test_select_reuseport
+test_flow_dissector
+flow_dissector_load
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index e65f50f9185e..fd3851d5c079 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -47,10 +47,12 @@ TEST_PROGS := test_kmod.sh \
 	test_tunnel.sh \
 	test_lwt_seg6local.sh \
 	test_lirc_mode2.sh \
-	test_skb_cgroup_id.sh
+	test_skb_cgroup_id.sh \
+	test_flow_dissector.sh
 
 # Compile but not part of 'make run_tests'
-TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user
+TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user \
+	flow_dissector_load test_flow_dissector
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index b4994a94968b..3655508f95fd 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -18,3 +18,4 @@ CONFIG_CRYPTO_HMAC=m
 CONFIG_CRYPTO_SHA256=m
 CONFIG_VXLAN=y
 CONFIG_GENEVE=y
+CONFIG_NET_CLS_FLOWER=m
diff --git a/tools/testing/selftests/bpf/flow_dissector_load.c b/tools/testing/selftests/bpf/flow_dissector_load.c
new file mode 100644
index 000000000000..d3273b5b3173
--- /dev/null
+++ b/tools/testing/selftests/bpf/flow_dissector_load.c
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <error.h>
+#include <errno.h>
+#include <getopt.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+const char *cfg_pin_path = "/sys/fs/bpf/flow_dissector";
+const char *cfg_map_name = "jmp_table";
+bool cfg_attach = true;
+char *cfg_section_name;
+char *cfg_path_name;
+
+static void load_and_attach_program(void)
+{
+	struct bpf_program *prog, *main_prog;
+	struct bpf_map *prog_array;
+	int i, fd, prog_fd, ret;
+	struct bpf_object *obj;
+	int prog_array_fd;
+
+	ret = bpf_prog_load(cfg_path_name, BPF_PROG_TYPE_FLOW_DISSECTOR, &obj,
+			    &prog_fd);
+	if (ret)
+		error(1, 0, "bpf_prog_load %s", cfg_path_name);
+
+	main_prog = bpf_object__find_program_by_title(obj, cfg_section_name);
+	if (!main_prog)
+		error(1, 0, "bpf_object__find_program_by_title %s",
+		      cfg_section_name);
+
+	prog_fd = bpf_program__fd(main_prog);
+	if (prog_fd < 0)
+		error(1, 0, "bpf_program__fd");
+
+	prog_array = bpf_object__find_map_by_name(obj, cfg_map_name);
+	if (!prog_array)
+		error(1, 0, "bpf_object__find_map_by_name %s", cfg_map_name);
+
+	prog_array_fd = bpf_map__fd(prog_array);
+	if (prog_array_fd < 0)
+		error(1, 0, "bpf_map__fd %s", cfg_map_name);
+
+	i = 0;
+	bpf_object__for_each_program(prog, obj) {
+		fd = bpf_program__fd(prog);
+		if (fd < 0)
+			error(1, 0, "bpf_program__fd");
+
+		if (fd != prog_fd) {
+			printf("%d: %s\n", i, bpf_program__title(prog, false));
+			bpf_map_update_elem(prog_array_fd, &i, &fd, BPF_ANY);
+			++i;
+		}
+	}
+
+	ret = bpf_prog_attach(prog_fd, 0 /* Ignore */, BPF_FLOW_DISSECTOR, 0);
+	if (ret)
+		error(1, 0, "bpf_prog_attach %s", cfg_path_name);
+
+	ret = bpf_object__pin(obj, cfg_pin_path);
+	if (ret)
+		error(1, 0, "bpf_object__pin %s", cfg_pin_path);
+
+}
+
+static void detach_program(void)
+{
+	char command[64];
+	int ret;
+
+	ret = bpf_prog_detach(0, BPF_FLOW_DISSECTOR);
+	if (ret)
+		error(1, 0, "bpf_prog_detach");
+
+	/* To unpin, it is necessary and sufficient to just remove this dir */
+	sprintf(command, "rm -r %s", cfg_pin_path);
+	ret = system(command);
+	if (ret)
+		error(1, errno, command);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	bool attach = false;
+	bool detach = false;
+	int c;
+
+	while ((c = getopt(argc, argv, "adp:s:")) != -1) {
+		switch (c) {
+		case 'a':
+			if (detach)
+				error(1, 0, "attach/detach are exclusive");
+			attach = true;
+			break;
+		case 'd':
+			if (attach)
+				error(1, 0, "attach/detach are exclusive");
+			detach = true;
+			break;
+		case 'p':
+			if (cfg_path_name)
+				error(1, 0, "only one prog name can be given");
+
+			cfg_path_name = optarg;
+			break;
+		case 's':
+			if (cfg_section_name)
+				error(1, 0, "only one section can be given");
+
+			cfg_section_name = optarg;
+			break;
+		}
+	}
+
+	if (detach)
+		cfg_attach = false;
+
+	if (cfg_attach && !cfg_path_name)
+		error(1, 0, "must provide a path to the BPF program");
+
+	if (cfg_attach && !cfg_section_name)
+		error(1, 0, "must provide a section name");
+}
+
+int main(int argc, char **argv)
+{
+	parse_opts(argc, argv);
+	if (cfg_attach)
+		load_and_attach_program();
+	else
+		detach_program();
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/test_flow_dissector.c b/tools/testing/selftests/bpf/test_flow_dissector.c
new file mode 100644
index 000000000000..12b784afba31
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_flow_dissector.c
@@ -0,0 +1,782 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Inject packets with all sorts of encapsulation into the kernel.
+ *
+ * IPv4/IPv6	outer layer 3
+ * GRE/GUE/BARE outer layer 4, where bare is IPIP/SIT/IPv4-in-IPv6/..
+ * IPv4/IPv6    inner layer 3
+ */
+
+#define _GNU_SOURCE
+
+#include <stddef.h>
+#include <arpa/inet.h>
+#include <asm/byteorder.h>
+#include <error.h>
+#include <errno.h>
+#include <linux/if_packet.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ipv6.h>
+#include <netinet/ip.h>
+#include <netinet/in.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#define CFG_PORT_INNER	8000
+
+/* Add some protocol definitions that do not exist in userspace */
+
+struct grehdr {
+	uint16_t unused;
+	uint16_t protocol;
+} __attribute__((packed));
+
+struct guehdr {
+	union {
+		struct {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+			__u8	hlen:5,
+				control:1,
+				version:2;
+#elif defined (__BIG_ENDIAN_BITFIELD)
+			__u8	version:2,
+				control:1,
+				hlen:5;
+#else
+#error  "Please fix <asm/byteorder.h>"
+#endif
+			__u8	proto_ctype;
+			__be16	flags;
+		};
+		__be32	word;
+	};
+};
+
+static uint8_t	cfg_dsfield_inner;
+static uint8_t	cfg_dsfield_outer;
+static uint8_t	cfg_encap_proto;
+static bool	cfg_expect_failure = false;
+static int	cfg_l3_extra = AF_UNSPEC;	/* optional SIT prefix */
+static int	cfg_l3_inner = AF_UNSPEC;
+static int	cfg_l3_outer = AF_UNSPEC;
+static int	cfg_num_pkt = 10;
+static int	cfg_num_secs = 0;
+static char	cfg_payload_char = 'a';
+static int	cfg_payload_len = 100;
+static int	cfg_port_gue = 6080;
+static bool	cfg_only_rx;
+static bool	cfg_only_tx;
+static int	cfg_src_port = 9;
+
+static char	buf[ETH_DATA_LEN];
+
+#define INIT_ADDR4(name, addr4, port)				\
+	static struct sockaddr_in name = {			\
+		.sin_family = AF_INET,				\
+		.sin_port = __constant_htons(port),		\
+		.sin_addr.s_addr = __constant_htonl(addr4),	\
+	};
+
+#define INIT_ADDR6(name, addr6, port)				\
+	static struct sockaddr_in6 name = {			\
+		.sin6_family = AF_INET6,			\
+		.sin6_port = __constant_htons(port),		\
+		.sin6_addr = addr6,				\
+	};
+
+INIT_ADDR4(in_daddr4, INADDR_LOOPBACK, CFG_PORT_INNER)
+INIT_ADDR4(in_saddr4, INADDR_LOOPBACK + 2, 0)
+INIT_ADDR4(out_daddr4, INADDR_LOOPBACK, 0)
+INIT_ADDR4(out_saddr4, INADDR_LOOPBACK + 1, 0)
+INIT_ADDR4(extra_daddr4, INADDR_LOOPBACK, 0)
+INIT_ADDR4(extra_saddr4, INADDR_LOOPBACK + 1, 0)
+
+INIT_ADDR6(in_daddr6, IN6ADDR_LOOPBACK_INIT, CFG_PORT_INNER)
+INIT_ADDR6(in_saddr6, IN6ADDR_LOOPBACK_INIT, 0)
+INIT_ADDR6(out_daddr6, IN6ADDR_LOOPBACK_INIT, 0)
+INIT_ADDR6(out_saddr6, IN6ADDR_LOOPBACK_INIT, 0)
+INIT_ADDR6(extra_daddr6, IN6ADDR_LOOPBACK_INIT, 0)
+INIT_ADDR6(extra_saddr6, IN6ADDR_LOOPBACK_INIT, 0)
+
+static unsigned long util_gettime(void)
+{
+	struct timeval tv;
+
+	gettimeofday(&tv, NULL);
+	return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
+}
+
+static void util_printaddr(const char *msg, struct sockaddr *addr)
+{
+	unsigned long off = 0;
+	char nbuf[INET6_ADDRSTRLEN];
+
+	switch (addr->sa_family) {
+	case PF_INET:
+		off = __builtin_offsetof(struct sockaddr_in, sin_addr);
+		break;
+	case PF_INET6:
+		off = __builtin_offsetof(struct sockaddr_in6, sin6_addr);
+		break;
+	default:
+		error(1, 0, "printaddr: unsupported family %u\n",
+		      addr->sa_family);
+	}
+
+	if (!inet_ntop(addr->sa_family, ((void *) addr) + off, nbuf,
+		       sizeof(nbuf)))
+		error(1, errno, "inet_ntop");
+
+	fprintf(stderr, "%s: %s\n", msg, nbuf);
+}
+
+static unsigned long add_csum_hword(const uint16_t *start, int num_u16)
+{
+	unsigned long sum = 0;
+	int i;
+
+	for (i = 0; i < num_u16; i++)
+		sum += start[i];
+
+	return sum;
+}
+
+static uint16_t build_ip_csum(const uint16_t *start, int num_u16,
+			      unsigned long sum)
+{
+	sum += add_csum_hword(start, num_u16);
+
+	while (sum >> 16)
+		sum = (sum & 0xffff) + (sum >> 16);
+
+	return ~sum;
+}
+
+static void build_ipv4_header(void *header, uint8_t proto,
+			      uint32_t src, uint32_t dst,
+			      int payload_len, uint8_t tos)
+{
+	struct iphdr *iph = header;
+
+	iph->ihl = 5;
+	iph->version = 4;
+	iph->tos = tos;
+	iph->ttl = 8;
+	iph->tot_len = htons(sizeof(*iph) + payload_len);
+	iph->id = htons(1337);
+	iph->protocol = proto;
+	iph->saddr = src;
+	iph->daddr = dst;
+	iph->check = build_ip_csum((void *) iph, iph->ihl << 1, 0);
+}
+
+static void ipv6_set_dsfield(struct ipv6hdr *ip6h, uint8_t dsfield)
+{
+	uint16_t val, *ptr = (uint16_t *)ip6h;
+
+	val = ntohs(*ptr);
+	val &= 0xF00F;
+	val |= ((uint16_t) dsfield) << 4;
+	*ptr = htons(val);
+}
+
+static void build_ipv6_header(void *header, uint8_t proto,
+			      struct sockaddr_in6 *src,
+			      struct sockaddr_in6 *dst,
+			      int payload_len, uint8_t dsfield)
+{
+	struct ipv6hdr *ip6h = header;
+
+	ip6h->version = 6;
+	ip6h->payload_len = htons(payload_len);
+	ip6h->nexthdr = proto;
+	ip6h->hop_limit = 8;
+	ipv6_set_dsfield(ip6h, dsfield);
+
+	memcpy(&ip6h->saddr, &src->sin6_addr, sizeof(ip6h->saddr));
+	memcpy(&ip6h->daddr, &dst->sin6_addr, sizeof(ip6h->daddr));
+}
+
+static uint16_t build_udp_v4_csum(const struct iphdr *iph,
+				  const struct udphdr *udph,
+				  int num_words)
+{
+	unsigned long pseudo_sum;
+	int num_u16 = sizeof(iph->saddr);	/* halfwords: twice byte len */
+
+	pseudo_sum = add_csum_hword((void *) &iph->saddr, num_u16);
+	pseudo_sum += htons(IPPROTO_UDP);
+	pseudo_sum += udph->len;
+	return build_ip_csum((void *) udph, num_words, pseudo_sum);
+}
+
+static uint16_t build_udp_v6_csum(const struct ipv6hdr *ip6h,
+				  const struct udphdr *udph,
+				  int num_words)
+{
+	unsigned long pseudo_sum;
+	int num_u16 = sizeof(ip6h->saddr);	/* halfwords: twice byte len */
+
+	pseudo_sum = add_csum_hword((void *) &ip6h->saddr, num_u16);
+	pseudo_sum += htons(ip6h->nexthdr);
+	pseudo_sum += ip6h->payload_len;
+	return build_ip_csum((void *) udph, num_words, pseudo_sum);
+}
+
+static void build_udp_header(void *header, int payload_len,
+			     uint16_t dport, int family)
+{
+	struct udphdr *udph = header;
+	int len = sizeof(*udph) + payload_len;
+
+	udph->source = htons(cfg_src_port);
+	udph->dest = htons(dport);
+	udph->len = htons(len);
+	udph->check = 0;
+	if (family == AF_INET)
+		udph->check = build_udp_v4_csum(header - sizeof(struct iphdr),
+						udph, len >> 1);
+	else
+		udph->check = build_udp_v6_csum(header - sizeof(struct ipv6hdr),
+						udph, len >> 1);
+}
+
+static void build_gue_header(void *header, uint8_t proto)
+{
+	struct guehdr *gueh = header;
+
+	gueh->proto_ctype = proto;
+}
+
+static void build_gre_header(void *header, uint16_t proto)
+{
+	struct grehdr *greh = header;
+
+	greh->protocol = htons(proto);
+}
+
+static int l3_length(int family)
+{
+	if (family == AF_INET)
+		return sizeof(struct iphdr);
+	else
+		return sizeof(struct ipv6hdr);
+}
+
+static int build_packet(void)
+{
+	int ol3_len = 0, ol4_len = 0, il3_len = 0, il4_len = 0;
+	int el3_len = 0;
+
+	if (cfg_l3_extra)
+		el3_len = l3_length(cfg_l3_extra);
+
+	/* calculate header offsets */
+	if (cfg_encap_proto) {
+		ol3_len = l3_length(cfg_l3_outer);
+
+		if (cfg_encap_proto == IPPROTO_GRE)
+			ol4_len = sizeof(struct grehdr);
+		else if (cfg_encap_proto == IPPROTO_UDP)
+			ol4_len = sizeof(struct udphdr) + sizeof(struct guehdr);
+	}
+
+	il3_len = l3_length(cfg_l3_inner);
+	il4_len = sizeof(struct udphdr);
+
+	if (el3_len + ol3_len + ol4_len + il3_len + il4_len + cfg_payload_len >=
+	    sizeof(buf))
+		error(1, 0, "packet too large\n");
+
+	/*
+	 * Fill packet from inside out, to calculate correct checksums.
+	 * But create ip before udp headers, as udp uses ip for pseudo-sum.
+	 */
+	memset(buf + el3_len + ol3_len + ol4_len + il3_len + il4_len,
+	       cfg_payload_char, cfg_payload_len);
+
+	/* add zero byte for udp csum padding */
+	buf[el3_len + ol3_len + ol4_len + il3_len + il4_len + cfg_payload_len] = 0;
+
+	switch (cfg_l3_inner) {
+	case PF_INET:
+		build_ipv4_header(buf + el3_len + ol3_len + ol4_len,
+				  IPPROTO_UDP,
+				  in_saddr4.sin_addr.s_addr,
+				  in_daddr4.sin_addr.s_addr,
+				  il4_len + cfg_payload_len,
+				  cfg_dsfield_inner);
+		break;
+	case PF_INET6:
+		build_ipv6_header(buf + el3_len + ol3_len + ol4_len,
+				  IPPROTO_UDP,
+				  &in_saddr6, &in_daddr6,
+				  il4_len + cfg_payload_len,
+				  cfg_dsfield_inner);
+		break;
+	}
+
+	build_udp_header(buf + el3_len + ol3_len + ol4_len + il3_len,
+			 cfg_payload_len, CFG_PORT_INNER, cfg_l3_inner);
+
+	if (!cfg_encap_proto)
+		return il3_len + il4_len + cfg_payload_len;
+
+	switch (cfg_l3_outer) {
+	case PF_INET:
+		build_ipv4_header(buf + el3_len, cfg_encap_proto,
+				  out_saddr4.sin_addr.s_addr,
+				  out_daddr4.sin_addr.s_addr,
+				  ol4_len + il3_len + il4_len + cfg_payload_len,
+				  cfg_dsfield_outer);
+		break;
+	case PF_INET6:
+		build_ipv6_header(buf + el3_len, cfg_encap_proto,
+				  &out_saddr6, &out_daddr6,
+				  ol4_len + il3_len + il4_len + cfg_payload_len,
+				  cfg_dsfield_outer);
+		break;
+	}
+
+	switch (cfg_encap_proto) {
+	case IPPROTO_UDP:
+		build_gue_header(buf + el3_len + ol3_len + ol4_len -
+				 sizeof(struct guehdr),
+				 cfg_l3_inner == PF_INET ? IPPROTO_IPIP
+							 : IPPROTO_IPV6);
+		build_udp_header(buf + el3_len + ol3_len,
+				 sizeof(struct guehdr) + il3_len + il4_len +
+				 cfg_payload_len,
+				 cfg_port_gue, cfg_l3_outer);
+		break;
+	case IPPROTO_GRE:
+		build_gre_header(buf + el3_len + ol3_len,
+				 cfg_l3_inner == PF_INET ? ETH_P_IP
+							 : ETH_P_IPV6);
+		break;
+	}
+
+	switch (cfg_l3_extra) {
+	case PF_INET:
+		build_ipv4_header(buf,
+				  cfg_l3_outer == PF_INET ? IPPROTO_IPIP
+							  : IPPROTO_IPV6,
+				  extra_saddr4.sin_addr.s_addr,
+				  extra_daddr4.sin_addr.s_addr,
+				  ol3_len + ol4_len + il3_len + il4_len +
+				  cfg_payload_len, 0);
+		break;
+	case PF_INET6:
+		build_ipv6_header(buf,
+				  cfg_l3_outer == PF_INET ? IPPROTO_IPIP
+							  : IPPROTO_IPV6,
+				  &extra_saddr6, &extra_daddr6,
+				  ol3_len + ol4_len + il3_len + il4_len +
+				  cfg_payload_len, 0);
+		break;
+	}
+
+	return el3_len + ol3_len + ol4_len + il3_len + il4_len +
+	       cfg_payload_len;
+}
+
+/* sender transmits encapsulated over RAW or unencap'd over UDP */
+static int setup_tx(void)
+{
+	int family, fd, ret;
+
+	if (cfg_l3_extra)
+		family = cfg_l3_extra;
+	else if (cfg_l3_outer)
+		family = cfg_l3_outer;
+	else
+		family = cfg_l3_inner;
+
+	fd = socket(family, SOCK_RAW, IPPROTO_RAW);
+	if (fd == -1)
+		error(1, errno, "socket tx");
+
+	if (cfg_l3_extra) {
+		if (cfg_l3_extra == PF_INET)
+			ret = connect(fd, (void *) &extra_daddr4,
+				      sizeof(extra_daddr4));
+		else
+			ret = connect(fd, (void *) &extra_daddr6,
+				      sizeof(extra_daddr6));
+		if (ret)
+			error(1, errno, "connect tx");
+	} else if (cfg_l3_outer) {
+		/* connect to destination if not encapsulated */
+		if (cfg_l3_outer == PF_INET)
+			ret = connect(fd, (void *) &out_daddr4,
+				      sizeof(out_daddr4));
+		else
+			ret = connect(fd, (void *) &out_daddr6,
+				      sizeof(out_daddr6));
+		if (ret)
+			error(1, errno, "connect tx");
+	} else {
+		/* otherwise using loopback */
+		if (cfg_l3_inner == PF_INET)
+			ret = connect(fd, (void *) &in_daddr4,
+				      sizeof(in_daddr4));
+		else
+			ret = connect(fd, (void *) &in_daddr6,
+				      sizeof(in_daddr6));
+		if (ret)
+			error(1, errno, "connect tx");
+	}
+
+	return fd;
+}
+
+/* receiver reads unencapsulated UDP */
+static int setup_rx(void)
+{
+	int fd, ret;
+
+	fd = socket(cfg_l3_inner, SOCK_DGRAM, 0);
+	if (fd == -1)
+		error(1, errno, "socket rx");
+
+	if (cfg_l3_inner == PF_INET)
+		ret = bind(fd, (void *) &in_daddr4, sizeof(in_daddr4));
+	else
+		ret = bind(fd, (void *) &in_daddr6, sizeof(in_daddr6));
+	if (ret)
+		error(1, errno, "bind rx");
+
+	return fd;
+}
+
+static int do_tx(int fd, const char *pkt, int len)
+{
+	int ret;
+
+	ret = write(fd, pkt, len);
+	if (ret == -1)
+		error(1, errno, "send");
+	if (ret != len)
+		error(1, errno, "send: len (%d < %d)\n", ret, len);
+
+	return 1;
+}
+
+static int do_poll(int fd, short events, int timeout)
+{
+	struct pollfd pfd;
+	int ret;
+
+	pfd.fd = fd;
+	pfd.events = events;
+
+	ret = poll(&pfd, 1, timeout);
+	if (ret == -1)
+		error(1, errno, "poll");
+	if (ret && !(pfd.revents & POLLIN))
+		error(1, errno, "poll: unexpected event 0x%x\n", pfd.revents);
+
+	return ret;
+}
+
+static int do_rx(int fd)
+{
+	char rbuf;
+	int ret, num = 0;
+
+	while (1) {
+		ret = recv(fd, &rbuf, 1, MSG_DONTWAIT);
+		if (ret == -1 && errno == EAGAIN)
+			break;
+		if (ret == -1)
+			error(1, errno, "recv");
+		if (rbuf != cfg_payload_char)
+			error(1, 0, "recv: payload mismatch");
+		num++;
+	};
+
+	return num;
+}
+
+static int do_main(void)
+{
+	unsigned long tstop, treport, tcur;
+	int fdt = -1, fdr = -1, len, tx = 0, rx = 0;
+
+	if (!cfg_only_tx)
+		fdr = setup_rx();
+	if (!cfg_only_rx)
+		fdt = setup_tx();
+
+	len = build_packet();
+
+	tcur = util_gettime();
+	treport = tcur + 1000;
+	tstop = tcur + (cfg_num_secs * 1000);
+
+	while (1) {
+		if (!cfg_only_rx)
+			tx += do_tx(fdt, buf, len);
+
+		if (!cfg_only_tx)
+			rx += do_rx(fdr);
+
+		if (cfg_num_secs) {
+			tcur = util_gettime();
+			if (tcur >= tstop)
+				break;
+			if (tcur >= treport) {
+				fprintf(stderr, "pkts: tx=%u rx=%u\n", tx, rx);
+				tx = 0;
+				rx = 0;
+				treport = tcur + 1000;
+			}
+		} else {
+			if (tx == cfg_num_pkt)
+				break;
+		}
+	}
+
+	/* read straggler packets, if any */
+	if (rx < tx) {
+		tstop = util_gettime() + 100;
+		while (rx < tx) {
+			tcur = util_gettime();
+			if (tcur >= tstop)
+				break;
+
+			do_poll(fdr, POLLIN, tstop - tcur);
+			rx += do_rx(fdr);
+		}
+	}
+
+	fprintf(stderr, "pkts: tx=%u rx=%u\n", tx, rx);
+
+	if (fdr != -1 && close(fdr))
+		error(1, errno, "close rx");
+	if (fdt != -1 && close(fdt))
+		error(1, errno, "close tx");
+
+	/*
+	 * success (== 0) only if received all packets
+	 * unless failure is expected, in which case none must arrive.
+	 */
+	if (cfg_expect_failure)
+		return rx != 0;
+	else
+		return rx != tx;
+}
+
+
+static void __attribute__((noreturn)) usage(const char *filepath)
+{
+	fprintf(stderr, "Usage: %s [-e gre|gue|bare|none] [-i 4|6] [-l len] "
+			"[-O 4|6] [-o 4|6] [-n num] [-t secs] [-R] [-T] "
+			"[-s <osrc> [-d <odst>] [-S <isrc>] [-D <idst>] "
+			"[-x <otos>] [-X <itos>] [-f <isport>] [-F]\n",
+		filepath);
+	exit(1);
+}
+
+static void parse_addr(int family, void *addr, const char *optarg)
+{
+	int ret;
+
+	ret = inet_pton(family, optarg, addr);
+	if (ret == -1)
+		error(1, errno, "inet_pton");
+	if (ret == 0)
+		error(1, 0, "inet_pton: bad string");
+}
+
+static void parse_addr4(struct sockaddr_in *addr, const char *optarg)
+{
+	parse_addr(AF_INET, &addr->sin_addr, optarg);
+}
+
+static void parse_addr6(struct sockaddr_in6 *addr, const char *optarg)
+{
+	parse_addr(AF_INET6, &addr->sin6_addr, optarg);
+}
+
+static int parse_protocol_family(const char *filepath, const char *optarg)
+{
+	if (!strcmp(optarg, "4"))
+		return PF_INET;
+	if (!strcmp(optarg, "6"))
+		return PF_INET6;
+
+	usage(filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	int c;
+
+	while ((c = getopt(argc, argv, "d:D:e:f:Fhi:l:n:o:O:Rs:S:t:Tx:X:")) != -1) {
+		switch (c) {
+		case 'd':
+			if (cfg_l3_outer == AF_UNSPEC)
+				error(1, 0, "-d must be preceded by -o");
+			if (cfg_l3_outer == AF_INET)
+				parse_addr4(&out_daddr4, optarg);
+			else
+				parse_addr6(&out_daddr6, optarg);
+			break;
+		case 'D':
+			if (cfg_l3_inner == AF_UNSPEC)
+				error(1, 0, "-D must be preceded by -i");
+			if (cfg_l3_inner == AF_INET)
+				parse_addr4(&in_daddr4, optarg);
+			else
+				parse_addr6(&in_daddr6, optarg);
+			break;
+		case 'e':
+			if (!strcmp(optarg, "gre"))
+				cfg_encap_proto = IPPROTO_GRE;
+			else if (!strcmp(optarg, "gue"))
+				cfg_encap_proto = IPPROTO_UDP;
+			else if (!strcmp(optarg, "bare"))
+				cfg_encap_proto = IPPROTO_IPIP;
+			else if (!strcmp(optarg, "none"))
+				cfg_encap_proto = IPPROTO_IP;	/* == 0 */
+			else
+				usage(argv[0]);
+			break;
+		case 'f':
+			cfg_src_port = strtol(optarg, NULL, 0);
+			break;
+		case 'F':
+			cfg_expect_failure = true;
+			break;
+		case 'h':
+			usage(argv[0]);
+			break;
+		case 'i':
+			if (!strcmp(optarg, "4"))
+				cfg_l3_inner = PF_INET;
+			else if (!strcmp(optarg, "6"))
+				cfg_l3_inner = PF_INET6;
+			else
+				usage(argv[0]);
+			break;
+		case 'l':
+			cfg_payload_len = strtol(optarg, NULL, 0);
+			break;
+		case 'n':
+			cfg_num_pkt = strtol(optarg, NULL, 0);
+			break;
+		case 'o':
+			cfg_l3_outer = parse_protocol_family(argv[0], optarg);
+			break;
+		case 'O':
+			cfg_l3_extra = parse_protocol_family(argv[0], optarg);
+			break;
+		case 'R':
+			cfg_only_rx = true;
+			break;
+		case 's':
+			if (cfg_l3_outer == AF_INET)
+				parse_addr4(&out_saddr4, optarg);
+			else
+				parse_addr6(&out_saddr6, optarg);
+			break;
+		case 'S':
+			if (cfg_l3_inner == AF_INET)
+				parse_addr4(&in_saddr4, optarg);
+			else
+				parse_addr6(&in_saddr6, optarg);
+			break;
+		case 't':
+			cfg_num_secs = strtol(optarg, NULL, 0);
+			break;
+		case 'T':
+			cfg_only_tx = true;
+			break;
+		case 'x':
+			cfg_dsfield_outer = strtol(optarg, NULL, 0);
+			break;
+		case 'X':
+			cfg_dsfield_inner = strtol(optarg, NULL, 0);
+			break;
+		}
+	}
+
+	if (cfg_only_rx && cfg_only_tx)
+		error(1, 0, "options: cannot combine rx-only and tx-only");
+
+	if (cfg_encap_proto && cfg_l3_outer == AF_UNSPEC)
+		error(1, 0, "options: must specify outer with encap");
+	else if ((!cfg_encap_proto) && cfg_l3_outer != AF_UNSPEC)
+		error(1, 0, "options: cannot combine no-encap and outer");
+	else if ((!cfg_encap_proto) && cfg_l3_extra != AF_UNSPEC)
+		error(1, 0, "options: cannot combine no-encap and extra");
+
+	if (cfg_l3_inner == AF_UNSPEC)
+		cfg_l3_inner = AF_INET6;
+	if (cfg_l3_inner == AF_INET6 && cfg_encap_proto == IPPROTO_IPIP)
+		cfg_encap_proto = IPPROTO_IPV6;
+
+	/* RFC 6040 4.2:
+	 *   on decap, if outer encountered congestion (CE == 0x3),
+	 *   but inner cannot encode ECN (NoECT == 0x0), then drop packet.
+	 */
+	if (((cfg_dsfield_outer & 0x3) == 0x3) &&
+	    ((cfg_dsfield_inner & 0x3) == 0x0))
+		cfg_expect_failure = true;
+}
+
+static void print_opts(void)
+{
+	if (cfg_l3_inner == PF_INET6) {
+		util_printaddr("inner.dest6", (void *) &in_daddr6);
+		util_printaddr("inner.source6", (void *) &in_saddr6);
+	} else {
+		util_printaddr("inner.dest4", (void *) &in_daddr4);
+		util_printaddr("inner.source4", (void *) &in_saddr4);
+	}
+
+	if (!cfg_l3_outer)
+		return;
+
+	fprintf(stderr, "encap proto:   %u\n", cfg_encap_proto);
+
+	if (cfg_l3_outer == PF_INET6) {
+		util_printaddr("outer.dest6", (void *) &out_daddr6);
+		util_printaddr("outer.source6", (void *) &out_saddr6);
+	} else {
+		util_printaddr("outer.dest4", (void *) &out_daddr4);
+		util_printaddr("outer.source4", (void *) &out_saddr4);
+	}
+
+	if (!cfg_l3_extra)
+		return;
+
+	if (cfg_l3_outer == PF_INET6) {
+		util_printaddr("extra.dest6", (void *) &extra_daddr6);
+		util_printaddr("extra.source6", (void *) &extra_saddr6);
+	} else {
+		util_printaddr("extra.dest4", (void *) &extra_daddr4);
+		util_printaddr("extra.source4", (void *) &extra_saddr4);
+	}
+
+}
+
+int main(int argc, char **argv)
+{
+	parse_opts(argc, argv);
+	print_opts();
+	return do_main();
+}
diff --git a/tools/testing/selftests/bpf/test_flow_dissector.sh b/tools/testing/selftests/bpf/test_flow_dissector.sh
new file mode 100755
index 000000000000..c0fb073b5eab
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_flow_dissector.sh
@@ -0,0 +1,115 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Load BPF flow dissector and verify it correctly dissects traffic
+export TESTNAME=test_flow_dissector
+unmount=0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ $UID != 0 ]; then
+	echo $msg please run this as root >&2
+	exit $ksft_skip
+fi
+
+# This test needs to be run in a network namespace with in_netns.sh. Check if
+# this is the case and run it with in_netns.sh if it is being run in the root
+# namespace.
+if [[ -z $(ip netns identify $$) ]]; then
+	../net/in_netns.sh "$0" "$@"
+	exit $?
+fi
+
+# Determine selftest success via shell exit code
+exit_handler()
+{
+	if (( $? == 0 )); then
+		echo "selftests: $TESTNAME [PASS]";
+	else
+		echo "selftests: $TESTNAME [FAILED]";
+	fi
+
+	set +e
+
+	# Cleanup
+	tc filter del dev lo ingress pref 1337 2> /dev/null
+	tc qdisc del dev lo ingress 2> /dev/null
+	./flow_dissector_load -d 2> /dev/null
+	if [ $unmount -ne 0 ]; then
+		umount bpffs 2> /dev/null
+	fi
+}
+
+# Exit script immediately (well catched by trap handler) if any
+# program/thing exits with a non-zero status.
+set -e
+
+# (Use 'trap -l' to list meaning of numbers)
+trap exit_handler 0 2 3 6 9
+
+# Mount BPF file system
+if /bin/mount | grep /sys/fs/bpf > /dev/null; then
+	echo "bpffs already mounted"
+else
+	echo "bpffs not mounted. Mounting..."
+	unmount=1
+	/bin/mount bpffs /sys/fs/bpf -t bpf
+fi
+
+# Attach BPF program
+./flow_dissector_load -p bpf_flow.o -s dissect
+
+# Setup
+tc qdisc add dev lo ingress
+
+echo "Testing IPv4..."
+# Drops all IP/UDP packets coming from port 9
+tc filter add dev lo parent ffff: protocol ip pref 1337 flower ip_proto \
+	udp src_port 9 action drop
+
+# Send 10 IPv4/UDP packets from port 8. Filter should not drop any.
+./test_flow_dissector -i 4 -f 8
+# Send 10 IPv4/UDP packets from port 9. Filter should drop all.
+./test_flow_dissector -i 4 -f 9 -F
+# Send 10 IPv4/UDP packets from port 10. Filter should not drop any.
+./test_flow_dissector -i 4 -f 10
+
+echo "Testing IPIP..."
+# Send 10 IPv4/IPv4/UDP packets from port 8. Filter should not drop any.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \
+	-D 192.168.0.1 -S 1.1.1.1 -f 8
+# Send 10 IPv4/IPv4/UDP packets from port 9. Filter should drop all.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \
+	-D 192.168.0.1 -S 1.1.1.1 -f 9 -F
+# Send 10 IPv4/IPv4/UDP packets from port 10. Filter should not drop any.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \
+	-D 192.168.0.1 -S 1.1.1.1 -f 10
+
+echo "Testing IPv4 + GRE..."
+# Send 10 IPv4/GRE/IPv4/UDP packets from port 8. Filter should not drop any.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \
+	-D 192.168.0.1 -S 1.1.1.1 -f 8
+# Send 10 IPv4/GRE/IPv4/UDP packets from port 9. Filter should drop all.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \
+	-D 192.168.0.1 -S 1.1.1.1 -f 9 -F
+# Send 10 IPv4/GRE/IPv4/UDP packets from port 10. Filter should not drop any.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \
+	-D 192.168.0.1 -S 1.1.1.1 -f 10
+
+tc filter del dev lo ingress pref 1337
+
+echo "Testing IPv6..."
+# Drops all IPv6/UDP packets coming from port 9
+tc filter add dev lo parent ffff: protocol ipv6 pref 1337 flower ip_proto \
+	udp src_port 9 action drop
+
+# Send 10 IPv6/UDP packets from port 8. Filter should not drop any.
+./test_flow_dissector -i 6 -f 8
+# Send 10 IPv6/UDP packets from port 9. Filter should drop all.
+./test_flow_dissector -i 6 -f 9 -F
+# Send 10 IPv6/UDP packets from port 10. Filter should not drop any.
+./test_flow_dissector -i 6 -f 10
+
+exit 0
diff --git a/tools/testing/selftests/bpf/with_addr.sh b/tools/testing/selftests/bpf/with_addr.sh
new file mode 100755
index 000000000000..ffcd3953f94c
--- /dev/null
+++ b/tools/testing/selftests/bpf/with_addr.sh
@@ -0,0 +1,54 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# add private ipv4 and ipv6 addresses to loopback
+
+readonly V6_INNER='100::a/128'
+readonly V4_INNER='192.168.0.1/32'
+
+if getopts ":s" opt; then
+  readonly SIT_DEV_NAME='sixtofourtest0'
+  readonly V6_SIT='2::/64'
+  readonly V4_SIT='172.17.0.1/32'
+  shift
+fi
+
+fail() {
+  echo "error: $*" 1>&2
+  exit 1
+}
+
+setup() {
+  ip -6 addr add "${V6_INNER}" dev lo || fail 'failed to setup v6 address'
+  ip -4 addr add "${V4_INNER}" dev lo || fail 'failed to setup v4 address'
+
+  if [[ -n "${V6_SIT}" ]]; then
+    ip link add "${SIT_DEV_NAME}" type sit remote any local any \
+	    || fail 'failed to add sit'
+    ip link set dev "${SIT_DEV_NAME}" up \
+	    || fail 'failed to bring sit device up'
+    ip -6 addr add "${V6_SIT}" dev "${SIT_DEV_NAME}" \
+	    || fail 'failed to setup v6 SIT address'
+    ip -4 addr add "${V4_SIT}" dev "${SIT_DEV_NAME}" \
+	    || fail 'failed to setup v4 SIT address'
+  fi
+
+  sleep 2	# avoid race causing bind to fail
+}
+
+cleanup() {
+  if [[ -n "${V6_SIT}" ]]; then
+    ip -4 addr del "${V4_SIT}" dev "${SIT_DEV_NAME}"
+    ip -6 addr del "${V6_SIT}" dev "${SIT_DEV_NAME}"
+    ip link del "${SIT_DEV_NAME}"
+  fi
+
+  ip -4 addr del "${V4_INNER}" dev lo
+  ip -6 addr del "${V6_INNER}" dev lo
+}
+
+trap cleanup EXIT
+
+setup
+"$@"
+exit "$?"
diff --git a/tools/testing/selftests/bpf/with_tunnels.sh b/tools/testing/selftests/bpf/with_tunnels.sh
new file mode 100755
index 000000000000..e24949ed3a20
--- /dev/null
+++ b/tools/testing/selftests/bpf/with_tunnels.sh
@@ -0,0 +1,36 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# setup tunnels for flow dissection test
+
+readonly SUFFIX="test_$(mktemp -u XXXX)"
+CONFIG="remote 127.0.0.2 local 127.0.0.1 dev lo"
+
+setup() {
+  ip link add "ipip_${SUFFIX}" type ipip ${CONFIG}
+  ip link add "gre_${SUFFIX}" type gre ${CONFIG}
+  ip link add "sit_${SUFFIX}" type sit ${CONFIG}
+
+  echo "tunnels before test:"
+  ip tunnel show
+
+  ip link set "ipip_${SUFFIX}" up
+  ip link set "gre_${SUFFIX}" up
+  ip link set "sit_${SUFFIX}" up
+}
+
+
+cleanup() {
+  ip tunnel del "ipip_${SUFFIX}"
+  ip tunnel del "gre_${SUFFIX}"
+  ip tunnel del "sit_${SUFFIX}"
+
+  echo "tunnels after test:"
+  ip tunnel show
+}
+
+trap cleanup EXIT
+
+setup
+"$@"
+exit "$?"
-- 
cgit 


From 70e88c758a6b8544b5e0d982e55d1e36f9aa0b85 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Fri, 14 Sep 2018 12:09:05 -0700
Subject: selftests/bpf: fix bpf_flow.c build

fix the following build error:
clang -I. -I./include/uapi -I../../../include/uapi -idirafter /usr/local/include -idirafter /data/users/ast/llvm/bld/lib/clang/7.0.0/include -idirafter /usr/include -Wno-compare-distinct-pointer-types \
	 -O2 -target bpf -emit-llvm -c bpf_flow.c -o - |      \
llc -march=bpf -mcpu=generic  -filetype=obj -o /data/users/ast/bpf-next/tools/testing/selftests/bpf/bpf_flow.o
LLVM ERROR: 'dissect' label emitted multiple times to assembly file
make: *** [/data/users/ast/bpf-next/tools/testing/selftests/bpf/bpf_flow.o] Error 1

Fixes: 9c98b13cc3bb ("flow_dissector: implements eBPF parser")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/bpf_flow.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/bpf_flow.c b/tools/testing/selftests/bpf/bpf_flow.c
index 5fb809d95867..107350a7821d 100644
--- a/tools/testing/selftests/bpf/bpf_flow.c
+++ b/tools/testing/selftests/bpf/bpf_flow.c
@@ -117,7 +117,7 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)
 }
 
 SEC("dissect")
-int dissect(struct __sk_buff *skb)
+int _dissect(struct __sk_buff *skb)
 {
 	if (!skb->vlan_present)
 		return parse_eth_proto(skb, skb->protocol);
-- 
cgit 


From 693b31b2fc1636f0aa7af53136d3b49f6ad9ff39 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 31 Jul 2018 17:55:57 -0300
Subject: powerpc/selftests: Wait all threads to join

Test tm-tmspr might exit before all threads stop executing, because it just
waits for the very last thread to join before proceeding/exiting.

This patch makes sure that all threads that were created will join before
proceeding/exiting.

This patch also guarantees that the amount of threads being created is equal
to thread_num.

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/tm/tm-tmspr.c | 27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/powerpc/tm/tm-tmspr.c b/tools/testing/selftests/powerpc/tm/tm-tmspr.c
index 2bda81c7bf23..df1d7d4b1c89 100644
--- a/tools/testing/selftests/powerpc/tm/tm-tmspr.c
+++ b/tools/testing/selftests/powerpc/tm/tm-tmspr.c
@@ -98,7 +98,7 @@ void texasr(void *in)
 
 int test_tmspr()
 {
-	pthread_t 	thread;
+	pthread_t	*thread;
 	int	   	thread_num;
 	unsigned long	i;
 
@@ -107,21 +107,28 @@ int test_tmspr()
 	/* To cause some context switching */
 	thread_num = 10 * sysconf(_SC_NPROCESSORS_ONLN);
 
+	thread = malloc(thread_num * sizeof(pthread_t));
+	if (thread == NULL)
+		return EXIT_FAILURE;
+
 	/* Test TFIAR and TFHAR */
-	for (i = 0 ; i < thread_num ; i += 2){
-		if (pthread_create(&thread, NULL, (void*)tfiar_tfhar, (void *)i))
+	for (i = 0; i < thread_num; i += 2) {
+		if (pthread_create(&thread[i], NULL, (void *)tfiar_tfhar,
+				   (void *)i))
 			return EXIT_FAILURE;
 	}
-	if (pthread_join(thread, NULL) != 0)
-		return EXIT_FAILURE;
-
 	/* Test TEXASR */
-	for (i = 0 ; i < thread_num ; i++){
-		if (pthread_create(&thread, NULL, (void*)texasr, (void *)i))
+	for (i = 1; i < thread_num; i += 2) {
+		if (pthread_create(&thread[i], NULL, (void *)texasr, (void *)i))
 			return EXIT_FAILURE;
 	}
-	if (pthread_join(thread, NULL) != 0)
-		return EXIT_FAILURE;
+
+	for (i = 0; i < thread_num; i++) {
+		if (pthread_join(thread[i], NULL) != 0)
+			return EXIT_FAILURE;
+	}
+
+	free(thread);
 
 	if (passed)
 		return 0;
-- 
cgit 


From 50c6b58a814d86a93c0f6964570f839632854044 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 14 Sep 2018 23:00:55 +0200
Subject: tls: fix currently broken MSG_PEEK behavior

In kTLS MSG_PEEK behavior is currently failing, strace example:

  [pid  2430] socket(AF_INET, SOCK_STREAM, IPPROTO_IP) = 3
  [pid  2430] socket(AF_INET, SOCK_STREAM, IPPROTO_IP) = 4
  [pid  2430] bind(4, {sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("0.0.0.0")}, 16) = 0
  [pid  2430] listen(4, 10)               = 0
  [pid  2430] getsockname(4, {sa_family=AF_INET, sin_port=htons(38855), sin_addr=inet_addr("0.0.0.0")}, [16]) = 0
  [pid  2430] connect(3, {sa_family=AF_INET, sin_port=htons(38855), sin_addr=inet_addr("0.0.0.0")}, 16) = 0
  [pid  2430] setsockopt(3, SOL_TCP, 0x1f /* TCP_??? */, [7564404], 4) = 0
  [pid  2430] setsockopt(3, 0x11a /* SOL_?? */, 1, "\3\0033\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"..., 40) = 0
  [pid  2430] accept(4, {sa_family=AF_INET, sin_port=htons(49636), sin_addr=inet_addr("127.0.0.1")}, [16]) = 5
  [pid  2430] setsockopt(5, SOL_TCP, 0x1f /* TCP_??? */, [7564404], 4) = 0
  [pid  2430] setsockopt(5, 0x11a /* SOL_?? */, 2, "\3\0033\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"..., 40) = 0
  [pid  2430] close(4)                    = 0
  [pid  2430] sendto(3, "test_read_peek", 14, 0, NULL, 0) = 14
  [pid  2430] sendto(3, "_mult_recs\0", 11, 0, NULL, 0) = 11
  [pid  2430] recvfrom(5, "test_read_peektest_read_peektest"..., 64, MSG_PEEK, NULL, NULL) = 64

As can be seen from strace, there are two TLS records sent,
i) 'test_read_peek' and ii) '_mult_recs\0' where we end up
peeking 'test_read_peektest_read_peektest'. This is clearly
wrong, and what happens is that given peek cannot call into
tls_sw_advance_skb() to unpause strparser and proceed with
the next skb, we end up looping over the current one, copying
the 'test_read_peek' over and over into the user provided
buffer.

Here, we can only peek into the currently held skb (current,
full TLS record) as otherwise we would end up having to hold
all the original skb(s) (depending on the peek depth) in a
separate queue when unpausing strparser to process next
records, minimally intrusive is to return only up to the
current record's size (which likely was what c46234ebb4d1
("tls: RX path for ktls") originally intended as well). Thus,
after patch we properly peek the first record:

  [pid  2046] wait4(2075,  <unfinished ...>
  [pid  2075] socket(AF_INET, SOCK_STREAM, IPPROTO_IP) = 3
  [pid  2075] socket(AF_INET, SOCK_STREAM, IPPROTO_IP) = 4
  [pid  2075] bind(4, {sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("0.0.0.0")}, 16) = 0
  [pid  2075] listen(4, 10)               = 0
  [pid  2075] getsockname(4, {sa_family=AF_INET, sin_port=htons(55115), sin_addr=inet_addr("0.0.0.0")}, [16]) = 0
  [pid  2075] connect(3, {sa_family=AF_INET, sin_port=htons(55115), sin_addr=inet_addr("0.0.0.0")}, 16) = 0
  [pid  2075] setsockopt(3, SOL_TCP, 0x1f /* TCP_??? */, [7564404], 4) = 0
  [pid  2075] setsockopt(3, 0x11a /* SOL_?? */, 1, "\3\0033\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"..., 40) = 0
  [pid  2075] accept(4, {sa_family=AF_INET, sin_port=htons(45732), sin_addr=inet_addr("127.0.0.1")}, [16]) = 5
  [pid  2075] setsockopt(5, SOL_TCP, 0x1f /* TCP_??? */, [7564404], 4) = 0
  [pid  2075] setsockopt(5, 0x11a /* SOL_?? */, 2, "\3\0033\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"..., 40) = 0
  [pid  2075] close(4)                    = 0
  [pid  2075] sendto(3, "test_read_peek", 14, 0, NULL, 0) = 14
  [pid  2075] sendto(3, "_mult_recs\0", 11, 0, NULL, 0) = 11
  [pid  2075] recvfrom(5, "test_read_peek", 64, MSG_PEEK, NULL, NULL) = 14

Fixes: c46234ebb4d1 ("tls: RX path for ktls")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c                  |  8 +++++++
 tools/testing/selftests/net/tls.c | 49 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 57 insertions(+)

(limited to 'tools/testing')

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 9e918489f4fb..b9c6ecfbcfea 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -931,7 +931,15 @@ int tls_sw_recvmsg(struct sock *sk,
 				if (control != TLS_RECORD_TYPE_DATA)
 					goto recv_end;
 			}
+		} else {
+			/* MSG_PEEK right now cannot look beyond current skb
+			 * from strparser, meaning we cannot advance skb here
+			 * and thus unpause strparser since we'd loose original
+			 * one.
+			 */
+			break;
 		}
+
 		/* If we have a new message from strparser, continue now. */
 		if (copied >= target && !ctx->recv_pkt)
 			break;
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index b3ebf2646e52..8fdfeafaf8c0 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -502,6 +502,55 @@ TEST_F(tls, recv_peek_multiple)
 	EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
 }
 
+TEST_F(tls, recv_peek_multiple_records)
+{
+	char const *test_str = "test_read_peek_mult_recs";
+	char const *test_str_first = "test_read_peek";
+	char const *test_str_second = "_mult_recs";
+	int len;
+	char buf[64];
+
+	len = strlen(test_str_first);
+	EXPECT_EQ(send(self->fd, test_str_first, len, 0), len);
+
+	len = strlen(test_str_second) + 1;
+	EXPECT_EQ(send(self->fd, test_str_second, len, 0), len);
+
+	len = sizeof(buf);
+	memset(buf, 0, len);
+	EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1);
+
+	/* MSG_PEEK can only peek into the current record. */
+	len = strlen(test_str_first) + 1;
+	EXPECT_EQ(memcmp(test_str_first, buf, len), 0);
+
+	len = sizeof(buf);
+	memset(buf, 0, len);
+	EXPECT_NE(recv(self->cfd, buf, len, 0), -1);
+
+	/* Non-MSG_PEEK will advance strparser (and therefore record)
+	 * however.
+	 */
+	len = strlen(test_str) + 1;
+	EXPECT_EQ(memcmp(test_str, buf, len), 0);
+
+	/* MSG_MORE will hold current record open, so later MSG_PEEK
+	 * will see everything.
+	 */
+	len = strlen(test_str_first);
+	EXPECT_EQ(send(self->fd, test_str_first, len, MSG_MORE), len);
+
+	len = strlen(test_str_second) + 1;
+	EXPECT_EQ(send(self->fd, test_str_second, len, 0), len);
+
+	len = sizeof(buf);
+	memset(buf, 0, len);
+	EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1);
+
+	len = strlen(test_str) + 1;
+	EXPECT_EQ(memcmp(test_str, buf, len), 0);
+}
+
 TEST_F(tls, pollin)
 {
 	char const *test_str = "test_poll";
-- 
cgit 


From 0185e2e69f8e640defb77380b6b0d054c2ec12e4 Mon Sep 17 00:00:00 2001
From: Vakul Garg <vakul.garg@nxp.com>
Date: Sun, 16 Sep 2018 10:04:28 +0530
Subject: selftests/tls: Add MSG_WAITALL in recv() syscall

A number of tls selftests rely upon recv() to return an exact number of
data bytes. When tls record crypto is done using an async accelerator,
it is possible that recv() returns lesser than expected number bytes.
This leads to failure of many test cases. To fix it, MSG_WAITALL has
been used in flags passed to recv() syscall.

Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/tls.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 07daff076ce0..96fc6fe70293 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -121,11 +121,11 @@ TEST_F(tls, send_then_sendfile)
 	buf = (char *)malloc(st.st_size);
 
 	EXPECT_EQ(send(self->fd, test_str, to_send, 0), to_send);
-	EXPECT_EQ(recv(self->cfd, recv_buf, to_send, 0), to_send);
+	EXPECT_EQ(recv(self->cfd, recv_buf, to_send, MSG_WAITALL), to_send);
 	EXPECT_EQ(memcmp(test_str, recv_buf, to_send), 0);
 
 	EXPECT_GE(sendfile(self->fd, filefd, 0, st.st_size), 0);
-	EXPECT_EQ(recv(self->cfd, buf, st.st_size, 0), st.st_size);
+	EXPECT_EQ(recv(self->cfd, buf, st.st_size, MSG_WAITALL), st.st_size);
 }
 
 TEST_F(tls, recv_max)
@@ -160,7 +160,7 @@ TEST_F(tls, msg_more)
 	EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len);
 	EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_DONTWAIT), -1);
 	EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
-	EXPECT_EQ(recv(self->cfd, buf, send_len * 2, MSG_DONTWAIT),
+	EXPECT_EQ(recv(self->cfd, buf, send_len * 2, MSG_WAITALL),
 		  send_len * 2);
 	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
 }
@@ -180,7 +180,7 @@ TEST_F(tls, sendmsg_single)
 	msg.msg_iov = &vec;
 	msg.msg_iovlen = 1;
 	EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len);
-	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_WAITALL), send_len);
 	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
 }
 
@@ -306,7 +306,7 @@ TEST_F(tls, splice_from_pipe2)
 	EXPECT_GE(splice(p[0], NULL, self->fd, NULL, 8000, 0), 0);
 	EXPECT_GE(write(p2[1], mem_send + 8000, 8000), 0);
 	EXPECT_GE(splice(p2[0], NULL, self->fd, NULL, 8000, 0), 0);
-	EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+	EXPECT_EQ(recv(self->cfd, mem_recv, send_len, MSG_WAITALL), send_len);
 	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
 }
 
@@ -436,7 +436,7 @@ TEST_F(tls, multiple_send_single_recv)
 	EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0);
 	EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0);
 	memset(recv_mem, 0, total_len);
-	EXPECT_EQ(recv(self->cfd, recv_mem, total_len, 0), total_len);
+	EXPECT_EQ(recv(self->cfd, recv_mem, total_len, MSG_WAITALL), total_len);
 
 	EXPECT_EQ(memcmp(send_mem, recv_mem, send_len), 0);
 	EXPECT_EQ(memcmp(send_mem, recv_mem + send_len, send_len), 0);
@@ -537,7 +537,7 @@ TEST_F(tls, pollin)
 
 	EXPECT_EQ(poll(&fd, 1, 20), 1);
 	EXPECT_EQ(fd.revents & POLLIN, 1);
-	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_WAITALL), send_len);
 	/* Test timing out */
 	EXPECT_EQ(poll(&fd, 1, 20), 0);
 }
@@ -555,7 +555,7 @@ TEST_F(tls, poll_wait)
 	/* Set timeout to inf. secs */
 	EXPECT_EQ(poll(&fd, 1, -1), 1);
 	EXPECT_EQ(fd.revents & POLLIN, 1);
-	EXPECT_EQ(recv(self->cfd, recv_mem, send_len, 0), send_len);
+	EXPECT_EQ(recv(self->cfd, recv_mem, send_len, MSG_WAITALL), send_len);
 }
 
 TEST_F(tls, blocking)
@@ -701,7 +701,7 @@ TEST_F(tls, control_msg)
 	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1);
 
 	vec.iov_base = buf;
-	EXPECT_EQ(recvmsg(self->cfd, &msg, 0), send_len);
+	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);
-- 
cgit 


From 0a286afee5a1e8dca86d824209dbd3200294f86f Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 17 Sep 2018 15:30:06 +0200
Subject: selftests: pmtu: properly redirect stderr to /dev/null

The cleanup function uses "$CMD 2 > /dev/null", which doesn't actually
send stderr to /dev/null, so when the netns doesn't exist, the error
message is shown. Use "2> /dev/null" instead, so that those messages
disappear, as was intended.

Fixes: d1f1b9cbf34c ("selftests: net: Introduce first PMTU test")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/pmtu.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 32a194e3e07a..0ab9423d009f 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -178,8 +178,8 @@ setup() {
 
 cleanup() {
 	[ ${cleanup_done} -eq 1 ] && return
-	ip netns del ${NS_A} 2 > /dev/null
-	ip netns del ${NS_B} 2 > /dev/null
+	ip netns del ${NS_A} 2> /dev/null
+	ip netns del ${NS_B} 2> /dev/null
 	cleanup_done=1
 }
 
-- 
cgit 


From 44d947eff19d64384efc06069509db7a0a1103b0 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Wed, 12 Sep 2018 17:31:05 -0300
Subject: selftests/powerpc: Do not fail with reschedule

There are cases where the test is not expecting to have the transaction
aborted, but, the test process might have been rescheduled, either in the
OS level or by KVM (if it is running on a KVM guest machine). The process
reschedule will cause a treclaim/recheckpoint which will cause the
transaction to doom, aborting the transaction as soon as the process is
rescheduled back to the CPU. This might cause the test to fail, but this is
not a failure in essence.

If that is the case, TEXASR[FC] is indicated with either
TM_CAUSE_RESCHEDULE or TM_CAUSE_KVM_RESCHEDULE for KVM interruptions.

In this scenario, ignore these two failures and avoid the whole test to
return failure.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Gustavo Romero <gromero@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/tm/tm-unavailable.c | 9 ++++++---
 tools/testing/selftests/powerpc/tm/tm.h             | 9 +++++++++
 2 files changed, 15 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/powerpc/tm/tm-unavailable.c b/tools/testing/selftests/powerpc/tm/tm-unavailable.c
index 156c8e750259..09894f4ff62e 100644
--- a/tools/testing/selftests/powerpc/tm/tm-unavailable.c
+++ b/tools/testing/selftests/powerpc/tm/tm-unavailable.c
@@ -236,7 +236,8 @@ void *tm_una_ping(void *input)
 	}
 
 	/* Check if we were not expecting a failure and a it occurred. */
-	if (!expecting_failure() && is_failure(cr_)) {
+	if (!expecting_failure() && is_failure(cr_) &&
+	    !failure_is_reschedule()) {
 		printf("\n\tUnexpected transaction failure 0x%02lx\n\t",
 			failure_code());
 		return (void *) -1;
@@ -244,9 +245,11 @@ void *tm_una_ping(void *input)
 
 	/*
 	 * Check if TM failed due to the cause we were expecting. 0xda is a
-	 * TM_CAUSE_FAC_UNAV cause, otherwise it's an unexpected cause.
+	 * TM_CAUSE_FAC_UNAV cause, otherwise it's an unexpected cause, unless
+	 * it was caused by a reschedule.
 	 */
-	if (is_failure(cr_) && !failure_is_unavailable()) {
+	if (is_failure(cr_) && !failure_is_unavailable() &&
+	    !failure_is_reschedule()) {
 		printf("\n\tUnexpected failure cause 0x%02lx\n\t",
 			failure_code());
 		return (void *) -1;
diff --git a/tools/testing/selftests/powerpc/tm/tm.h b/tools/testing/selftests/powerpc/tm/tm.h
index df4204247d45..5518b1d4ef8b 100644
--- a/tools/testing/selftests/powerpc/tm/tm.h
+++ b/tools/testing/selftests/powerpc/tm/tm.h
@@ -52,6 +52,15 @@ static inline bool failure_is_unavailable(void)
 	return (failure_code() & TM_CAUSE_FAC_UNAV) == TM_CAUSE_FAC_UNAV;
 }
 
+static inline bool failure_is_reschedule(void)
+{
+	if ((failure_code() & TM_CAUSE_RESCHED) == TM_CAUSE_RESCHED ||
+	    (failure_code() & TM_CAUSE_KVM_RESCHED) == TM_CAUSE_KVM_RESCHED)
+		return true;
+
+	return false;
+}
+
 static inline bool failure_is_nesting(void)
 {
 	return (__builtin_get_texasru() & 0x400000);
-- 
cgit 


From 6bd317d3c865ebcddcb287a424093fe4758c40ef Mon Sep 17 00:00:00 2001
From: Lei Yang <Lei.Yang@windriver.com>
Date: Wed, 29 Aug 2018 15:04:08 +0800
Subject: kvm: selftests: use -pthread instead of -lpthread

I run into the following error

testing/selftests/kvm/dirty_log_test.c:285: undefined reference to `pthread_create'
testing/selftests/kvm/dirty_log_test.c:297: undefined reference to `pthread_join'
collect2: error: ld returned 1 exit status

my gcc version is gcc version 4.8.4
"-pthread" would work everywhere

Signed-off-by: Lei Yang <Lei.Yang@windriver.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 03b0f551bedf..48c970c90353 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -20,7 +20,7 @@ INSTALL_HDR_PATH = $(top_srcdir)/usr
 LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
 LINUX_TOOL_INCLUDE = $(top_srcdir)tools/include
 CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -I..
-LDFLAGS += -lpthread
+LDFLAGS += -pthread
 
 # After inclusion, $(OUTPUT) is defined and
 # $(TEST_GEN_PROGS) starts with $(OUTPUT)/
-- 
cgit 


From 8b56ee91ffc88ea01400c012e10fe22a9d233265 Mon Sep 17 00:00:00 2001
From: Drew Schmitt <dasch@google.com>
Date: Mon, 20 Aug 2018 10:32:16 -0700
Subject: kvm: selftests: Add platform_info_test

Test guest access to MSR_PLATFORM_INFO when the capability is enabled
or disabled.

Signed-off-by: Drew Schmitt <dasch@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/.gitignore           |   1 +
 tools/testing/selftests/kvm/Makefile             |   3 +-
 tools/testing/selftests/kvm/include/kvm_util.h   |   4 +
 tools/testing/selftests/kvm/lib/kvm_util.c       |  89 ++++++++++++++++++
 tools/testing/selftests/kvm/platform_info_test.c | 110 +++++++++++++++++++++++
 5 files changed, 206 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/kvm/platform_info_test.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 4202139d81d9..5c34752e1cff 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,4 +1,5 @@
 cr4_cpuid_sync_test
+platform_info_test
 set_sregs_test
 sync_regs_test
 vmx_tsc_adjust_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 48c970c90353..37e4bd8619a6 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -6,7 +6,8 @@ UNAME_M := $(shell uname -m)
 LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c
 LIBKVM_x86_64 = lib/x86.c lib/vmx.c
 
-TEST_GEN_PROGS_x86_64 = set_sregs_test
+TEST_GEN_PROGS_x86_64 = platform_info_test
+TEST_GEN_PROGS_x86_64 += set_sregs_test
 TEST_GEN_PROGS_x86_64 += sync_regs_test
 TEST_GEN_PROGS_x86_64 += vmx_tsc_adjust_test
 TEST_GEN_PROGS_x86_64 += cr4_cpuid_sync_test
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index bb5a25fb82c6..3acf9a91704c 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -50,6 +50,7 @@ enum vm_mem_backing_src_type {
 };
 
 int kvm_check_cap(long cap);
+int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap);
 
 struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);
 void kvm_vm_free(struct kvm_vm *vmp);
@@ -108,6 +109,9 @@ void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid,
 			  struct kvm_vcpu_events *events);
 void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid,
 			  struct kvm_vcpu_events *events);
+uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index);
+void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
+	uint64_t msr_value);
 
 const char *exit_reason_str(unsigned int exit_reason);
 
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index e9ba389c48db..6fd8c089cafc 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -63,6 +63,29 @@ int kvm_check_cap(long cap)
 	return ret;
 }
 
+/* VM Enable Capability
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   cap - Capability
+ *
+ * Output Args: None
+ *
+ * Return: On success, 0. On failure a TEST_ASSERT failure is produced.
+ *
+ * Enables a capability (KVM_CAP_*) on the VM.
+ */
+int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap)
+{
+	int ret;
+
+	ret = ioctl(vm->fd, KVM_ENABLE_CAP, cap);
+	TEST_ASSERT(ret == 0, "KVM_ENABLE_CAP IOCTL failed,\n"
+		"  rc: %i errno: %i", ret, errno);
+
+	return ret;
+}
+
 static void vm_open(struct kvm_vm *vm, int perm)
 {
 	vm->kvm_fd = open(KVM_DEV_PATH, perm);
@@ -1220,6 +1243,72 @@ void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid,
 		ret, errno);
 }
 
+/* VCPU Get MSR
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpuid - VCPU ID
+ *   msr_index - Index of MSR
+ *
+ * Output Args: None
+ *
+ * Return: On success, value of the MSR. On failure a TEST_ASSERT is produced.
+ *
+ * Get value of MSR for VCPU.
+ */
+uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+	struct {
+		struct kvm_msrs header;
+		struct kvm_msr_entry entry;
+	} buffer = {};
+	int r;
+
+	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+	buffer.header.nmsrs = 1;
+	buffer.entry.index = msr_index;
+	r = ioctl(vcpu->fd, KVM_GET_MSRS, &buffer.header);
+	TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n"
+		"  rc: %i errno: %i", r, errno);
+
+	return buffer.entry.data;
+}
+
+/* VCPU Set MSR
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpuid - VCPU ID
+ *   msr_index - Index of MSR
+ *   msr_value - New value of MSR
+ *
+ * Output Args: None
+ *
+ * Return: On success, nothing. On failure a TEST_ASSERT is produced.
+ *
+ * Set value of MSR for VCPU.
+ */
+void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
+	uint64_t msr_value)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+	struct {
+		struct kvm_msrs header;
+		struct kvm_msr_entry entry;
+	} buffer = {};
+	int r;
+
+	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+	memset(&buffer, 0, sizeof(buffer));
+	buffer.header.nmsrs = 1;
+	buffer.entry.index = msr_index;
+	buffer.entry.data = msr_value;
+	r = ioctl(vcpu->fd, KVM_SET_MSRS, &buffer.header);
+	TEST_ASSERT(r == 1, "KVM_SET_MSRS IOCTL failed,\n"
+		"  rc: %i errno: %i", r, errno);
+}
+
 /* VM VCPU Args Set
  *
  * Input Args:
diff --git a/tools/testing/selftests/kvm/platform_info_test.c b/tools/testing/selftests/kvm/platform_info_test.c
new file mode 100644
index 000000000000..3764e7121265
--- /dev/null
+++ b/tools/testing/selftests/kvm/platform_info_test.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test for x86 KVM_CAP_MSR_PLATFORM_INFO
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Verifies expected behavior of controlling guest access to
+ * MSR_PLATFORM_INFO.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#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 "x86.h"
+
+#define VCPU_ID 0
+#define MSR_PLATFORM_INFO_MAX_TURBO_RATIO 0xff00
+
+static void guest_code(void)
+{
+	uint64_t msr_platform_info;
+
+	for (;;) {
+		msr_platform_info = rdmsr(MSR_PLATFORM_INFO);
+		GUEST_SYNC(msr_platform_info);
+		asm volatile ("inc %r11");
+	}
+}
+
+static void set_msr_platform_info_enabled(struct kvm_vm *vm, bool enable)
+{
+	struct kvm_enable_cap cap = {};
+
+	cap.cap = KVM_CAP_MSR_PLATFORM_INFO;
+	cap.flags = 0;
+	cap.args[0] = (int)enable;
+	vm_enable_cap(vm, &cap);
+}
+
+static void test_msr_platform_info_enabled(struct kvm_vm *vm)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+	struct guest_args args;
+
+	set_msr_platform_info_enabled(vm, true);
+	vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			"Exit_reason other than KVM_EXIT_IO: %u (%s),\n",
+			run->exit_reason,
+			exit_reason_str(run->exit_reason));
+	guest_args_read(vm, VCPU_ID, &args);
+	TEST_ASSERT(args.port == GUEST_PORT_SYNC,
+			"Received IO from port other than PORT_HOST_SYNC: %u\n",
+			run->io.port);
+	TEST_ASSERT((args.arg1 & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) ==
+		MSR_PLATFORM_INFO_MAX_TURBO_RATIO,
+		"Expected MSR_PLATFORM_INFO to have max turbo ratio mask: %i.",
+		MSR_PLATFORM_INFO_MAX_TURBO_RATIO);
+}
+
+static void test_msr_platform_info_disabled(struct kvm_vm *vm)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+
+	set_msr_platform_info_enabled(vm, false);
+	vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN,
+			"Exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n",
+			run->exit_reason,
+			exit_reason_str(run->exit_reason));
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_vm *vm;
+	struct kvm_run *state;
+	int rv;
+	uint64_t msr_platform_info;
+
+	/* Tell stdout not to buffer its content */
+	setbuf(stdout, NULL);
+
+	rv = kvm_check_cap(KVM_CAP_MSR_PLATFORM_INFO);
+	if (!rv) {
+		fprintf(stderr,
+			"KVM_CAP_MSR_PLATFORM_INFO not supported, skip test\n");
+		exit(KSFT_SKIP);
+	}
+
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+	msr_platform_info = vcpu_get_msr(vm, VCPU_ID, MSR_PLATFORM_INFO);
+	vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO,
+		msr_platform_info | MSR_PLATFORM_INFO_MAX_TURBO_RATIO);
+	test_msr_platform_info_disabled(vm);
+	test_msr_platform_info_enabled(vm);
+	vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, msr_platform_info);
+
+	kvm_vm_free(vm);
+
+	return 0;
+}
-- 
cgit 


From 3136a3698804f55a26f68e8c897d7ccf254923ad Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 20 Sep 2018 09:21:34 +0300
Subject: selftests: forwarding: lib: Add ethtool_stats_get()

Add a new service function to obtain ethtool counters.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index ca53b539aa2d..4c2351996a7f 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -494,6 +494,14 @@ tc_rule_stats_get()
 	    | jq '.[1].options.actions[].stats.packets'
 }
 
+ethtool_stats_get()
+{
+	local dev=$1; shift
+	local stat=$1; shift
+
+	ethtool -S $dev | grep "^ *$stat:" | head -n 1 | cut -d: -f2
+}
+
 mac_get()
 {
 	local if_name=$1
-- 
cgit 


From a381ed12ea33888a08f0e3e5ba22a255fa5f7257 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 20 Sep 2018 09:21:35 +0300
Subject: selftests: forwarding: lib: Add mtu_set(), mtu_restore()

Some selftests need to tweak MTU of an interface, and naturally should
at teardown restore the MTU back to the original value. Add two
functions to facilitate this MTU handling: mtu_set() to change MTU
value, and mtu_reset() to change it back to what it was before.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 4c2351996a7f..0e73698b2048 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -549,6 +549,23 @@ forwarding_restore()
 	sysctl_restore net.ipv4.conf.all.forwarding
 }
 
+declare -A MTU_ORIG
+mtu_set()
+{
+	local dev=$1; shift
+	local mtu=$1; shift
+
+	MTU_ORIG["$dev"]=$(ip -j link show dev $dev | jq -e '.[].mtu')
+	ip link set dev $dev mtu $mtu
+}
+
+mtu_restore()
+{
+	local dev=$1; shift
+
+	ip link set dev $dev mtu ${MTU_ORIG["$dev"]}
+}
+
 tc_offload_check()
 {
 	local num_netifs=${1:-$NUM_NETIFS}
-- 
cgit 


From b5638d46c90a6998859a4fc9ea697b264da96092 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 20 Sep 2018 09:21:36 +0300
Subject: selftests: mlxsw: Add a test for UC behavior under MC flood

A so-called "MC-aware" mode has recently been enabled in mlxsw. In
MC-aware mode, BUM traffic is handled in a special way so that when a
switch is flooded with BUM, UC performance isn't unduly impacted.
Without enablement of this mode, a stream of BUM traffic can cause
sustained UC throughput drop in excess of 99 %.

Add a test for this behavior. Compare how much UC throughput degrades as
a stream of broadcast frames floods the switch. A minimal degradation is
tolerated to cover for glitches in traffic injection performance.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/qos_mc_aware.sh    | 347 +++++++++++++++++++++
 1 file changed, 347 insertions(+)
 create mode 100644 tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
new file mode 100644
index 000000000000..0150bb2741eb
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
@@ -0,0 +1,347 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# A test for switch behavior under MC overload. An issue in Spectrum chips
+# causes throughput of UC traffic to drop severely when a switch is under heavy
+# MC load. This issue can be overcome by putting the switch to MC-aware mode.
+# This test verifies that UC performance stays intact even as the switch is
+# under MC flood, and therefore that the MC-aware mode is enabled and correctly
+# configured.
+#
+# Because mlxsw throttles CPU port, the traffic can't actually reach userspace
+# at full speed. That makes it impossible to use iperf3 to simply measure the
+# throughput, because many packets (that reach $h3) don't get to the kernel at
+# all even in UDP mode (the situation is even worse in TCP mode, where one can't
+# hope to see more than a couple Mbps).
+#
+# So instead we send traffic with mausezahn and use RX ethtool counters at $h3.
+# Multicast traffic is untagged, unicast traffic is tagged with PCP 1. Therefore
+# each gets a different priority and we can use per-prio ethtool counters to
+# measure the throughput. In order to avoid prioritizing unicast traffic, prio
+# qdisc is installed on $swp3 and maps all priorities to the same band #7 (and
+# thus TC 0).
+#
+# Mausezahn can't actually saturate the links unless it's using large frames.
+# Thus we set MTU to 10K on all involved interfaces. Then both unicast and
+# multicast traffic uses 8K frames.
+#
+# +-----------------------+                +----------------------------------+
+# | H1                    |                |                               H2 |
+# |                       |                |  unicast --> + $h2.111           |
+# |                       |                |  traffic     | 192.0.2.129/28    |
+# |          multicast    |                |              | e-qos-map 0:1     |
+# |          traffic      |                |              |                   |
+# | $h1 + <-----          |                |              + $h2               |
+# +-----|-----------------+                +--------------|-------------------+
+#       |                                                 |
+# +-----|-------------------------------------------------|-------------------+
+# |     + $swp1                                           + $swp2             |
+# |     | >1Gbps                                          | >1Gbps            |
+# | +---|----------------+                     +----------|----------------+  |
+# | |   + $swp1.1        |                     |          + $swp2.111      |  |
+# | |                BR1 |             SW      | BR111                     |  |
+# | |   + $swp3.1        |                     |          + $swp3.111      |  |
+# | +---|----------------+                     +----------|----------------+  |
+# |     \_________________________________________________/                   |
+# |                                    |                                      |
+# |                                    + $swp3                                |
+# |                                    | 1Gbps bottleneck                     |
+# |                                    | prio qdisc: {0..7} -> 7              |
+# +------------------------------------|--------------------------------------+
+#                                      |
+#                                   +--|-----------------+
+#                                   |  + $h3          H3 |
+#                                   |  |                 |
+#                                   |  + $h3.111         |
+#                                   |    192.0.2.130/28  |
+#                                   +--------------------+
+
+ALL_TESTS="
+	ping_ipv4
+	test_mc_aware
+"
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+NUM_NETIFS=6
+source $lib_dir/lib.sh
+
+h1_create()
+{
+	simple_if_init $h1
+	mtu_set $h1 10000
+}
+
+h1_destroy()
+{
+	mtu_restore $h1
+	simple_if_fini $h1
+}
+
+h2_create()
+{
+	simple_if_init $h2
+	mtu_set $h2 10000
+
+	vlan_create $h2 111 v$h2 192.0.2.129/28
+	ip link set dev $h2.111 type vlan egress-qos-map 0:1
+}
+
+h2_destroy()
+{
+	vlan_destroy $h2 111
+
+	mtu_restore $h2
+	simple_if_fini $h2
+}
+
+h3_create()
+{
+	simple_if_init $h3
+	mtu_set $h3 10000
+
+	vlan_create $h3 111 v$h3 192.0.2.130/28
+}
+
+h3_destroy()
+{
+	vlan_destroy $h3 111
+
+	mtu_restore $h3
+	simple_if_fini $h3
+}
+
+switch_create()
+{
+	ip link set dev $swp1 up
+	mtu_set $swp1 10000
+
+	ip link set dev $swp2 up
+	mtu_set $swp2 10000
+
+	ip link set dev $swp3 up
+	mtu_set $swp3 10000
+
+	vlan_create $swp2 111
+	vlan_create $swp3 111
+
+	ethtool -s $swp3 speed 1000 autoneg off
+	tc qdisc replace dev $swp3 root handle 3: \
+	   prio bands 8 priomap 7 7 7 7 7 7 7 7
+
+	ip link add name br1 type bridge vlan_filtering 0
+	ip link set dev br1 up
+	ip link set dev $swp1 master br1
+	ip link set dev $swp3 master br1
+
+	ip link add name br111 type bridge vlan_filtering 0
+	ip link set dev br111 up
+	ip link set dev $swp2.111 master br111
+	ip link set dev $swp3.111 master br111
+}
+
+switch_destroy()
+{
+	ip link del dev br111
+	ip link del dev br1
+
+	tc qdisc del dev $swp3 root handle 3:
+	ethtool -s $swp3 autoneg on
+
+	vlan_destroy $swp3 111
+	vlan_destroy $swp2 111
+
+	mtu_restore $swp3
+	ip link set dev $swp3 down
+
+	mtu_restore $swp2
+	ip link set dev $swp2 down
+
+	mtu_restore $swp1
+	ip link set dev $swp1 down
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	h3mac=$(mac_get $h3)
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+	h3_create
+	switch_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	switch_destroy
+	h3_destroy
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test $h2 192.0.2.130
+}
+
+humanize()
+{
+	local speed=$1; shift
+
+	for unit in bps Kbps Mbps Gbps; do
+		if (($(echo "$speed < 1024" | bc))); then
+			break
+		fi
+
+		speed=$(echo "scale=1; $speed / 1024" | bc)
+	done
+
+	echo "$speed${unit}"
+}
+
+rate()
+{
+	local t0=$1; shift
+	local t1=$1; shift
+	local interval=$1; shift
+
+	echo $((8 * (t1 - t0) / interval))
+}
+
+check_rate()
+{
+	local rate=$1; shift
+	local min=$1; shift
+	local what=$1; shift
+
+	if ((rate > min)); then
+		return 0
+	fi
+
+	echo "$what $(humanize $ir) < $(humanize $min_ingress)" > /dev/stderr
+	return 1
+}
+
+measure_uc_rate()
+{
+	local what=$1; shift
+
+	local interval=10
+	local i
+	local ret=0
+
+	# Dips in performance might cause momentary ingress rate to drop below
+	# 1Gbps. That wouldn't saturate egress and MC would thus get through,
+	# seemingly winning bandwidth on account of UC. Demand at least 2Gbps
+	# average ingress rate to somewhat mitigate this.
+	local min_ingress=2147483648
+
+	mausezahn $h2.111 -p 8000 -A 192.0.2.129 -B 192.0.2.130 -c 0 \
+		-a own -b $h3mac -t udp -q &
+	sleep 1
+
+	for i in {5..0}; do
+		local t0=$(ethtool_stats_get $h3 rx_octets_prio_1)
+		local u0=$(ethtool_stats_get $swp2 rx_octets_prio_1)
+		sleep $interval
+		local t1=$(ethtool_stats_get $h3 rx_octets_prio_1)
+		local u1=$(ethtool_stats_get $swp2 rx_octets_prio_1)
+
+		local ir=$(rate $u0 $u1 $interval)
+		local er=$(rate $t0 $t1 $interval)
+
+		if check_rate $ir $min_ingress "$what ingress rate"; then
+			break
+		fi
+
+		# Fail the test if we can't get the throughput.
+		if ((i == 0)); then
+			ret=1
+		fi
+	done
+
+	# Suppress noise from killing mausezahn.
+	{ kill %% && wait; } 2>/dev/null
+
+	echo $ir $er
+	exit $ret
+}
+
+test_mc_aware()
+{
+	RET=0
+
+	local -a uc_rate
+	uc_rate=($(measure_uc_rate "UC-only"))
+	check_err $? "Could not get high enough UC-only ingress rate"
+	local ucth1=${uc_rate[1]}
+
+	mausezahn $h1 -p 8000 -c 0 -a own -b bc -t udp -q &
+
+	local d0=$(date +%s)
+	local t0=$(ethtool_stats_get $h3 rx_octets_prio_0)
+	local u0=$(ethtool_stats_get $swp1 rx_octets_prio_0)
+
+	local -a uc_rate_2
+	uc_rate_2=($(measure_uc_rate "UC+MC"))
+	check_err $? "Could not get high enough UC+MC ingress rate"
+	local ucth2=${uc_rate_2[1]}
+
+	local d1=$(date +%s)
+	local t1=$(ethtool_stats_get $h3 rx_octets_prio_0)
+	local u1=$(ethtool_stats_get $swp1 rx_octets_prio_0)
+
+	local deg=$(bc <<< "
+			scale=2
+			ret = 100 * ($ucth1 - $ucth2) / $ucth1
+			if (ret > 0) { ret } else { 0 }
+		    ")
+	check_err $(bc <<< "$deg > 10")
+
+	local interval=$((d1 - d0))
+	local mc_ir=$(rate $u0 $u1 $interval)
+	local mc_er=$(rate $t0 $t1 $interval)
+
+	# Suppress noise from killing mausezahn.
+	{ kill %% && wait; } 2>/dev/null
+
+	log_test "UC performace under MC overload"
+
+	echo "UC-only throughput  $(humanize $ucth1)"
+	echo "UC+MC throughput    $(humanize $ucth2)"
+	echo "Degradation         $deg %"
+	echo
+	echo "Full report:"
+	echo "  UC only:"
+	echo "    ingress UC throughput $(humanize ${uc_rate[0]})"
+	echo "    egress UC throughput  $(humanize ${uc_rate[1]})"
+	echo "  UC+MC:"
+	echo "    ingress UC throughput $(humanize ${uc_rate_2[0]})"
+	echo "    egress UC throughput  $(humanize ${uc_rate_2[1]})"
+	echo "    ingress MC throughput $(humanize $mc_ir)"
+	echo "    egress MC throughput  $(humanize $mc_er)"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit 


From 5028027844cfc6168e39650abecd817ba64c9d98 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Tue, 18 Sep 2018 09:01:54 -0700
Subject: bpf: test_maps, only support ESTABLISHED socks

Ensure that sockets added to a sock{map|hash} that is not in the
ESTABLISHED state is rejected.

Fixes: 1aa12bdf1bfb ("bpf: sockmap, add sock close() hook to remove socks")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_maps.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 6f54f84144a0..9b552c0fc47d 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -580,7 +580,11 @@ static void test_sockmap(int tasks, void *data)
 	/* Test update without programs */
 	for (i = 0; i < 6; i++) {
 		err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY);
-		if (err) {
+		if (i < 2 && !err) {
+			printf("Allowed update sockmap '%i:%i' not in ESTABLISHED\n",
+			       i, sfd[i]);
+			goto out_sockmap;
+		} else if (i >= 2 && err) {
 			printf("Failed noprog update sockmap '%i:%i'\n",
 			       i, sfd[i]);
 			goto out_sockmap;
@@ -741,7 +745,7 @@ static void test_sockmap(int tasks, void *data)
 	}
 
 	/* Test map update elem afterwards fd lives in fd and map_fd */
-	for (i = 0; i < 6; i++) {
+	for (i = 2; i < 6; i++) {
 		err = bpf_map_update_elem(map_fd_rx, &i, &sfd[i], BPF_ANY);
 		if (err) {
 			printf("Failed map_fd_rx update sockmap %i '%i:%i'\n",
@@ -845,7 +849,7 @@ static void test_sockmap(int tasks, void *data)
 	}
 
 	/* Delete the elems without programs */
-	for (i = 0; i < 6; i++) {
+	for (i = 2; i < 6; i++) {
 		err = bpf_map_delete_elem(fd, &i);
 		if (err) {
 			printf("Failed delete sockmap %i '%i:%i'\n",
-- 
cgit 


From bccc17118bcf3c62c947361d51760334f6602f43 Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Fri, 21 Sep 2018 11:17:17 -0700
Subject: selftests/net: add ipv6 tests to ip_defrag selftest

This patch adds ipv6 defragmentation tests to ip_defrag selftest,
to complement existing ipv4 tests.

Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/ip_defrag.c  | 249 ++++++++++++++++++++-----------
 tools/testing/selftests/net/ip_defrag.sh |  39 +++--
 2 files changed, 190 insertions(+), 98 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/ip_defrag.c b/tools/testing/selftests/net/ip_defrag.c
index 55fdcdc78eef..2366dc6bce71 100644
--- a/tools/testing/selftests/net/ip_defrag.c
+++ b/tools/testing/selftests/net/ip_defrag.c
@@ -23,21 +23,28 @@ static bool		cfg_overlap;
 static unsigned short	cfg_port = 9000;
 
 const struct in_addr addr4 = { .s_addr = __constant_htonl(INADDR_LOOPBACK + 2) };
+const struct in6_addr addr6 = IN6ADDR_LOOPBACK_INIT;
 
 #define IP4_HLEN	(sizeof(struct iphdr))
 #define IP6_HLEN	(sizeof(struct ip6_hdr))
 #define UDP_HLEN	(sizeof(struct udphdr))
 
-static int msg_len;
+/* IPv6 fragment header lenth. */
+#define FRAG_HLEN	8
+
+static int payload_len;
 static int max_frag_len;
 
 #define MSG_LEN_MAX	60000	/* Max UDP payload length. */
 
 #define IP4_MF		(1u << 13)  /* IPv4 MF flag. */
+#define IP6_MF		(1)  /* IPv6 MF flag. */
+
+#define CSUM_MANGLED_0 (0xffff)
 
 static uint8_t udp_payload[MSG_LEN_MAX];
 static uint8_t ip_frame[IP_MAXPACKET];
-static uint16_t ip_id = 0xabcd;
+static uint32_t ip_id = 0xabcd;
 static int msg_counter;
 static int frag_counter;
 static unsigned int seed;
@@ -48,25 +55,25 @@ static void recv_validate_udp(int fd_udp)
 	ssize_t ret;
 	static uint8_t recv_buff[MSG_LEN_MAX];
 
-	ret = recv(fd_udp, recv_buff, msg_len, 0);
+	ret = recv(fd_udp, recv_buff, payload_len, 0);
 	msg_counter++;
 
 	if (cfg_overlap) {
 		if (ret != -1)
-			error(1, 0, "recv: expected timeout; got %d; seed = %u",
-				(int)ret, seed);
+			error(1, 0, "recv: expected timeout; got %d",
+				(int)ret);
 		if (errno != ETIMEDOUT && errno != EAGAIN)
-			error(1, errno, "recv: expected timeout: %d; seed = %u",
-				 errno, seed);
+			error(1, errno, "recv: expected timeout: %d",
+				 errno);
 		return;  /* OK */
 	}
 
 	if (ret == -1)
-		error(1, errno, "recv: msg_len = %d max_frag_len = %d",
-			msg_len, max_frag_len);
-	if (ret != msg_len)
-		error(1, 0, "recv: wrong size: %d vs %d", (int)ret, msg_len);
-	if (memcmp(udp_payload, recv_buff, msg_len))
+		error(1, errno, "recv: payload_len = %d max_frag_len = %d",
+			payload_len, max_frag_len);
+	if (ret != payload_len)
+		error(1, 0, "recv: wrong size: %d vs %d", (int)ret, payload_len);
+	if (memcmp(udp_payload, recv_buff, payload_len))
 		error(1, 0, "recv: wrong data");
 }
 
@@ -92,31 +99,95 @@ static uint32_t raw_checksum(uint8_t *buf, int len, uint32_t sum)
 static uint16_t udp_checksum(struct ip *iphdr, struct udphdr *udphdr)
 {
 	uint32_t sum = 0;
+	uint16_t res;
 
 	sum = raw_checksum((uint8_t *)&iphdr->ip_src, 2 * sizeof(iphdr->ip_src),
-				IPPROTO_UDP + (uint32_t)(UDP_HLEN + msg_len));
-	sum = raw_checksum((uint8_t *)udp_payload, msg_len, sum);
+				IPPROTO_UDP + (uint32_t)(UDP_HLEN + payload_len));
+	sum = raw_checksum((uint8_t *)udphdr, UDP_HLEN, sum);
+	sum = raw_checksum((uint8_t *)udp_payload, payload_len, sum);
+	res = 0xffff & ~sum;
+	if (res)
+		return htons(res);
+	else
+		return CSUM_MANGLED_0;
+}
+
+static uint16_t udp6_checksum(struct ip6_hdr *iphdr, struct udphdr *udphdr)
+{
+	uint32_t sum = 0;
+	uint16_t res;
+
+	sum = raw_checksum((uint8_t *)&iphdr->ip6_src, 2 * sizeof(iphdr->ip6_src),
+				IPPROTO_UDP);
+	sum = raw_checksum((uint8_t *)&udphdr->len, sizeof(udphdr->len), sum);
 	sum = raw_checksum((uint8_t *)udphdr, UDP_HLEN, sum);
-	return htons(0xffff & ~sum);
+	sum = raw_checksum((uint8_t *)udp_payload, payload_len, sum);
+	res = 0xffff & ~sum;
+	if (res)
+		return htons(res);
+	else
+		return CSUM_MANGLED_0;
 }
 
 static void send_fragment(int fd_raw, struct sockaddr *addr, socklen_t alen,
-				struct ip *iphdr, int offset)
+				int offset, bool ipv6)
 {
 	int frag_len;
 	int res;
+	int payload_offset = offset > 0 ? offset - UDP_HLEN : 0;
+	uint8_t *frag_start = ipv6 ? ip_frame + IP6_HLEN + FRAG_HLEN :
+					ip_frame + IP4_HLEN;
+
+	if (offset == 0) {
+		struct udphdr udphdr;
+		udphdr.source = htons(cfg_port + 1);
+		udphdr.dest = htons(cfg_port);
+		udphdr.len = htons(UDP_HLEN + payload_len);
+		udphdr.check = 0;
+		if (ipv6)
+			udphdr.check = udp6_checksum((struct ip6_hdr *)ip_frame, &udphdr);
+		else
+			udphdr.check = udp_checksum((struct ip *)ip_frame, &udphdr);
+		memcpy(frag_start, &udphdr, UDP_HLEN);
+	}
 
-	if (msg_len - offset <= max_frag_len) {
-		/* This is the last fragment. */
-		frag_len = IP4_HLEN + msg_len - offset;
-		iphdr->ip_off = htons((offset + UDP_HLEN) / 8);
+	if (ipv6) {
+		struct ip6_hdr *ip6hdr = (struct ip6_hdr *)ip_frame;
+		struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN);
+		if (payload_len - payload_offset <= max_frag_len && offset > 0) {
+			/* This is the last fragment. */
+			frag_len = FRAG_HLEN + payload_len - payload_offset;
+			fraghdr->ip6f_offlg = htons(offset);
+		} else {
+			frag_len = FRAG_HLEN + max_frag_len;
+			fraghdr->ip6f_offlg = htons(offset | IP6_MF);
+		}
+		ip6hdr->ip6_plen = htons(frag_len);
+		if (offset == 0)
+			memcpy(frag_start + UDP_HLEN, udp_payload,
+				frag_len - FRAG_HLEN - UDP_HLEN);
+		else
+			memcpy(frag_start, udp_payload + payload_offset,
+				frag_len - FRAG_HLEN);
+		frag_len += IP6_HLEN;
 	} else {
-		frag_len = IP4_HLEN + max_frag_len;
-		iphdr->ip_off = htons((offset + UDP_HLEN) / 8 | IP4_MF);
+		struct ip *iphdr = (struct ip *)ip_frame;
+		if (payload_len - payload_offset <= max_frag_len && offset > 0) {
+			/* This is the last fragment. */
+			frag_len = IP4_HLEN + payload_len - payload_offset;
+			iphdr->ip_off = htons(offset / 8);
+		} else {
+			frag_len = IP4_HLEN + max_frag_len;
+			iphdr->ip_off = htons(offset / 8 | IP4_MF);
+		}
+		iphdr->ip_len = htons(frag_len);
+		if (offset == 0)
+			memcpy(frag_start + UDP_HLEN, udp_payload,
+				frag_len - IP4_HLEN - UDP_HLEN);
+		else
+			memcpy(frag_start, udp_payload + payload_offset,
+				frag_len - IP4_HLEN);
 	}
-	iphdr->ip_len = htons(frag_len);
-	memcpy(ip_frame + IP4_HLEN, udp_payload + offset,
-		 frag_len - IP4_HLEN);
 
 	res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen);
 	if (res < 0)
@@ -127,9 +198,11 @@ static void send_fragment(int fd_raw, struct sockaddr *addr, socklen_t alen,
 	frag_counter++;
 }
 
-static void send_udp_frags_v4(int fd_raw, struct sockaddr *addr, socklen_t alen)
+static void send_udp_frags(int fd_raw, struct sockaddr *addr,
+				socklen_t alen, bool ipv6)
 {
 	struct ip *iphdr = (struct ip *)ip_frame;
+	struct ip6_hdr *ip6hdr = (struct ip6_hdr *)ip_frame;
 	struct udphdr udphdr;
 	int res;
 	int offset;
@@ -142,31 +215,55 @@ static void send_udp_frags_v4(int fd_raw, struct sockaddr *addr, socklen_t alen)
 	 * Odd fragments (1st, 3rd, 5th, etc.) are sent out first, then
 	 * even fragments (0th, 2nd, etc.) are sent out.
 	 */
-	memset(iphdr, 0, sizeof(*iphdr));
-	iphdr->ip_hl = 5;
-	iphdr->ip_v = 4;
-	iphdr->ip_tos = 0;
-	iphdr->ip_id = htons(ip_id++);
-	iphdr->ip_ttl = 0x40;
-	iphdr->ip_p = IPPROTO_UDP;
-	iphdr->ip_src.s_addr = htonl(INADDR_LOOPBACK);
-	iphdr->ip_dst = addr4;
-	iphdr->ip_sum = 0;
+	if (ipv6) {
+		struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN);
+		((struct sockaddr_in6 *)addr)->sin6_port = 0;
+		memset(ip6hdr, 0, sizeof(*ip6hdr));
+		ip6hdr->ip6_flow = htonl(6<<28);  /* Version. */
+		ip6hdr->ip6_nxt = IPPROTO_FRAGMENT;
+		ip6hdr->ip6_hops = 255;
+		ip6hdr->ip6_src = addr6;
+		ip6hdr->ip6_dst = addr6;
+		fraghdr->ip6f_nxt = IPPROTO_UDP;
+		fraghdr->ip6f_reserved = 0;
+		fraghdr->ip6f_ident = htonl(ip_id++);
+	} else {
+		memset(iphdr, 0, sizeof(*iphdr));
+		iphdr->ip_hl = 5;
+		iphdr->ip_v = 4;
+		iphdr->ip_tos = 0;
+		iphdr->ip_id = htons(ip_id++);
+		iphdr->ip_ttl = 0x40;
+		iphdr->ip_p = IPPROTO_UDP;
+		iphdr->ip_src.s_addr = htonl(INADDR_LOOPBACK);
+		iphdr->ip_dst = addr4;
+		iphdr->ip_sum = 0;
+	}
 
 	/* Odd fragments. */
-	offset = 0;
-	while (offset < msg_len) {
-		send_fragment(fd_raw, addr, alen, iphdr, offset);
+	offset = max_frag_len;
+	while (offset < (UDP_HLEN + payload_len)) {
+		send_fragment(fd_raw, addr, alen, offset, ipv6);
 		offset += 2 * max_frag_len;
 	}
 
 	if (cfg_overlap) {
 		/* Send an extra random fragment. */
-		offset = rand() % (UDP_HLEN + msg_len - 1);
+		offset = rand() % (UDP_HLEN + payload_len - 1);
 		/* sendto() returns EINVAL if offset + frag_len is too small. */
-		frag_len = IP4_HLEN + UDP_HLEN + rand() % 256;
-		iphdr->ip_off = htons(offset / 8 | IP4_MF);
-		iphdr->ip_len = htons(frag_len);
+		if (ipv6) {
+			struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN);
+			frag_len = max_frag_len + rand() % 256;
+			/* In IPv6 if !!(frag_len % 8), the fragment is dropped. */
+			frag_len &= ~0x7;
+			fraghdr->ip6f_offlg = htons(offset / 8 | IP6_MF);
+			ip6hdr->ip6_plen = htons(frag_len);
+			frag_len += IP6_HLEN;
+		} else {
+			frag_len = IP4_HLEN + UDP_HLEN + rand() % 256;
+			iphdr->ip_off = htons(offset / 8 | IP4_MF);
+			iphdr->ip_len = htons(frag_len);
+		}
 		res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen);
 		if (res < 0)
 			error(1, errno, "sendto overlap");
@@ -175,48 +272,26 @@ static void send_udp_frags_v4(int fd_raw, struct sockaddr *addr, socklen_t alen)
 		frag_counter++;
 	}
 
-	/* Zeroth fragment (UDP header). */
-	frag_len = IP4_HLEN + UDP_HLEN;
-	iphdr->ip_len = htons(frag_len);
-	iphdr->ip_off = htons(IP4_MF);
-
-	udphdr.source = htons(cfg_port + 1);
-	udphdr.dest = htons(cfg_port);
-	udphdr.len = htons(UDP_HLEN + msg_len);
-	udphdr.check = 0;
-	udphdr.check = udp_checksum(iphdr, &udphdr);
-
-	memcpy(ip_frame + IP4_HLEN, &udphdr, UDP_HLEN);
-	res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen);
-	if (res < 0)
-		error(1, errno, "sendto UDP header");
-	if (res != frag_len)
-		error(1, 0, "sendto UDP header: %d vs %d", (int)res, frag_len);
-	frag_counter++;
-
-	/* Even fragments. */
-	offset = max_frag_len;
-	while (offset < msg_len) {
-		send_fragment(fd_raw, addr, alen, iphdr, offset);
+	/* Event fragments. */
+	offset = 0;
+	while (offset < (UDP_HLEN + payload_len)) {
+		send_fragment(fd_raw, addr, alen, offset, ipv6);
 		offset += 2 * max_frag_len;
 	}
 }
 
-static void run_test(struct sockaddr *addr, socklen_t alen)
+static void run_test(struct sockaddr *addr, socklen_t alen, bool ipv6)
 {
-	int fd_tx_udp, fd_tx_raw, fd_rx_udp;
+	int fd_tx_raw, fd_rx_udp;
 	struct timeval tv = { .tv_sec = 0, .tv_usec = 10 * 1000 };
 	int idx;
+	int min_frag_len = ipv6 ? 1280 : 8;
 
 	/* Initialize the payload. */
 	for (idx = 0; idx < MSG_LEN_MAX; ++idx)
 		udp_payload[idx] = idx % 256;
 
 	/* Open sockets. */
-	fd_tx_udp = socket(addr->sa_family, SOCK_DGRAM, 0);
-	if (fd_tx_udp == -1)
-		error(1, errno, "socket tx_udp");
-
 	fd_tx_raw = socket(addr->sa_family, SOCK_RAW, IPPROTO_RAW);
 	if (fd_tx_raw == -1)
 		error(1, errno, "socket tx_raw");
@@ -230,22 +305,21 @@ static void run_test(struct sockaddr *addr, socklen_t alen)
 	if (setsockopt(fd_rx_udp, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
 		error(1, errno, "setsockopt rcv timeout");
 
-	for (msg_len = 1; msg_len < MSG_LEN_MAX; msg_len += (rand() % 4096)) {
+	for (payload_len = min_frag_len; payload_len < MSG_LEN_MAX;
+			payload_len += (rand() % 4096)) {
 		if (cfg_verbose)
-			printf("msg_len: %d\n", msg_len);
-		max_frag_len = addr->sa_family == AF_INET ? 8 : 1280;
-		for (; max_frag_len < 1500 && max_frag_len <= msg_len;
-				max_frag_len += 8) {
-			send_udp_frags_v4(fd_tx_raw, addr, alen);
+			printf("payload_len: %d\n", payload_len);
+		max_frag_len = min_frag_len;
+		do {
+			send_udp_frags(fd_tx_raw, addr, alen, ipv6);
 			recv_validate_udp(fd_rx_udp);
-		}
+			max_frag_len += 8 * (rand() % 8);
+		} while (max_frag_len < (1500 - FRAG_HLEN) && max_frag_len <= payload_len);
 	}
 
 	/* Cleanup. */
 	if (close(fd_tx_raw))
 		error(1, errno, "close tx_raw");
-	if (close(fd_tx_udp))
-		error(1, errno, "close tx_udp");
 	if (close(fd_rx_udp))
 		error(1, errno, "close rx_udp");
 
@@ -265,13 +339,18 @@ static void run_test_v4(void)
 	addr.sin_port = htons(cfg_port);
 	addr.sin_addr = addr4;
 
-	run_test((void *)&addr, sizeof(addr));
+	run_test((void *)&addr, sizeof(addr), false /* !ipv6 */);
 }
 
 static void run_test_v6(void)
 {
-	fprintf(stderr, "NOT IMPL.\n");
-	exit(1);
+	struct sockaddr_in6 addr = {0};
+
+	addr.sin6_family = AF_INET6;
+	addr.sin6_port = htons(cfg_port);
+	addr.sin6_addr = addr6;
+
+	run_test((void *)&addr, sizeof(addr), true /* ipv6 */);
 }
 
 static void parse_opts(int argc, char **argv)
@@ -303,6 +382,8 @@ int main(int argc, char **argv)
 	parse_opts(argc, argv);
 	seed = time(NULL);
 	srand(seed);
+	/* Print the seed to track/reproduce potential failures. */
+	printf("seed = %d\n", seed);
 
 	if (cfg_do_ipv4)
 		run_test_v4();
diff --git a/tools/testing/selftests/net/ip_defrag.sh b/tools/testing/selftests/net/ip_defrag.sh
index 78743adcca9e..3a4042d918f0 100755
--- a/tools/testing/selftests/net/ip_defrag.sh
+++ b/tools/testing/selftests/net/ip_defrag.sh
@@ -6,23 +6,34 @@
 set +x
 set -e
 
-echo "ipv4 defrag"
+readonly NETNS="ns-$(mktemp -u XXXXXX)"
+
+setup() {
+	ip netns add "${NETNS}"
+	ip -netns "${NETNS}" link set lo up
+	ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null
+	ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null
+	ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_high_thresh=9000000 &> /dev/null
+	ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_low_thresh=7000000 &> /dev/null
+}
 
-run_v4() {
-sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null
-sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null
-./ip_defrag -4
+cleanup() {
+	ip netns del "${NETNS}"
 }
-export -f run_v4
 
-./in_netns.sh "run_v4"
+trap cleanup EXIT
+setup
+
+echo "ipv4 defrag"
+ip netns exec "${NETNS}" ./ip_defrag -4
+
 
 echo "ipv4 defrag with overlaps"
-run_v4o() {
-sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null
-sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null
-./ip_defrag -4o
-}
-export -f run_v4o
+ip netns exec "${NETNS}" ./ip_defrag -4o
+
+echo "ipv6 defrag"
+ip netns exec "${NETNS}" ./ip_defrag -6
+
+echo "ipv6 defrag with overlaps"
+ip netns exec "${NETNS}" ./ip_defrag -6o
 
-./in_netns.sh "run_v4o"
-- 
cgit 


From ce01a1575f45bf319e374592656441021a7f5823 Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Date: Thu, 27 Sep 2018 14:39:19 -0400
Subject: rseq/selftests: fix parametrized test with -fpie

On x86-64, the parametrized selftest code for rseq crashes with a
segmentation fault when compiled with -fpie. This happens when the
param_test binary is loaded at an address beyond 32-bit on x86-64.

The issue is caused by use of a 32-bit register to hold the address
of the loop counter variable.

Fix this by using a 64-bit register to calculate the address of the
loop counter variables as an offset from rip.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: <stable@vger.kernel.org> # v4.18
Cc: Shuah Khan <shuah@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: linux-kselftest@vger.kernel.org
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/rseq/param_test.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index 642d4e12abea..eec2663261f2 100644
--- a/tools/testing/selftests/rseq/param_test.c
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -56,15 +56,13 @@ unsigned int yield_mod_cnt, nr_abort;
 			printf(fmt, ## __VA_ARGS__);	\
 	} while (0)
 
-#if defined(__x86_64__) || defined(__i386__)
+#ifdef __i386__
 
 #define INJECT_ASM_REG	"eax"
 
 #define RSEQ_INJECT_CLOBBER \
 	, INJECT_ASM_REG
 
-#ifdef __i386__
-
 #define RSEQ_INJECT_ASM(n) \
 	"mov asm_loop_cnt_" #n ", %%" INJECT_ASM_REG "\n\t" \
 	"test %%" INJECT_ASM_REG ",%%" INJECT_ASM_REG "\n\t" \
@@ -76,9 +74,16 @@ unsigned int yield_mod_cnt, nr_abort;
 
 #elif defined(__x86_64__)
 
+#define INJECT_ASM_REG_P	"rax"
+#define INJECT_ASM_REG		"eax"
+
+#define RSEQ_INJECT_CLOBBER \
+	, INJECT_ASM_REG_P \
+	, INJECT_ASM_REG
+
 #define RSEQ_INJECT_ASM(n) \
-	"lea asm_loop_cnt_" #n "(%%rip), %%" INJECT_ASM_REG "\n\t" \
-	"mov (%%" INJECT_ASM_REG "), %%" INJECT_ASM_REG "\n\t" \
+	"lea asm_loop_cnt_" #n "(%%rip), %%" INJECT_ASM_REG_P "\n\t" \
+	"mov (%%" INJECT_ASM_REG_P "), %%" INJECT_ASM_REG "\n\t" \
 	"test %%" INJECT_ASM_REG ",%%" INJECT_ASM_REG "\n\t" \
 	"jz 333f\n\t" \
 	"222:\n\t" \
@@ -86,10 +91,6 @@ unsigned int yield_mod_cnt, nr_abort;
 	"jnz 222b\n\t" \
 	"333:\n\t"
 
-#else
-#error "Unsupported architecture"
-#endif
-
 #elif defined(__s390__)
 
 #define RSEQ_INJECT_INPUT \
-- 
cgit 


From c9bf507d0acba950e5d85ef27727ce61458ef5aa Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 26 Sep 2018 15:24:56 -0700
Subject: selftests/bpf: Use libbpf_attach_type_by_name in test_socket_cookie

Use newly introduced libbpf_attach_type_by_name in test_socket_cookie
selftest.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_socket_cookie.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_socket_cookie.c b/tools/testing/selftests/bpf/test_socket_cookie.c
index 68e108e4687a..b6c2c605d8c0 100644
--- a/tools/testing/selftests/bpf/test_socket_cookie.c
+++ b/tools/testing/selftests/bpf/test_socket_cookie.c
@@ -158,11 +158,7 @@ static int run_test(int cgfd)
 	bpf_object__for_each_program(prog, pobj) {
 		prog_name = bpf_program__title(prog, /*needs_copy*/ false);
 
-		if (strcmp(prog_name, "cgroup/connect6") == 0) {
-			attach_type = BPF_CGROUP_INET6_CONNECT;
-		} else if (strcmp(prog_name, "sockops") == 0) {
-			attach_type = BPF_CGROUP_SOCK_OPS;
-		} else {
+		if (libbpf_attach_type_by_name(prog_name, &attach_type)) {
 			log_err("Unexpected prog: %s", prog_name);
 			goto err;
 		}
-- 
cgit 


From 370920c47b26ae3a837f7c46f0795804ae2940f7 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 26 Sep 2018 15:24:57 -0700
Subject: selftests/bpf: Test libbpf_{prog,attach}_type_by_name

Add selftest for libbpf functions libbpf_prog_type_by_name and
libbpf_attach_type_by_name.

Example of output:
  % ./tools/testing/selftests/bpf/test_section_names
  Summary: 35 PASSED, 0 FAILED

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/Makefile             |   2 +-
 tools/testing/selftests/bpf/test_section_names.c | 208 +++++++++++++++++++++++
 2 files changed, 209 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/test_section_names.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index fd3851d5c079..059d64a0f897 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -23,7 +23,7 @@ $(TEST_CUSTOM_PROGS): $(OUTPUT)/%: %.c
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
 	test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
 	test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \
-	test_socket_cookie test_cgroup_storage test_select_reuseport
+	test_socket_cookie test_cgroup_storage test_select_reuseport test_section_names
 
 TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
 	test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o     \
diff --git a/tools/testing/selftests/bpf/test_section_names.c b/tools/testing/selftests/bpf/test_section_names.c
new file mode 100644
index 000000000000..7c4f41572b1c
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_section_names.c
@@ -0,0 +1,208 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <err.h>
+#include <bpf/libbpf.h>
+
+#include "bpf_util.h"
+
+struct sec_name_test {
+	const char sec_name[32];
+	struct {
+		int rc;
+		enum bpf_prog_type prog_type;
+		enum bpf_attach_type expected_attach_type;
+	} expected_load;
+	struct {
+		int rc;
+		enum bpf_attach_type attach_type;
+	} expected_attach;
+};
+
+static struct sec_name_test tests[] = {
+	{"InvAliD", {-EINVAL, 0, 0}, {-EINVAL, 0} },
+	{"cgroup", {-EINVAL, 0, 0}, {-EINVAL, 0} },
+	{"socket", {0, BPF_PROG_TYPE_SOCKET_FILTER, 0}, {-EINVAL, 0} },
+	{"kprobe/", {0, BPF_PROG_TYPE_KPROBE, 0}, {-EINVAL, 0} },
+	{"kretprobe/", {0, BPF_PROG_TYPE_KPROBE, 0}, {-EINVAL, 0} },
+	{"classifier", {0, BPF_PROG_TYPE_SCHED_CLS, 0}, {-EINVAL, 0} },
+	{"action", {0, BPF_PROG_TYPE_SCHED_ACT, 0}, {-EINVAL, 0} },
+	{"tracepoint/", {0, BPF_PROG_TYPE_TRACEPOINT, 0}, {-EINVAL, 0} },
+	{
+		"raw_tracepoint/",
+		{0, BPF_PROG_TYPE_RAW_TRACEPOINT, 0},
+		{-EINVAL, 0},
+	},
+	{"xdp", {0, BPF_PROG_TYPE_XDP, 0}, {-EINVAL, 0} },
+	{"perf_event", {0, BPF_PROG_TYPE_PERF_EVENT, 0}, {-EINVAL, 0} },
+	{"lwt_in", {0, BPF_PROG_TYPE_LWT_IN, 0}, {-EINVAL, 0} },
+	{"lwt_out", {0, BPF_PROG_TYPE_LWT_OUT, 0}, {-EINVAL, 0} },
+	{"lwt_xmit", {0, BPF_PROG_TYPE_LWT_XMIT, 0}, {-EINVAL, 0} },
+	{"lwt_seg6local", {0, BPF_PROG_TYPE_LWT_SEG6LOCAL, 0}, {-EINVAL, 0} },
+	{
+		"cgroup_skb/ingress",
+		{0, BPF_PROG_TYPE_CGROUP_SKB, 0},
+		{0, BPF_CGROUP_INET_INGRESS},
+	},
+	{
+		"cgroup_skb/egress",
+		{0, BPF_PROG_TYPE_CGROUP_SKB, 0},
+		{0, BPF_CGROUP_INET_EGRESS},
+	},
+	{"cgroup/skb", {0, BPF_PROG_TYPE_CGROUP_SKB, 0}, {-EINVAL, 0} },
+	{
+		"cgroup/sock",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK, 0},
+		{0, BPF_CGROUP_INET_SOCK_CREATE},
+	},
+	{
+		"cgroup/post_bind4",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK, BPF_CGROUP_INET4_POST_BIND},
+		{0, BPF_CGROUP_INET4_POST_BIND},
+	},
+	{
+		"cgroup/post_bind6",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK, BPF_CGROUP_INET6_POST_BIND},
+		{0, BPF_CGROUP_INET6_POST_BIND},
+	},
+	{
+		"cgroup/dev",
+		{0, BPF_PROG_TYPE_CGROUP_DEVICE, 0},
+		{0, BPF_CGROUP_DEVICE},
+	},
+	{"sockops", {0, BPF_PROG_TYPE_SOCK_OPS, 0}, {0, BPF_CGROUP_SOCK_OPS} },
+	{
+		"sk_skb/stream_parser",
+		{0, BPF_PROG_TYPE_SK_SKB, 0},
+		{0, BPF_SK_SKB_STREAM_PARSER},
+	},
+	{
+		"sk_skb/stream_verdict",
+		{0, BPF_PROG_TYPE_SK_SKB, 0},
+		{0, BPF_SK_SKB_STREAM_VERDICT},
+	},
+	{"sk_skb", {0, BPF_PROG_TYPE_SK_SKB, 0}, {-EINVAL, 0} },
+	{"sk_msg", {0, BPF_PROG_TYPE_SK_MSG, 0}, {0, BPF_SK_MSG_VERDICT} },
+	{"lirc_mode2", {0, BPF_PROG_TYPE_LIRC_MODE2, 0}, {0, BPF_LIRC_MODE2} },
+	{
+		"flow_dissector",
+		{0, BPF_PROG_TYPE_FLOW_DISSECTOR, 0},
+		{0, BPF_FLOW_DISSECTOR},
+	},
+	{
+		"cgroup/bind4",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_BIND},
+		{0, BPF_CGROUP_INET4_BIND},
+	},
+	{
+		"cgroup/bind6",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_BIND},
+		{0, BPF_CGROUP_INET6_BIND},
+	},
+	{
+		"cgroup/connect4",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_CONNECT},
+		{0, BPF_CGROUP_INET4_CONNECT},
+	},
+	{
+		"cgroup/connect6",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT},
+		{0, BPF_CGROUP_INET6_CONNECT},
+	},
+	{
+		"cgroup/sendmsg4",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG},
+		{0, BPF_CGROUP_UDP4_SENDMSG},
+	},
+	{
+		"cgroup/sendmsg6",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG},
+		{0, BPF_CGROUP_UDP6_SENDMSG},
+	},
+};
+
+static int test_prog_type_by_name(const struct sec_name_test *test)
+{
+	enum bpf_attach_type expected_attach_type;
+	enum bpf_prog_type prog_type;
+	int rc;
+
+	rc = libbpf_prog_type_by_name(test->sec_name, &prog_type,
+				      &expected_attach_type);
+
+	if (rc != test->expected_load.rc) {
+		warnx("prog: unexpected rc=%d for %s", rc, test->sec_name);
+		return -1;
+	}
+
+	if (rc)
+		return 0;
+
+	if (prog_type != test->expected_load.prog_type) {
+		warnx("prog: unexpected prog_type=%d for %s", prog_type,
+		      test->sec_name);
+		return -1;
+	}
+
+	if (expected_attach_type != test->expected_load.expected_attach_type) {
+		warnx("prog: unexpected expected_attach_type=%d for %s",
+		      expected_attach_type, test->sec_name);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int test_attach_type_by_name(const struct sec_name_test *test)
+{
+	enum bpf_attach_type attach_type;
+	int rc;
+
+	rc = libbpf_attach_type_by_name(test->sec_name, &attach_type);
+
+	if (rc != test->expected_attach.rc) {
+		warnx("attach: unexpected rc=%d for %s", rc, test->sec_name);
+		return -1;
+	}
+
+	if (rc)
+		return 0;
+
+	if (attach_type != test->expected_attach.attach_type) {
+		warnx("attach: unexpected attach_type=%d for %s", attach_type,
+		      test->sec_name);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int run_test_case(const struct sec_name_test *test)
+{
+	if (test_prog_type_by_name(test))
+		return -1;
+	if (test_attach_type_by_name(test))
+		return -1;
+	return 0;
+}
+
+static int run_tests(void)
+{
+	int passes = 0;
+	int fails = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(tests); ++i) {
+		if (run_test_case(&tests[i]))
+			++fails;
+		else
+			++passes;
+	}
+	printf("Summary: %d PASSED, %d FAILED\n", passes, fails);
+	return fails ? -1 : 0;
+}
+
+int main(int argc, char **argv)
+{
+	return run_tests();
+}
-- 
cgit 


From 7e0cf1c983b5b24426d130fd949a055d520acc9a Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Fri, 28 Sep 2018 14:53:18 +1000
Subject: selftests/powerpc: Fix Makefiles for headers_install change

Commit b2d35fa5fc80 ("selftests: add headers_install to lib.mk")
introduced a requirement that Makefiles more than one level below the
selftests directory need to define top_srcdir, but it didn't update
any of the powerpc Makefiles.

This broke building all the powerpc selftests with eg:

  make[1]: Entering directory '/src/linux/tools/testing/selftests/powerpc'
  BUILD_TARGET=/src/linux/tools/testing/selftests/powerpc/alignment; mkdir -p $BUILD_TARGET; make OUTPUT=$BUILD_TARGET -k -C alignment all
  make[2]: Entering directory '/src/linux/tools/testing/selftests/powerpc/alignment'
  ../../lib.mk:20: ../../../../scripts/subarch.include: No such file or directory
  make[2]: *** No rule to make target '../../../../scripts/subarch.include'.
  make[2]: Failed to remake makefile '../../../../scripts/subarch.include'.
  Makefile:38: recipe for target 'alignment' failed

Fix it by setting top_srcdir in the affected Makefiles.

Fixes: b2d35fa5fc80 ("selftests: add headers_install to lib.mk")
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/alignment/Makefile     | 1 +
 tools/testing/selftests/powerpc/benchmarks/Makefile    | 1 +
 tools/testing/selftests/powerpc/cache_shape/Makefile   | 1 +
 tools/testing/selftests/powerpc/copyloops/Makefile     | 1 +
 tools/testing/selftests/powerpc/dscr/Makefile          | 1 +
 tools/testing/selftests/powerpc/math/Makefile          | 1 +
 tools/testing/selftests/powerpc/mm/Makefile            | 1 +
 tools/testing/selftests/powerpc/pmu/Makefile           | 1 +
 tools/testing/selftests/powerpc/pmu/ebb/Makefile       | 1 +
 tools/testing/selftests/powerpc/primitives/Makefile    | 1 +
 tools/testing/selftests/powerpc/ptrace/Makefile        | 1 +
 tools/testing/selftests/powerpc/signal/Makefile        | 1 +
 tools/testing/selftests/powerpc/stringloops/Makefile   | 1 +
 tools/testing/selftests/powerpc/switch_endian/Makefile | 1 +
 tools/testing/selftests/powerpc/syscalls/Makefile      | 1 +
 tools/testing/selftests/powerpc/tm/Makefile            | 1 +
 tools/testing/selftests/powerpc/vphn/Makefile          | 1 +
 17 files changed, 17 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/powerpc/alignment/Makefile b/tools/testing/selftests/powerpc/alignment/Makefile
index 93baacab7693..d056486f49de 100644
--- a/tools/testing/selftests/powerpc/alignment/Makefile
+++ b/tools/testing/selftests/powerpc/alignment/Makefile
@@ -1,5 +1,6 @@
 TEST_GEN_PROGS := copy_first_unaligned alignment_handler
 
+top_srcdir = ../../../../..
 include ../../lib.mk
 
 $(TEST_GEN_PROGS): ../harness.c ../utils.c
diff --git a/tools/testing/selftests/powerpc/benchmarks/Makefile b/tools/testing/selftests/powerpc/benchmarks/Makefile
index b4d7432a0ecd..d40300a65b42 100644
--- a/tools/testing/selftests/powerpc/benchmarks/Makefile
+++ b/tools/testing/selftests/powerpc/benchmarks/Makefile
@@ -4,6 +4,7 @@ TEST_GEN_FILES := exec_target
 
 CFLAGS += -O2
 
+top_srcdir = ../../../../..
 include ../../lib.mk
 
 $(TEST_GEN_PROGS): ../harness.c
diff --git a/tools/testing/selftests/powerpc/cache_shape/Makefile b/tools/testing/selftests/powerpc/cache_shape/Makefile
index 1be547434a49..ede4d3dae750 100644
--- a/tools/testing/selftests/powerpc/cache_shape/Makefile
+++ b/tools/testing/selftests/powerpc/cache_shape/Makefile
@@ -5,6 +5,7 @@ all: $(TEST_PROGS)
 
 $(TEST_PROGS): ../harness.c ../utils.c
 
+top_srcdir = ../../../../..
 include ../../lib.mk
 
 clean:
diff --git a/tools/testing/selftests/powerpc/copyloops/Makefile b/tools/testing/selftests/powerpc/copyloops/Makefile
index 1cf89a34d97c..44574f3818b3 100644
--- a/tools/testing/selftests/powerpc/copyloops/Makefile
+++ b/tools/testing/selftests/powerpc/copyloops/Makefile
@@ -17,6 +17,7 @@ TEST_GEN_PROGS := copyuser_64_t0 copyuser_64_t1 copyuser_64_t2 \
 
 EXTRA_SOURCES := validate.c ../harness.c stubs.S
 
+top_srcdir = ../../../../..
 include ../../lib.mk
 
 $(OUTPUT)/copyuser_64_t%:	copyuser_64.S $(EXTRA_SOURCES)
diff --git a/tools/testing/selftests/powerpc/dscr/Makefile b/tools/testing/selftests/powerpc/dscr/Makefile
index 55d7db7a616b..5df476364b4d 100644
--- a/tools/testing/selftests/powerpc/dscr/Makefile
+++ b/tools/testing/selftests/powerpc/dscr/Makefile
@@ -3,6 +3,7 @@ TEST_GEN_PROGS := dscr_default_test dscr_explicit_test dscr_user_test	\
 	      dscr_inherit_test dscr_inherit_exec_test dscr_sysfs_test	\
 	      dscr_sysfs_thread_test
 
+top_srcdir = ../../../../..
 include ../../lib.mk
 
 $(OUTPUT)/dscr_default_test: LDLIBS += -lpthread
diff --git a/tools/testing/selftests/powerpc/math/Makefile b/tools/testing/selftests/powerpc/math/Makefile
index 0dd3a01fdab9..11a10d7a2bbd 100644
--- a/tools/testing/selftests/powerpc/math/Makefile
+++ b/tools/testing/selftests/powerpc/math/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 TEST_GEN_PROGS := fpu_syscall fpu_preempt fpu_signal vmx_syscall vmx_preempt vmx_signal vsx_preempt
 
+top_srcdir = ../../../../..
 include ../../lib.mk
 
 $(TEST_GEN_PROGS): ../harness.c
diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile
index 8ebbe96d80a8..33ced6e0ad25 100644
--- a/tools/testing/selftests/powerpc/mm/Makefile
+++ b/tools/testing/selftests/powerpc/mm/Makefile
@@ -5,6 +5,7 @@ noarg:
 TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors
 TEST_GEN_FILES := tempfile
 
+top_srcdir = ../../../../..
 include ../../lib.mk
 
 $(TEST_GEN_PROGS): ../harness.c
diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile
index 6e1629bf5b09..19046db995fe 100644
--- a/tools/testing/selftests/powerpc/pmu/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/Makefile
@@ -5,6 +5,7 @@ noarg:
 TEST_GEN_PROGS := count_instructions l3_bank_test per_event_excludes
 EXTRA_SOURCES := ../harness.c event.c lib.c ../utils.c
 
+top_srcdir = ../../../../..
 include ../../lib.mk
 
 all: $(TEST_GEN_PROGS) ebb
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
index c4e64bc2e265..bd5dfa509272 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
@@ -17,6 +17,7 @@ TEST_GEN_PROGS := reg_access_test event_attributes_test cycles_test	\
 	 lost_exception_test no_handler_test			\
 	 cycles_with_mmcr2_test
 
+top_srcdir = ../../../../../..
 include ../../../lib.mk
 
 $(TEST_GEN_PROGS): ../../harness.c ../../utils.c ../event.c ../lib.c \
diff --git a/tools/testing/selftests/powerpc/primitives/Makefile b/tools/testing/selftests/powerpc/primitives/Makefile
index 175366db7be8..ea2b7bd09e36 100644
--- a/tools/testing/selftests/powerpc/primitives/Makefile
+++ b/tools/testing/selftests/powerpc/primitives/Makefile
@@ -2,6 +2,7 @@ CFLAGS += -I$(CURDIR)
 
 TEST_GEN_PROGS := load_unaligned_zeropad
 
+top_srcdir = ../../../../..
 include ../../lib.mk
 
 $(TEST_GEN_PROGS): ../harness.c
diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile
index 28f5b781a553..923d531265f8 100644
--- a/tools/testing/selftests/powerpc/ptrace/Makefile
+++ b/tools/testing/selftests/powerpc/ptrace/Makefile
@@ -4,6 +4,7 @@ TEST_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \
               ptrace-tm-spd-vsx ptrace-tm-spr ptrace-hwbreak ptrace-pkey core-pkey \
               perf-hwbreak
 
+top_srcdir = ../../../../..
 include ../../lib.mk
 
 all: $(TEST_PROGS)
diff --git a/tools/testing/selftests/powerpc/signal/Makefile b/tools/testing/selftests/powerpc/signal/Makefile
index a7cbd5082e27..1fca25c6ace0 100644
--- a/tools/testing/selftests/powerpc/signal/Makefile
+++ b/tools/testing/selftests/powerpc/signal/Makefile
@@ -8,6 +8,7 @@ $(TEST_PROGS): ../harness.c ../utils.c signal.S
 CFLAGS += -maltivec
 signal_tm: CFLAGS += -mhtm
 
+top_srcdir = ../../../../..
 include ../../lib.mk
 
 clean:
diff --git a/tools/testing/selftests/powerpc/stringloops/Makefile b/tools/testing/selftests/powerpc/stringloops/Makefile
index 10b35c87a4f4..7fc0623d85c3 100644
--- a/tools/testing/selftests/powerpc/stringloops/Makefile
+++ b/tools/testing/selftests/powerpc/stringloops/Makefile
@@ -29,6 +29,7 @@ endif
 
 ASFLAGS = $(CFLAGS)
 
+top_srcdir = ../../../../..
 include ../../lib.mk
 
 $(TEST_GEN_PROGS): $(EXTRA_SOURCES)
diff --git a/tools/testing/selftests/powerpc/switch_endian/Makefile b/tools/testing/selftests/powerpc/switch_endian/Makefile
index 30b8ff8fb82e..fcd2dcb8972b 100644
--- a/tools/testing/selftests/powerpc/switch_endian/Makefile
+++ b/tools/testing/selftests/powerpc/switch_endian/Makefile
@@ -5,6 +5,7 @@ ASFLAGS += -O2 -Wall -g -nostdlib -m64
 
 EXTRA_CLEAN = $(OUTPUT)/*.o $(OUTPUT)/check-reversed.S
 
+top_srcdir = ../../../../..
 include ../../lib.mk
 
 $(OUTPUT)/switch_endian_test: $(OUTPUT)/check-reversed.S
diff --git a/tools/testing/selftests/powerpc/syscalls/Makefile b/tools/testing/selftests/powerpc/syscalls/Makefile
index da22ca7c38c1..161b8846336f 100644
--- a/tools/testing/selftests/powerpc/syscalls/Makefile
+++ b/tools/testing/selftests/powerpc/syscalls/Makefile
@@ -2,6 +2,7 @@ TEST_GEN_PROGS := ipc_unmuxed
 
 CFLAGS += -I../../../../../usr/include
 
+top_srcdir = ../../../../..
 include ../../lib.mk
 
 $(TEST_GEN_PROGS): ../harness.c
diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile
index c0e45d2dde25..9fc2cf6fbc92 100644
--- a/tools/testing/selftests/powerpc/tm/Makefile
+++ b/tools/testing/selftests/powerpc/tm/Makefile
@@ -6,6 +6,7 @@ TEST_GEN_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack
 	tm-vmxcopy tm-fork tm-tar tm-tmspr tm-vmx-unavail tm-unavailable tm-trap \
 	$(SIGNAL_CONTEXT_CHK_TESTS) tm-sigreturn
 
+top_srcdir = ../../../../..
 include ../../lib.mk
 
 $(TEST_GEN_PROGS): ../harness.c ../utils.c
diff --git a/tools/testing/selftests/powerpc/vphn/Makefile b/tools/testing/selftests/powerpc/vphn/Makefile
index f8ced26748f8..fb82068c9fda 100644
--- a/tools/testing/selftests/powerpc/vphn/Makefile
+++ b/tools/testing/selftests/powerpc/vphn/Makefile
@@ -2,6 +2,7 @@ TEST_GEN_PROGS := test-vphn
 
 CFLAGS += -m64
 
+top_srcdir = ../../../../..
 include ../../lib.mk
 
 $(TEST_GEN_PROGS): ../harness.c
-- 
cgit 


From a804e5e21875418af03e0a413a633f4643739c90 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Thu, 27 Sep 2018 16:35:13 +0300
Subject: selftests: forwarding: test for bridge sticky flag

This test adds an fdb entry with the sticky flag and sends traffic from
a different port with the same mac as a source address expecting the entry
to not change ports if the flag is operating correctly.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/bridge_sticky_fdb.sh  | 69 ++++++++++++++++++++++
 1 file changed, 69 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/bridge_sticky_fdb.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/forwarding/bridge_sticky_fdb.sh b/tools/testing/selftests/net/forwarding/bridge_sticky_fdb.sh
new file mode 100755
index 000000000000..1f8ef0eff862
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/bridge_sticky_fdb.sh
@@ -0,0 +1,69 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="sticky"
+NUM_NETIFS=4
+TEST_MAC=de:ad:be:ef:13:37
+source lib.sh
+
+switch_create()
+{
+	ip link add dev br0 type bridge
+
+	ip link set dev $swp1 master br0
+	ip link set dev $swp2 master br0
+
+	ip link set dev br0 up
+	ip link set dev $h1 up
+	ip link set dev $swp1 up
+	ip link set dev $h2 up
+	ip link set dev $swp2 up
+}
+
+switch_destroy()
+{
+	ip link set dev $swp2 down
+	ip link set dev $h2 down
+	ip link set dev $swp1 down
+	ip link set dev $h1 down
+
+	ip link del dev br0
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+	h2=${NETIFS[p3]}
+	swp2=${NETIFS[p4]}
+
+	switch_create
+}
+
+cleanup()
+{
+	pre_cleanup
+	switch_destroy
+}
+
+sticky()
+{
+	bridge fdb add $TEST_MAC dev $swp1 master static sticky
+	check_err $? "Could not add fdb entry"
+	bridge fdb del $TEST_MAC dev $swp1 vlan 1 master static sticky
+	$MZ $h2 -c 1 -a $TEST_MAC -t arp "request" -q
+	bridge -j fdb show br br0 brport $swp1\
+		| jq -e ".[] | select(.mac == \"$TEST_MAC\")" &> /dev/null
+	check_err $? "Did not find FDB record when should"
+
+	log_test "Sticky fdb entry"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit 


From 66ee620f06f99d72475db6eb638559ba608c7dee Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Mon, 25 Jun 2018 06:56:50 -0400
Subject: idr: Permit any valid kernel pointer to be stored

An upcoming change to the encoding of internal entries will set the bottom
two bits to 0b10.  Unfortunately, m68k only aligns some data structures
to 2 bytes, so the IDR will interpret them as internal entries and things
will go badly wrong.

Change the radix tree so that it stops either when the node indicates
that it's the bottom of the tree (shift == 0) or when the entry is not an
internal entry.  This means we cannot insert an arbitrary kernel pointer
as a multiorder entry, but the IDR does not permit multiorder entries.

Annoyingly, this means the IDR can no longer take advantage of the radix
tree's ability to store a single entry at offset 0 without allocating
memory.  A pointer which is 2-byte aligned cannot be stored directly in
the root as it would be indistinguishable from a node, so we must allocate
a node in order to store a 2-byte pointer at index 0.  The idr_replace()
function does not take a GFP flags argument, so cannot allocate memory.
If a user inserts a 4-byte aligned pointer at index 0 and then replaces
it with a 2-byte aligned pointer, we must be able to store it.

Arbitrary pointer values are still not permitted; pointers of the
form 2 + (i * 4) for values of i between 0 and 1023 are reserved for
the implementation.  These are not valid kernel pointers as they would
point into the zero page.

This change does cause a runtime memory consumption regression for
the IDA.  I will recover that later.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
Tested-by: Guenter Roeck <linux@roeck-us.net>
---
 lib/idr.c                           |  4 ---
 lib/radix-tree.c                    | 21 +++++++++----
 tools/testing/radix-tree/idr-test.c | 63 +++++++++++++++++++++++++++++++++++++
 3 files changed, 78 insertions(+), 10 deletions(-)

(limited to 'tools/testing')

diff --git a/lib/idr.c b/lib/idr.c
index fab2fd5bc326..729e381e23b4 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -39,8 +39,6 @@ int idr_alloc_u32(struct idr *idr, void *ptr, u32 *nextid,
 	unsigned int base = idr->idr_base;
 	unsigned int id = *nextid;
 
-	if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr)))
-		return -EINVAL;
 	if (WARN_ON_ONCE(!(idr->idr_rt.gfp_mask & ROOT_IS_IDR)))
 		idr->idr_rt.gfp_mask |= IDR_RT_MARKER;
 
@@ -295,8 +293,6 @@ void *idr_replace(struct idr *idr, void *ptr, unsigned long id)
 	void __rcu **slot = NULL;
 	void *entry;
 
-	if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr)))
-		return ERR_PTR(-EINVAL);
 	id -= idr->idr_base;
 
 	entry = __radix_tree_lookup(&idr->idr_rt, id, &node, &slot);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index bc03ecc4dfd2..a904a8ddd174 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -703,6 +703,14 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root,
 		if (!radix_tree_is_internal_node(child) && node->shift)
 			break;
 
+		/*
+		 * For an IDR, we must not shrink entry 0 into the root in
+		 * case somebody calls idr_replace() with a pointer that
+		 * appears to be an internal entry
+		 */
+		if (!node->shift && is_idr(root))
+			break;
+
 		if (radix_tree_is_internal_node(child))
 			entry_to_node(child)->parent = NULL;
 
@@ -875,8 +883,8 @@ static void radix_tree_free_nodes(struct radix_tree_node *node)
 
 	for (;;) {
 		void *entry = rcu_dereference_raw(child->slots[offset]);
-		if (radix_tree_is_internal_node(entry) &&
-					!is_sibling_entry(child, entry)) {
+		if (radix_tree_is_internal_node(entry) && child->shift &&
+				!is_sibling_entry(child, entry)) {
 			child = entry_to_node(entry);
 			offset = 0;
 			continue;
@@ -1049,6 +1057,8 @@ void *__radix_tree_lookup(const struct radix_tree_root *root,
 		parent = entry_to_node(node);
 		offset = radix_tree_descend(parent, &node, index);
 		slot = parent->slots + offset;
+		if (parent->shift == 0)
+			break;
 	}
 
 	if (nodep)
@@ -1123,9 +1133,6 @@ static inline void replace_sibling_entries(struct radix_tree_node *node,
 static void replace_slot(void __rcu **slot, void *item,
 		struct radix_tree_node *node, int count, int exceptional)
 {
-	if (WARN_ON_ONCE(radix_tree_is_internal_node(item)))
-		return;
-
 	if (node && (count || exceptional)) {
 		node->count += count;
 		node->exceptional += exceptional;
@@ -1784,7 +1791,7 @@ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root,
 			goto restart;
 		if (child == RADIX_TREE_RETRY)
 			break;
-	} while (radix_tree_is_internal_node(child));
+	} while (node->shift && radix_tree_is_internal_node(child));
 
 	/* Update the iterator state */
 	iter->index = (index &~ node_maxindex(node)) | (offset << node->shift);
@@ -2150,6 +2157,8 @@ void __rcu **idr_get_free(struct radix_tree_root *root,
 		shift = error;
 		child = rcu_dereference_raw(root->rnode);
 	}
+	if (start == 0 && shift == 0)
+		shift = RADIX_TREE_MAP_SHIFT;
 
 	while (shift) {
 		shift -= RADIX_TREE_MAP_SHIFT;
diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index 321ba92c70d2..f620c831a4b5 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -227,6 +227,66 @@ void idr_u32_test(int base)
 	idr_u32_test1(&idr, 0xffffffff);
 }
 
+static void idr_align_test(struct idr *idr)
+{
+	char name[] = "Motorola 68000";
+	int i, id;
+	void *entry;
+
+	for (i = 0; i < 9; i++) {
+		BUG_ON(idr_alloc(idr, &name[i], 0, 0, GFP_KERNEL) != i);
+		idr_for_each_entry(idr, entry, id);
+	}
+	idr_destroy(idr);
+
+	for (i = 1; i < 10; i++) {
+		BUG_ON(idr_alloc(idr, &name[i], 0, 0, GFP_KERNEL) != i - 1);
+		idr_for_each_entry(idr, entry, id);
+	}
+	idr_destroy(idr);
+
+	for (i = 2; i < 11; i++) {
+		BUG_ON(idr_alloc(idr, &name[i], 0, 0, GFP_KERNEL) != i - 2);
+		idr_for_each_entry(idr, entry, id);
+	}
+	idr_destroy(idr);
+
+	for (i = 3; i < 12; i++) {
+		BUG_ON(idr_alloc(idr, &name[i], 0, 0, GFP_KERNEL) != i - 3);
+		idr_for_each_entry(idr, entry, id);
+	}
+	idr_destroy(idr);
+
+	for (i = 0; i < 8; i++) {
+		BUG_ON(idr_alloc(idr, &name[i], 0, 0, GFP_KERNEL) != 0);
+		BUG_ON(idr_alloc(idr, &name[i + 1], 0, 0, GFP_KERNEL) != 1);
+		idr_for_each_entry(idr, entry, id);
+		idr_remove(idr, 1);
+		idr_for_each_entry(idr, entry, id);
+		idr_remove(idr, 0);
+		BUG_ON(!idr_is_empty(idr));
+	}
+
+	for (i = 0; i < 8; i++) {
+		BUG_ON(idr_alloc(idr, NULL, 0, 0, GFP_KERNEL) != 0);
+		idr_for_each_entry(idr, entry, id);
+		idr_replace(idr, &name[i], 0);
+		idr_for_each_entry(idr, entry, id);
+		BUG_ON(idr_find(idr, 0) != &name[i]);
+		idr_remove(idr, 0);
+	}
+
+	for (i = 0; i < 8; i++) {
+		BUG_ON(idr_alloc(idr, &name[i], 0, 0, GFP_KERNEL) != 0);
+		BUG_ON(idr_alloc(idr, NULL, 0, 0, GFP_KERNEL) != 1);
+		idr_remove(idr, 1);
+		idr_for_each_entry(idr, entry, id);
+		idr_replace(idr, &name[i + 1], 0);
+		idr_for_each_entry(idr, entry, id);
+		idr_remove(idr, 0);
+	}
+}
+
 void idr_checks(void)
 {
 	unsigned long i;
@@ -307,6 +367,7 @@ void idr_checks(void)
 	idr_u32_test(4);
 	idr_u32_test(1);
 	idr_u32_test(0);
+	idr_align_test(&idr);
 }
 
 #define module_init(x)
@@ -341,6 +402,7 @@ void ida_check_nomem(void)
  */
 void ida_check_conv_user(void)
 {
+#if 0
 	DEFINE_IDA(ida);
 	unsigned long i;
 
@@ -358,6 +420,7 @@ void ida_check_conv_user(void)
 		IDA_BUG_ON(&ida, id != i);
 	}
 	ida_destroy(&ida);
+#endif
 }
 
 void ida_check_random(void)
-- 
cgit 


From 3159f943aafdbacb2f94c38fdaadabf2bbde2a14 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Fri, 3 Nov 2017 13:30:42 -0400
Subject: xarray: Replace exceptional entries

Introduce xarray value entries and tagged pointers to replace radix
tree exceptional entries.  This is a slight change in encoding to allow
the use of an extra bit (we can now store BITS_PER_LONG - 1 bits in a
value entry).  It is also a change in emphasis; exceptional entries are
intimidating and different.  As the comment explains, you can choose
to store values or pointers in the xarray and they are both first-class
citizens.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
Reviewed-by: Josef Bacik <jbacik@fb.com>
---
 arch/powerpc/include/asm/book3s/64/pgtable.h |   4 +-
 arch/powerpc/include/asm/nohash/64/pgtable.h |   4 +-
 drivers/gpu/drm/i915/i915_gem.c              |  17 ++--
 drivers/staging/erofs/utils.c                |  18 ++---
 fs/btrfs/compression.c                       |   2 +-
 fs/dax.c                                     | 112 +++++++++++++--------------
 fs/proc/task_mmu.c                           |   2 +-
 include/linux/radix-tree.h                   |  36 ++-------
 include/linux/swapops.h                      |  19 ++---
 include/linux/xarray.h                       | 102 ++++++++++++++++++++++++
 lib/idr.c                                    |  60 ++++++--------
 lib/radix-tree.c                             |  21 +++--
 mm/filemap.c                                 |  10 +--
 mm/khugepaged.c                              |   2 +-
 mm/madvise.c                                 |   2 +-
 mm/memcontrol.c                              |   2 +-
 mm/mincore.c                                 |   2 +-
 mm/readahead.c                               |   2 +-
 mm/shmem.c                                   |  10 +--
 mm/swap.c                                    |   2 +-
 mm/truncate.c                                |  12 +--
 mm/workingset.c                              |  13 ++--
 tools/testing/radix-tree/idr-test.c          |   6 +-
 tools/testing/radix-tree/linux/radix-tree.h  |   1 -
 tools/testing/radix-tree/multiorder.c        |  47 ++++++-----
 tools/testing/radix-tree/test.c              |   2 +-
 26 files changed, 278 insertions(+), 232 deletions(-)

(limited to 'tools/testing')

diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 2fdc865ca374..62039e557ac0 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -723,9 +723,7 @@ static inline bool pte_user(pte_t pte)
 	BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \
 	BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_SOFT_DIRTY);	\
 	} while (0)
-/*
- * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT;
- */
+
 #define SWP_TYPE_BITS 5
 #define __swp_type(x)		(((x).val >> _PAGE_BIT_SWAP_TYPE) \
 				& ((1UL << SWP_TYPE_BITS) - 1))
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index 7cd6809f4d33..05765c2d2c1f 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -313,9 +313,7 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
 #define MAX_SWAPFILES_CHECK() do { \
 	BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS); \
 	} while (0)
-/*
- * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT;
- */
+
 #define SWP_TYPE_BITS 5
 #define __swp_type(x)		(((x).val >> _PAGE_BIT_SWAP_TYPE) \
 				& ((1UL << SWP_TYPE_BITS) - 1))
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index fcc73a6ab503..316730b45f84 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5996,7 +5996,8 @@ i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
 	count = __sg_page_count(sg);
 
 	while (idx + count <= n) {
-		unsigned long exception, i;
+		void *entry;
+		unsigned long i;
 		int ret;
 
 		/* If we cannot allocate and insert this entry, or the
@@ -6011,12 +6012,9 @@ i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
 		if (ret && ret != -EEXIST)
 			goto scan;
 
-		exception =
-			RADIX_TREE_EXCEPTIONAL_ENTRY |
-			idx << RADIX_TREE_EXCEPTIONAL_SHIFT;
+		entry = xa_mk_value(idx);
 		for (i = 1; i < count; i++) {
-			ret = radix_tree_insert(&iter->radix, idx + i,
-						(void *)exception);
+			ret = radix_tree_insert(&iter->radix, idx + i, entry);
 			if (ret && ret != -EEXIST)
 				goto scan;
 		}
@@ -6054,15 +6052,14 @@ lookup:
 	GEM_BUG_ON(!sg);
 
 	/* If this index is in the middle of multi-page sg entry,
-	 * the radixtree will contain an exceptional entry that points
+	 * the radix tree will contain a value entry that points
 	 * to the start of that range. We will return the pointer to
 	 * the base page and the offset of this page within the
 	 * sg entry's range.
 	 */
 	*offset = 0;
-	if (unlikely(radix_tree_exception(sg))) {
-		unsigned long base =
-			(unsigned long)sg >> RADIX_TREE_EXCEPTIONAL_SHIFT;
+	if (unlikely(xa_is_value(sg))) {
+		unsigned long base = xa_to_value(sg);
 
 		sg = radix_tree_lookup(&iter->radix, base);
 		GEM_BUG_ON(!sg);
diff --git a/drivers/staging/erofs/utils.c b/drivers/staging/erofs/utils.c
index 595cf90af9bb..bdee9bd09f11 100644
--- a/drivers/staging/erofs/utils.c
+++ b/drivers/staging/erofs/utils.c
@@ -35,7 +35,6 @@ static atomic_long_t erofs_global_shrink_cnt;
 
 #ifdef CONFIG_EROFS_FS_ZIP
 
-/* radix_tree and the future XArray both don't use tagptr_t yet */
 struct erofs_workgroup *erofs_find_workgroup(
 	struct super_block *sb, pgoff_t index, bool *tag)
 {
@@ -47,9 +46,8 @@ repeat:
 	rcu_read_lock();
 	grp = radix_tree_lookup(&sbi->workstn_tree, index);
 	if (grp != NULL) {
-		*tag = radix_tree_exceptional_entry(grp);
-		grp = (void *)((unsigned long)grp &
-			~RADIX_TREE_EXCEPTIONAL_ENTRY);
+		*tag = xa_pointer_tag(grp);
+		grp = xa_untag_pointer(grp);
 
 		if (erofs_workgroup_get(grp, &oldcount)) {
 			/* prefer to relax rcu read side */
@@ -83,9 +81,7 @@ int erofs_register_workgroup(struct super_block *sb,
 	sbi = EROFS_SB(sb);
 	erofs_workstn_lock(sbi);
 
-	if (tag)
-		grp = (void *)((unsigned long)grp |
-			1UL << RADIX_TREE_EXCEPTIONAL_SHIFT);
+	grp = xa_tag_pointer(grp, tag);
 
 	err = radix_tree_insert(&sbi->workstn_tree,
 		grp->index, grp);
@@ -131,9 +127,7 @@ repeat:
 
 	for (i = 0; i < found; ++i) {
 		int cnt;
-		struct erofs_workgroup *grp = (void *)
-			((unsigned long)batch[i] &
-				~RADIX_TREE_EXCEPTIONAL_ENTRY);
+		struct erofs_workgroup *grp = xa_untag_pointer(batch[i]);
 
 		first_index = grp->index + 1;
 
@@ -150,8 +144,8 @@ repeat:
 #endif
 			continue;
 
-		if (radix_tree_delete(&sbi->workstn_tree,
-			grp->index) != grp) {
+		if (xa_untag_pointer(radix_tree_delete(&sbi->workstn_tree,
+			grp->index)) != grp) {
 #ifdef EROFS_FS_HAS_MANAGED_CACHE
 skip:
 			erofs_workgroup_unfreeze(grp, 1);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 9bfa66592aa7..fd25e125303c 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -440,7 +440,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		rcu_read_lock();
 		page = radix_tree_lookup(&mapping->i_pages, pg_index);
 		rcu_read_unlock();
-		if (page && !radix_tree_exceptional_entry(page)) {
+		if (page && !xa_is_value(page)) {
 			misses++;
 			if (misses > 4)
 				break;
diff --git a/fs/dax.c b/fs/dax.c
index b68ce484e1be..ebcec36335eb 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -59,56 +59,57 @@ static int __init init_dax_wait_table(void)
 fs_initcall(init_dax_wait_table);
 
 /*
- * We use lowest available bit in exceptional entry for locking, one bit for
- * the entry size (PMD) and two more to tell us if the entry is a zero page or
- * an empty entry that is just used for locking.  In total four special bits.
+ * DAX pagecache entries use XArray value entries so they can't be mistaken
+ * for pages.  We use one bit for locking, one bit for the entry size (PMD)
+ * and two more to tell us if the entry is a zero page or an empty entry that
+ * is just used for locking.  In total four special bits.
  *
  * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the ZERO_PAGE
  * and EMPTY bits aren't set the entry is a normal DAX entry with a filesystem
  * block allocation.
  */
-#define RADIX_DAX_SHIFT		(RADIX_TREE_EXCEPTIONAL_SHIFT + 4)
-#define RADIX_DAX_ENTRY_LOCK	(1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
-#define RADIX_DAX_PMD		(1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1))
-#define RADIX_DAX_ZERO_PAGE	(1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
-#define RADIX_DAX_EMPTY		(1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3))
+#define DAX_SHIFT	(4)
+#define DAX_LOCKED	(1UL << 0)
+#define DAX_PMD		(1UL << 1)
+#define DAX_ZERO_PAGE	(1UL << 2)
+#define DAX_EMPTY	(1UL << 3)
 
 static unsigned long dax_radix_pfn(void *entry)
 {
-	return (unsigned long)entry >> RADIX_DAX_SHIFT;
+	return xa_to_value(entry) >> DAX_SHIFT;
 }
 
 static void *dax_radix_locked_entry(unsigned long pfn, unsigned long flags)
 {
-	return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags |
-			(pfn << RADIX_DAX_SHIFT) | RADIX_DAX_ENTRY_LOCK);
+	return xa_mk_value(flags | ((unsigned long)pfn << DAX_SHIFT) |
+			DAX_LOCKED);
 }
 
 static unsigned int dax_radix_order(void *entry)
 {
-	if ((unsigned long)entry & RADIX_DAX_PMD)
+	if (xa_to_value(entry) & DAX_PMD)
 		return PMD_SHIFT - PAGE_SHIFT;
 	return 0;
 }
 
 static int dax_is_pmd_entry(void *entry)
 {
-	return (unsigned long)entry & RADIX_DAX_PMD;
+	return xa_to_value(entry) & DAX_PMD;
 }
 
 static int dax_is_pte_entry(void *entry)
 {
-	return !((unsigned long)entry & RADIX_DAX_PMD);
+	return !(xa_to_value(entry) & DAX_PMD);
 }
 
 static int dax_is_zero_entry(void *entry)
 {
-	return (unsigned long)entry & RADIX_DAX_ZERO_PAGE;
+	return xa_to_value(entry) & DAX_ZERO_PAGE;
 }
 
 static int dax_is_empty_entry(void *entry)
 {
-	return (unsigned long)entry & RADIX_DAX_EMPTY;
+	return xa_to_value(entry) & DAX_EMPTY;
 }
 
 /*
@@ -186,9 +187,9 @@ static void dax_wake_mapping_entry_waiter(struct address_space *mapping,
  */
 static inline int slot_locked(struct address_space *mapping, void **slot)
 {
-	unsigned long entry = (unsigned long)
-		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock);
-	return entry & RADIX_DAX_ENTRY_LOCK;
+	unsigned long entry = xa_to_value(
+		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock));
+	return entry & DAX_LOCKED;
 }
 
 /*
@@ -196,12 +197,11 @@ static inline int slot_locked(struct address_space *mapping, void **slot)
  */
 static inline void *lock_slot(struct address_space *mapping, void **slot)
 {
-	unsigned long entry = (unsigned long)
-		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock);
-
-	entry |= RADIX_DAX_ENTRY_LOCK;
-	radix_tree_replace_slot(&mapping->i_pages, slot, (void *)entry);
-	return (void *)entry;
+	unsigned long v = xa_to_value(
+		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock));
+	void *entry = xa_mk_value(v | DAX_LOCKED);
+	radix_tree_replace_slot(&mapping->i_pages, slot, entry);
+	return entry;
 }
 
 /*
@@ -209,17 +209,16 @@ static inline void *lock_slot(struct address_space *mapping, void **slot)
  */
 static inline void *unlock_slot(struct address_space *mapping, void **slot)
 {
-	unsigned long entry = (unsigned long)
-		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock);
-
-	entry &= ~(unsigned long)RADIX_DAX_ENTRY_LOCK;
-	radix_tree_replace_slot(&mapping->i_pages, slot, (void *)entry);
-	return (void *)entry;
+	unsigned long v = xa_to_value(
+		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock));
+	void *entry = xa_mk_value(v & ~DAX_LOCKED);
+	radix_tree_replace_slot(&mapping->i_pages, slot, entry);
+	return entry;
 }
 
 /*
  * Lookup entry in radix tree, wait for it to become unlocked if it is
- * exceptional entry and return it. The caller must call
+ * a DAX entry and return it. The caller must call
  * put_unlocked_mapping_entry() when he decided not to lock the entry or
  * put_locked_mapping_entry() when he locked the entry and now wants to
  * unlock it.
@@ -242,7 +241,7 @@ static void *__get_unlocked_mapping_entry(struct address_space *mapping,
 		entry = __radix_tree_lookup(&mapping->i_pages, index, NULL,
 					  &slot);
 		if (!entry ||
-		    WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)) ||
+		    WARN_ON_ONCE(!xa_is_value(entry)) ||
 		    !slot_locked(mapping, slot)) {
 			if (slotp)
 				*slotp = slot;
@@ -283,7 +282,7 @@ static void unlock_mapping_entry(struct address_space *mapping, pgoff_t index)
 
 	xa_lock_irq(&mapping->i_pages);
 	entry = __radix_tree_lookup(&mapping->i_pages, index, NULL, &slot);
-	if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry) ||
+	if (WARN_ON_ONCE(!entry || !xa_is_value(entry) ||
 			 !slot_locked(mapping, slot))) {
 		xa_unlock_irq(&mapping->i_pages);
 		return;
@@ -472,12 +471,11 @@ void dax_unlock_mapping_entry(struct page *page)
 }
 
 /*
- * Find radix tree entry at given index. If it points to an exceptional entry,
- * return it with the radix tree entry locked. If the radix tree doesn't
- * contain given index, create an empty exceptional entry for the index and
- * return with it locked.
+ * Find radix tree entry at given index. If it is a DAX entry, return it
+ * with the radix tree entry locked. If the radix tree doesn't contain the
+ * given index, create an empty entry for the index and return with it locked.
  *
- * When requesting an entry with size RADIX_DAX_PMD, grab_mapping_entry() will
+ * When requesting an entry with size DAX_PMD, grab_mapping_entry() will
  * either return that locked entry or will return an error.  This error will
  * happen if there are any 4k entries within the 2MiB range that we are
  * requesting.
@@ -507,13 +505,13 @@ restart:
 	xa_lock_irq(&mapping->i_pages);
 	entry = get_unlocked_mapping_entry(mapping, index, &slot);
 
-	if (WARN_ON_ONCE(entry && !radix_tree_exceptional_entry(entry))) {
+	if (WARN_ON_ONCE(entry && !xa_is_value(entry))) {
 		entry = ERR_PTR(-EIO);
 		goto out_unlock;
 	}
 
 	if (entry) {
-		if (size_flag & RADIX_DAX_PMD) {
+		if (size_flag & DAX_PMD) {
 			if (dax_is_pte_entry(entry)) {
 				put_unlocked_mapping_entry(mapping, index,
 						entry);
@@ -584,7 +582,7 @@ restart:
 					true);
 		}
 
-		entry = dax_radix_locked_entry(0, size_flag | RADIX_DAX_EMPTY);
+		entry = dax_radix_locked_entry(0, size_flag | DAX_EMPTY);
 
 		err = __radix_tree_insert(&mapping->i_pages, index,
 				dax_radix_order(entry), entry);
@@ -673,8 +671,7 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 			if (index >= end)
 				break;
 
-			if (WARN_ON_ONCE(
-			     !radix_tree_exceptional_entry(pvec_ent)))
+			if (WARN_ON_ONCE(!xa_is_value(pvec_ent)))
 				continue;
 
 			xa_lock_irq(&mapping->i_pages);
@@ -713,7 +710,7 @@ static int __dax_invalidate_mapping_entry(struct address_space *mapping,
 
 	xa_lock_irq(pages);
 	entry = get_unlocked_mapping_entry(mapping, index, NULL);
-	if (!entry || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)))
+	if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
 		goto out;
 	if (!trunc &&
 	    (radix_tree_tag_get(pages, index, PAGECACHE_TAG_DIRTY) ||
@@ -729,8 +726,8 @@ out:
 	return ret;
 }
 /*
- * Delete exceptional DAX entry at @index from @mapping. Wait for radix tree
- * entry to get unlocked before deleting it.
+ * Delete DAX entry at @index from @mapping.  Wait for it
+ * to be unlocked before deleting it.
  */
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 {
@@ -740,7 +737,7 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 	 * This gets called from truncate / punch_hole path. As such, the caller
 	 * must hold locks protecting against concurrent modifications of the
 	 * radix tree (usually fs-private i_mmap_sem for writing). Since the
-	 * caller has seen exceptional entry for this index, we better find it
+	 * caller has seen a DAX entry for this index, we better find it
 	 * at that index as well...
 	 */
 	WARN_ON_ONCE(!ret);
@@ -748,7 +745,7 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 }
 
 /*
- * Invalidate exceptional DAX entry if it is clean.
+ * Invalidate DAX entry if it is clean.
  */
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 				      pgoff_t index)
@@ -802,7 +799,7 @@ static void *dax_insert_mapping_entry(struct address_space *mapping,
 	if (dirty)
 		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 
-	if (dax_is_zero_entry(entry) && !(flags & RADIX_DAX_ZERO_PAGE)) {
+	if (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE)) {
 		/* we are replacing a zero page with block mapping */
 		if (dax_is_pmd_entry(entry))
 			unmap_mapping_pages(mapping, index & ~PG_PMD_COLOUR,
@@ -940,13 +937,13 @@ static int dax_writeback_one(struct dax_device *dax_dev,
 	 * A page got tagged dirty in DAX mapping? Something is seriously
 	 * wrong.
 	 */
-	if (WARN_ON(!radix_tree_exceptional_entry(entry)))
+	if (WARN_ON(!xa_is_value(entry)))
 		return -EIO;
 
 	xa_lock_irq(pages);
 	entry2 = get_unlocked_mapping_entry(mapping, index, &slot);
 	/* Entry got punched out / reallocated? */
-	if (!entry2 || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry2)))
+	if (!entry2 || WARN_ON_ONCE(!xa_is_value(entry2)))
 		goto put_unlocked;
 	/*
 	 * Entry got reallocated elsewhere? No need to writeback. We have to
@@ -1123,8 +1120,9 @@ static vm_fault_t dax_load_hole(struct address_space *mapping, void *entry,
 	pfn_t pfn = pfn_to_pfn_t(my_zero_pfn(vaddr));
 	vm_fault_t ret;
 
-	dax_insert_mapping_entry(mapping, vmf, entry, pfn, RADIX_DAX_ZERO_PAGE,
-			false);
+	dax_insert_mapping_entry(mapping, vmf, entry, pfn,
+			DAX_ZERO_PAGE, false);
+
 	ret = vmf_insert_mixed(vmf->vma, vaddr, pfn);
 	trace_dax_load_hole(inode, vmf, ret);
 	return ret;
@@ -1514,7 +1512,7 @@ static vm_fault_t dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap,
 
 	pfn = page_to_pfn_t(zero_page);
 	ret = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
-			RADIX_DAX_PMD | RADIX_DAX_ZERO_PAGE, false);
+			DAX_PMD | DAX_ZERO_PAGE, false);
 
 	ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
 	if (!pmd_none(*(vmf->pmd))) {
@@ -1597,7 +1595,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	 * is already in the tree, for instance), it will return -EEXIST and
 	 * we just fall back to 4k entries.
 	 */
-	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
+	entry = grab_mapping_entry(mapping, pgoff, DAX_PMD);
 	if (IS_ERR(entry))
 		goto fallback;
 
@@ -1635,7 +1633,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 			goto finish_iomap;
 
 		entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
-						RADIX_DAX_PMD, write && !sync);
+						DAX_PMD, write && !sync);
 
 		/*
 		 * If we are doing synchronous page fault and inode needs fsync,
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 5ea1d64cb0b4..669abb617321 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -521,7 +521,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 		if (!page)
 			return;
 
-		if (radix_tree_exceptional_entry(page))
+		if (xa_is_value(page))
 			mss->swap += PAGE_SIZE;
 		else
 			put_page(page);
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 34149e8b5f73..e9e76ab4fbbf 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -28,34 +28,26 @@
 #include <linux/rcupdate.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
+#include <linux/xarray.h>
 
 /*
  * The bottom two bits of the slot determine how the remaining bits in the
  * slot are interpreted:
  *
  * 00 - data pointer
- * 01 - internal entry
- * 10 - exceptional entry
- * 11 - this bit combination is currently unused/reserved
+ * 10 - internal entry
+ * x1 - value entry
  *
  * The internal entry may be a pointer to the next level in the tree, a
  * sibling entry, or an indicator that the entry in this slot has been moved
  * to another location in the tree and the lookup should be restarted.  While
  * NULL fits the 'data pointer' pattern, it means that there is no entry in
  * the tree for this index (no matter what level of the tree it is found at).
- * This means that you cannot store NULL in the tree as a value for the index.
+ * This means that storing a NULL entry in the tree is the same as deleting
+ * the entry from the tree.
  */
 #define RADIX_TREE_ENTRY_MASK		3UL
-#define RADIX_TREE_INTERNAL_NODE	1UL
-
-/*
- * Most users of the radix tree store pointers but shmem/tmpfs stores swap
- * entries in the same tree.  They are marked as exceptional entries to
- * distinguish them from pointers to struct page.
- * EXCEPTIONAL_ENTRY tests the bit, EXCEPTIONAL_SHIFT shifts content past it.
- */
-#define RADIX_TREE_EXCEPTIONAL_ENTRY	2
-#define RADIX_TREE_EXCEPTIONAL_SHIFT	2
+#define RADIX_TREE_INTERNAL_NODE	2UL
 
 static inline bool radix_tree_is_internal_node(void *ptr)
 {
@@ -83,11 +75,10 @@ static inline bool radix_tree_is_internal_node(void *ptr)
 
 /*
  * @count is the count of every non-NULL element in the ->slots array
- * whether that is an exceptional entry, a retry entry, a user pointer,
+ * whether that is a value entry, a retry entry, a user pointer,
  * a sibling entry or a pointer to the next level of the tree.
  * @exceptional is the count of every element in ->slots which is
- * either radix_tree_exceptional_entry() or is a sibling entry for an
- * exceptional entry.
+ * either a value entry or a sibling of a value entry.
  */
 struct radix_tree_node {
 	unsigned char	shift;		/* Bits remaining in each slot */
@@ -268,17 +259,6 @@ static inline int radix_tree_deref_retry(void *arg)
 	return unlikely(radix_tree_is_internal_node(arg));
 }
 
-/**
- * radix_tree_exceptional_entry	- radix_tree_deref_slot gave exceptional entry?
- * @arg:	value returned by radix_tree_deref_slot
- * Returns:	0 if well-aligned pointer, non-0 if exceptional entry.
- */
-static inline int radix_tree_exceptional_entry(void *arg)
-{
-	/* Not unlikely because radix_tree_exception often tested first */
-	return (unsigned long)arg & RADIX_TREE_EXCEPTIONAL_ENTRY;
-}
-
 /**
  * radix_tree_exception	- radix_tree_deref_slot returned either exception?
  * @arg:	value returned by radix_tree_deref_slot
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 22af9d8a84ae..4d961668e5fc 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -18,9 +18,8 @@
  *
  * swp_entry_t's are *never* stored anywhere in their arch-dependent format.
  */
-#define SWP_TYPE_SHIFT(e)	((sizeof(e.val) * 8) - \
-			(MAX_SWAPFILES_SHIFT + RADIX_TREE_EXCEPTIONAL_SHIFT))
-#define SWP_OFFSET_MASK(e)	((1UL << SWP_TYPE_SHIFT(e)) - 1)
+#define SWP_TYPE_SHIFT	(BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT)
+#define SWP_OFFSET_MASK	((1UL << SWP_TYPE_SHIFT) - 1)
 
 /*
  * Store a type+offset into a swp_entry_t in an arch-independent format
@@ -29,8 +28,7 @@ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset)
 {
 	swp_entry_t ret;
 
-	ret.val = (type << SWP_TYPE_SHIFT(ret)) |
-			(offset & SWP_OFFSET_MASK(ret));
+	ret.val = (type << SWP_TYPE_SHIFT) | (offset & SWP_OFFSET_MASK);
 	return ret;
 }
 
@@ -40,7 +38,7 @@ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset)
  */
 static inline unsigned swp_type(swp_entry_t entry)
 {
-	return (entry.val >> SWP_TYPE_SHIFT(entry));
+	return (entry.val >> SWP_TYPE_SHIFT);
 }
 
 /*
@@ -49,7 +47,7 @@ static inline unsigned swp_type(swp_entry_t entry)
  */
 static inline pgoff_t swp_offset(swp_entry_t entry)
 {
-	return entry.val & SWP_OFFSET_MASK(entry);
+	return entry.val & SWP_OFFSET_MASK;
 }
 
 #ifdef CONFIG_MMU
@@ -90,16 +88,13 @@ static inline swp_entry_t radix_to_swp_entry(void *arg)
 {
 	swp_entry_t entry;
 
-	entry.val = (unsigned long)arg >> RADIX_TREE_EXCEPTIONAL_SHIFT;
+	entry.val = xa_to_value(arg);
 	return entry;
 }
 
 static inline void *swp_to_radix_entry(swp_entry_t entry)
 {
-	unsigned long value;
-
-	value = entry.val << RADIX_TREE_EXCEPTIONAL_SHIFT;
-	return (void *)(value | RADIX_TREE_EXCEPTIONAL_ENTRY);
+	return xa_mk_value(entry.val);
 }
 
 #if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 9e4c86853fa4..5c8acfc4ff55 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -5,9 +5,111 @@
  * eXtensible Arrays
  * Copyright (c) 2017 Microsoft Corporation
  * Author: Matthew Wilcox <willy@infradead.org>
+ *
+ * See Documentation/core-api/xarray.rst for how to use the XArray.
  */
 
+#include <linux/bug.h>
 #include <linux/spinlock.h>
+#include <linux/types.h>
+
+/*
+ * The bottom two bits of the entry determine how the XArray interprets
+ * the contents:
+ *
+ * 00: Pointer entry
+ * 10: Internal entry
+ * x1: Value entry or tagged pointer
+ *
+ * Attempting to store internal entries in the XArray is a bug.
+ */
+
+#define BITS_PER_XA_VALUE	(BITS_PER_LONG - 1)
+
+/**
+ * xa_mk_value() - Create an XArray entry from an integer.
+ * @v: Value to store in XArray.
+ *
+ * Context: Any context.
+ * Return: An entry suitable for storing in the XArray.
+ */
+static inline void *xa_mk_value(unsigned long v)
+{
+	WARN_ON((long)v < 0);
+	return (void *)((v << 1) | 1);
+}
+
+/**
+ * xa_to_value() - Get value stored in an XArray entry.
+ * @entry: XArray entry.
+ *
+ * Context: Any context.
+ * Return: The value stored in the XArray entry.
+ */
+static inline unsigned long xa_to_value(const void *entry)
+{
+	return (unsigned long)entry >> 1;
+}
+
+/**
+ * xa_is_value() - Determine if an entry is a value.
+ * @entry: XArray entry.
+ *
+ * Context: Any context.
+ * Return: True if the entry is a value, false if it is a pointer.
+ */
+static inline bool xa_is_value(const void *entry)
+{
+	return (unsigned long)entry & 1;
+}
+
+/**
+ * xa_tag_pointer() - Create an XArray entry for a tagged pointer.
+ * @p: Plain pointer.
+ * @tag: Tag value (0, 1 or 3).
+ *
+ * If the user of the XArray prefers, they can tag their pointers instead
+ * of storing value entries.  Three tags are available (0, 1 and 3).
+ * These are distinct from the xa_mark_t as they are not replicated up
+ * through the array and cannot be searched for.
+ *
+ * Context: Any context.
+ * Return: An XArray entry.
+ */
+static inline void *xa_tag_pointer(void *p, unsigned long tag)
+{
+	return (void *)((unsigned long)p | tag);
+}
+
+/**
+ * xa_untag_pointer() - Turn an XArray entry into a plain pointer.
+ * @entry: XArray entry.
+ *
+ * If you have stored a tagged pointer in the XArray, call this function
+ * to get the untagged version of the pointer.
+ *
+ * Context: Any context.
+ * Return: A pointer.
+ */
+static inline void *xa_untag_pointer(void *entry)
+{
+	return (void *)((unsigned long)entry & ~3UL);
+}
+
+/**
+ * xa_pointer_tag() - Get the tag stored in an XArray entry.
+ * @entry: XArray entry.
+ *
+ * If you have stored a tagged pointer in the XArray, call this function
+ * to get the tag of that pointer.
+ *
+ * Context: Any context.
+ * Return: A tag.
+ */
+static inline unsigned int xa_pointer_tag(void *entry)
+{
+	return (unsigned long)entry & 3UL;
+}
 
 #define xa_trylock(xa)		spin_trylock(&(xa)->xa_lock)
 #define xa_lock(xa)		spin_lock(&(xa)->xa_lock)
diff --git a/lib/idr.c b/lib/idr.c
index 729e381e23b4..88419fbc5737 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -338,11 +338,8 @@ EXPORT_SYMBOL(idr_replace);
  * by the number of bits in the leaf bitmap before doing a radix tree lookup.
  *
  * As an optimisation, if there are only a few low bits set in any given
- * leaf, instead of allocating a 128-byte bitmap, we use the 'exceptional
- * entry' functionality of the radix tree to store BITS_PER_LONG - 2 bits
- * directly in the entry.  By being really tricksy, we could store
- * BITS_PER_LONG - 1 bits, but there're diminishing returns after optimising
- * for 0-3 allocated IDs.
+ * leaf, instead of allocating a 128-byte bitmap, we store the bits
+ * directly in the entry.
  *
  * We allow the radix tree 'exceptional' count to get out of date.  Nothing
  * in the IDA nor the radix tree code checks it.  If it becomes important
@@ -366,12 +363,11 @@ static int ida_get_new_above(struct ida *ida, int start)
 	struct radix_tree_iter iter;
 	struct ida_bitmap *bitmap;
 	unsigned long index;
-	unsigned bit, ebit;
+	unsigned bit;
 	int new;
 
 	index = start / IDA_BITMAP_BITS;
 	bit = start % IDA_BITMAP_BITS;
-	ebit = bit + RADIX_TREE_EXCEPTIONAL_SHIFT;
 
 	slot = radix_tree_iter_init(&iter, index);
 	for (;;) {
@@ -386,25 +382,23 @@ static int ida_get_new_above(struct ida *ida, int start)
 				return PTR_ERR(slot);
 			}
 		}
-		if (iter.index > index) {
+		if (iter.index > index)
 			bit = 0;
-			ebit = RADIX_TREE_EXCEPTIONAL_SHIFT;
-		}
 		new = iter.index * IDA_BITMAP_BITS;
 		bitmap = rcu_dereference_raw(*slot);
-		if (radix_tree_exception(bitmap)) {
-			unsigned long tmp = (unsigned long)bitmap;
-			ebit = find_next_zero_bit(&tmp, BITS_PER_LONG, ebit);
-			if (ebit < BITS_PER_LONG) {
-				tmp |= 1UL << ebit;
-				rcu_assign_pointer(*slot, (void *)tmp);
-				return new + ebit -
-					RADIX_TREE_EXCEPTIONAL_SHIFT;
+		if (xa_is_value(bitmap)) {
+			unsigned long tmp = xa_to_value(bitmap);
+			int vbit = find_next_zero_bit(&tmp, BITS_PER_XA_VALUE,
+							bit);
+			if (vbit < BITS_PER_XA_VALUE) {
+				tmp |= 1UL << vbit;
+				rcu_assign_pointer(*slot, xa_mk_value(tmp));
+				return new + vbit;
 			}
 			bitmap = this_cpu_xchg(ida_bitmap, NULL);
 			if (!bitmap)
 				return -EAGAIN;
-			bitmap->bitmap[0] = tmp >> RADIX_TREE_EXCEPTIONAL_SHIFT;
+			bitmap->bitmap[0] = tmp;
 			rcu_assign_pointer(*slot, bitmap);
 		}
 
@@ -425,17 +419,14 @@ static int ida_get_new_above(struct ida *ida, int start)
 			new += bit;
 			if (new < 0)
 				return -ENOSPC;
-			if (ebit < BITS_PER_LONG) {
-				bitmap = (void *)((1UL << ebit) |
-						RADIX_TREE_EXCEPTIONAL_ENTRY);
-				radix_tree_iter_replace(root, &iter, slot,
-						bitmap);
-				return new;
+			if (bit < BITS_PER_XA_VALUE) {
+				bitmap = xa_mk_value(1UL << bit);
+			} else {
+				bitmap = this_cpu_xchg(ida_bitmap, NULL);
+				if (!bitmap)
+					return -EAGAIN;
+				__set_bit(bit, bitmap->bitmap);
 			}
-			bitmap = this_cpu_xchg(ida_bitmap, NULL);
-			if (!bitmap)
-				return -EAGAIN;
-			__set_bit(bit, bitmap->bitmap);
 			radix_tree_iter_replace(root, &iter, slot, bitmap);
 		}
 
@@ -457,9 +448,9 @@ static void ida_remove(struct ida *ida, int id)
 		goto err;
 
 	bitmap = rcu_dereference_raw(*slot);
-	if (radix_tree_exception(bitmap)) {
+	if (xa_is_value(bitmap)) {
 		btmp = (unsigned long *)slot;
-		offset += RADIX_TREE_EXCEPTIONAL_SHIFT;
+		offset += 1; /* Intimate knowledge of the value encoding */
 		if (offset >= BITS_PER_LONG)
 			goto err;
 	} else {
@@ -470,9 +461,8 @@ static void ida_remove(struct ida *ida, int id)
 
 	__clear_bit(offset, btmp);
 	radix_tree_iter_tag_set(&ida->ida_rt, &iter, IDR_FREE);
-	if (radix_tree_exception(bitmap)) {
-		if (rcu_dereference_raw(*slot) ==
-					(void *)RADIX_TREE_EXCEPTIONAL_ENTRY)
+	if (xa_is_value(bitmap)) {
+		if (xa_to_value(rcu_dereference_raw(*slot)) == 0)
 			radix_tree_iter_delete(&ida->ida_rt, &iter, slot);
 	} else if (bitmap_empty(btmp, IDA_BITMAP_BITS)) {
 		kfree(bitmap);
@@ -503,7 +493,7 @@ void ida_destroy(struct ida *ida)
 	xa_lock_irqsave(&ida->ida_rt, flags);
 	radix_tree_for_each_slot(slot, &ida->ida_rt, &iter, 0) {
 		struct ida_bitmap *bitmap = rcu_dereference_raw(*slot);
-		if (!radix_tree_exception(bitmap))
+		if (!xa_is_value(bitmap))
 			kfree(bitmap);
 		radix_tree_iter_delete(&ida->ida_rt, &iter, slot);
 	}
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index a904a8ddd174..b6c0e7f3a894 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -340,14 +340,12 @@ static void dump_ida_node(void *entry, unsigned long index)
 		for (i = 0; i < RADIX_TREE_MAP_SIZE; i++)
 			dump_ida_node(node->slots[i],
 					index | (i << node->shift));
-	} else if (radix_tree_exceptional_entry(entry)) {
+	} else if (xa_is_value(entry)) {
 		pr_debug("ida excp: %p offset %d indices %lu-%lu data %lx\n",
 				entry, (int)(index & RADIX_TREE_MAP_MASK),
 				index * IDA_BITMAP_BITS,
-				index * IDA_BITMAP_BITS + BITS_PER_LONG -
-					RADIX_TREE_EXCEPTIONAL_SHIFT,
-				(unsigned long)entry >>
-					RADIX_TREE_EXCEPTIONAL_SHIFT);
+				index * IDA_BITMAP_BITS + BITS_PER_XA_VALUE,
+				xa_to_value(entry));
 	} else {
 		struct ida_bitmap *bitmap = entry;
 
@@ -656,7 +654,7 @@ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp,
 		BUG_ON(shift > BITS_PER_LONG);
 		if (radix_tree_is_internal_node(entry)) {
 			entry_to_node(entry)->parent = node;
-		} else if (radix_tree_exceptional_entry(entry)) {
+		} else if (xa_is_value(entry)) {
 			/* Moving an exceptional root->rnode to a node */
 			node->exceptional = 1;
 		}
@@ -955,12 +953,12 @@ static inline int insert_entries(struct radix_tree_node *node,
 					!is_sibling_entry(node, old) &&
 					(old != RADIX_TREE_RETRY))
 			radix_tree_free_nodes(old);
-		if (radix_tree_exceptional_entry(old))
+		if (xa_is_value(old))
 			node->exceptional--;
 	}
 	if (node) {
 		node->count += n;
-		if (radix_tree_exceptional_entry(item))
+		if (xa_is_value(item))
 			node->exceptional += n;
 	}
 	return n;
@@ -974,7 +972,7 @@ static inline int insert_entries(struct radix_tree_node *node,
 	rcu_assign_pointer(*slot, item);
 	if (node) {
 		node->count++;
-		if (radix_tree_exceptional_entry(item))
+		if (xa_is_value(item))
 			node->exceptional++;
 	}
 	return 1;
@@ -1190,8 +1188,7 @@ void __radix_tree_replace(struct radix_tree_root *root,
 			  radix_tree_update_node_t update_node)
 {
 	void *old = rcu_dereference_raw(*slot);
-	int exceptional = !!radix_tree_exceptional_entry(item) -
-				!!radix_tree_exceptional_entry(old);
+	int exceptional = !!xa_is_value(item) - !!xa_is_value(old);
 	int count = calculate_count(root, node, slot, item, old);
 
 	/*
@@ -1992,7 +1989,7 @@ static bool __radix_tree_delete(struct radix_tree_root *root,
 				struct radix_tree_node *node, void __rcu **slot)
 {
 	void *old = rcu_dereference_raw(*slot);
-	int exceptional = radix_tree_exceptional_entry(old) ? -1 : 0;
+	int exceptional = xa_is_value(old) ? -1 : 0;
 	unsigned offset = get_slot_offset(node, slot);
 	int tag;
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 52517f28e6f4..4de14e75c4ec 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -127,7 +127,7 @@ static int page_cache_tree_insert(struct address_space *mapping,
 
 		p = radix_tree_deref_slot_protected(slot,
 						    &mapping->i_pages.xa_lock);
-		if (!radix_tree_exceptional_entry(p))
+		if (!xa_is_value(p))
 			return -EEXIST;
 
 		mapping->nrexceptional--;
@@ -336,7 +336,7 @@ page_cache_tree_delete_batch(struct address_space *mapping,
 			break;
 		page = radix_tree_deref_slot_protected(slot,
 						       &mapping->i_pages.xa_lock);
-		if (radix_tree_exceptional_entry(page))
+		if (xa_is_value(page))
 			continue;
 		if (!tail_pages) {
 			/*
@@ -1355,7 +1355,7 @@ pgoff_t page_cache_next_hole(struct address_space *mapping,
 		struct page *page;
 
 		page = radix_tree_lookup(&mapping->i_pages, index);
-		if (!page || radix_tree_exceptional_entry(page))
+		if (!page || xa_is_value(page))
 			break;
 		index++;
 		if (index == 0)
@@ -1396,7 +1396,7 @@ pgoff_t page_cache_prev_hole(struct address_space *mapping,
 		struct page *page;
 
 		page = radix_tree_lookup(&mapping->i_pages, index);
-		if (!page || radix_tree_exceptional_entry(page))
+		if (!page || xa_is_value(page))
 			break;
 		index--;
 		if (index == ULONG_MAX)
@@ -1539,7 +1539,7 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
 
 repeat:
 	page = find_get_entry(mapping, offset);
-	if (radix_tree_exceptional_entry(page))
+	if (xa_is_value(page))
 		page = NULL;
 	if (!page)
 		goto no_page;
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index a31d740e6cd1..4820e4adf853 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1369,7 +1369,7 @@ static void collapse_shmem(struct mm_struct *mm,
 
 		page = radix_tree_deref_slot_protected(slot,
 				&mapping->i_pages.xa_lock);
-		if (radix_tree_exceptional_entry(page) || !PageUptodate(page)) {
+		if (xa_is_value(page) || !PageUptodate(page)) {
 			xa_unlock_irq(&mapping->i_pages);
 			/* swap in or instantiate fallocated page */
 			if (shmem_getpage(mapping->host, index, &page,
diff --git a/mm/madvise.c b/mm/madvise.c
index 972a9eaa898b..9d802566c494 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -251,7 +251,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma,
 		index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
 
 		page = find_get_entry(mapping, index);
-		if (!radix_tree_exceptional_entry(page)) {
+		if (!xa_is_value(page)) {
 			if (page)
 				put_page(page);
 			continue;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e79cb59552d9..29d9d1a69b36 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4750,7 +4750,7 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
 	/* shmem/tmpfs may report page out on swap: account for that too. */
 	if (shmem_mapping(mapping)) {
 		page = find_get_entry(mapping, pgoff);
-		if (radix_tree_exceptional_entry(page)) {
+		if (xa_is_value(page)) {
 			swp_entry_t swp = radix_to_swp_entry(page);
 			if (do_memsw_account())
 				*entry = swp;
diff --git a/mm/mincore.c b/mm/mincore.c
index fc37afe226e6..4985965aa20a 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -66,7 +66,7 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
 		 * shmem/tmpfs may return swap: account for swapcache
 		 * page too.
 		 */
-		if (radix_tree_exceptional_entry(page)) {
+		if (xa_is_value(page)) {
 			swp_entry_t swp = radix_to_swp_entry(page);
 			page = find_get_page(swap_address_space(swp),
 					     swp_offset(swp));
diff --git a/mm/readahead.c b/mm/readahead.c
index 4e630143a0ba..de657077d41d 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -179,7 +179,7 @@ unsigned int __do_page_cache_readahead(struct address_space *mapping,
 		rcu_read_lock();
 		page = radix_tree_lookup(&mapping->i_pages, page_offset);
 		rcu_read_unlock();
-		if (page && !radix_tree_exceptional_entry(page)) {
+		if (page && !xa_is_value(page)) {
 			/*
 			 * Page already present?  Kick off the current batch of
 			 * contiguous pages before continuing with the next
diff --git a/mm/shmem.c b/mm/shmem.c
index 446942677cd4..c1062760fe41 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -709,7 +709,7 @@ unsigned long shmem_partial_swap_usage(struct address_space *mapping,
 			continue;
 		}
 
-		if (radix_tree_exceptional_entry(page))
+		if (xa_is_value(page))
 			swapped++;
 
 		if (need_resched()) {
@@ -824,7 +824,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			if (index >= end)
 				break;
 
-			if (radix_tree_exceptional_entry(page)) {
+			if (xa_is_value(page)) {
 				if (unfalloc)
 					continue;
 				nr_swaps_freed += !shmem_free_swap(mapping,
@@ -921,7 +921,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			if (index >= end)
 				break;
 
-			if (radix_tree_exceptional_entry(page)) {
+			if (xa_is_value(page)) {
 				if (unfalloc)
 					continue;
 				if (shmem_free_swap(mapping, index, page)) {
@@ -1643,7 +1643,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 repeat:
 	swap.val = 0;
 	page = find_lock_entry(mapping, index);
-	if (radix_tree_exceptional_entry(page)) {
+	if (xa_is_value(page)) {
 		swap = radix_to_swp_entry(page);
 		page = NULL;
 	}
@@ -2578,7 +2578,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
 				index = indices[i];
 			}
 			page = pvec.pages[i];
-			if (page && !radix_tree_exceptional_entry(page)) {
+			if (page && !xa_is_value(page)) {
 				if (!PageUptodate(page))
 					page = NULL;
 			}
diff --git a/mm/swap.c b/mm/swap.c
index 26fc9b5f1b6c..4c5c7fcc6e46 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -965,7 +965,7 @@ void pagevec_remove_exceptionals(struct pagevec *pvec)
 
 	for (i = 0, j = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
-		if (!radix_tree_exceptional_entry(page))
+		if (!xa_is_value(page))
 			pvec->pages[j++] = page;
 	}
 	pvec->nr = j;
diff --git a/mm/truncate.c b/mm/truncate.c
index 1d2fb2dca96f..ed778555c9f3 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -70,7 +70,7 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping,
 		return;
 
 	for (j = 0; j < pagevec_count(pvec); j++)
-		if (radix_tree_exceptional_entry(pvec->pages[j]))
+		if (xa_is_value(pvec->pages[j]))
 			break;
 
 	if (j == pagevec_count(pvec))
@@ -85,7 +85,7 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping,
 		struct page *page = pvec->pages[i];
 		pgoff_t index = indices[i];
 
-		if (!radix_tree_exceptional_entry(page)) {
+		if (!xa_is_value(page)) {
 			pvec->pages[j++] = page;
 			continue;
 		}
@@ -347,7 +347,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 			if (index >= end)
 				break;
 
-			if (radix_tree_exceptional_entry(page))
+			if (xa_is_value(page))
 				continue;
 
 			if (!trylock_page(page))
@@ -442,7 +442,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 				break;
 			}
 
-			if (radix_tree_exceptional_entry(page))
+			if (xa_is_value(page))
 				continue;
 
 			lock_page(page);
@@ -561,7 +561,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 			if (index > end)
 				break;
 
-			if (radix_tree_exceptional_entry(page)) {
+			if (xa_is_value(page)) {
 				invalidate_exceptional_entry(mapping, index,
 							     page);
 				continue;
@@ -692,7 +692,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 			if (index > end)
 				break;
 
-			if (radix_tree_exceptional_entry(page)) {
+			if (xa_is_value(page)) {
 				if (!invalidate_exceptional_entry2(mapping,
 								   index, page))
 					ret = -EBUSY;
diff --git a/mm/workingset.c b/mm/workingset.c
index 4516dd790129..bb109b3afac2 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -155,8 +155,8 @@
  * refault distance will immediately activate the refaulting page.
  */
 
-#define EVICTION_SHIFT	(RADIX_TREE_EXCEPTIONAL_ENTRY + \
-			 NODES_SHIFT +	\
+#define EVICTION_SHIFT	((BITS_PER_LONG - BITS_PER_XA_VALUE) +	\
+			 NODES_SHIFT +				\
 			 MEM_CGROUP_ID_SHIFT)
 #define EVICTION_MASK	(~0UL >> EVICTION_SHIFT)
 
@@ -173,20 +173,19 @@ static unsigned int bucket_order __read_mostly;
 static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction)
 {
 	eviction >>= bucket_order;
+	eviction &= EVICTION_MASK;
 	eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid;
 	eviction = (eviction << NODES_SHIFT) | pgdat->node_id;
-	eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT);
 
-	return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY);
+	return xa_mk_value(eviction);
 }
 
 static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
 			  unsigned long *evictionp)
 {
-	unsigned long entry = (unsigned long)shadow;
+	unsigned long entry = xa_to_value(shadow);
 	int memcgid, nid;
 
-	entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT;
 	nid = entry & ((1UL << NODES_SHIFT) - 1);
 	entry >>= NODES_SHIFT;
 	memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1);
@@ -453,7 +452,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 		goto out_invalid;
 	for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) {
 		if (node->slots[i]) {
-			if (WARN_ON_ONCE(!radix_tree_exceptional_entry(node->slots[i])))
+			if (WARN_ON_ONCE(!xa_is_value(node->slots[i])))
 				goto out_invalid;
 			if (WARN_ON_ONCE(!node->exceptional))
 				goto out_invalid;
diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index f620c831a4b5..a5a4494922a6 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -19,7 +19,7 @@
 
 #include "test.h"
 
-#define DUMMY_PTR	((void *)0x12)
+#define DUMMY_PTR	((void *)0x10)
 
 int item_idr_free(int id, void *p, void *data)
 {
@@ -411,11 +411,11 @@ void ida_check_conv_user(void)
 		int id = ida_alloc(&ida, GFP_NOWAIT);
 		if (id == -ENOMEM) {
 			IDA_BUG_ON(&ida, (i % IDA_BITMAP_BITS) !=
-					BITS_PER_LONG - 2);
+					BITS_PER_XA_VALUE);
 			id = ida_alloc(&ida, GFP_KERNEL);
 		} else {
 			IDA_BUG_ON(&ida, (i % IDA_BITMAP_BITS) ==
-					BITS_PER_LONG - 2);
+					BITS_PER_XA_VALUE);
 		}
 		IDA_BUG_ON(&ida, id != i);
 	}
diff --git a/tools/testing/radix-tree/linux/radix-tree.h b/tools/testing/radix-tree/linux/radix-tree.h
index 24f13d27a8da..d1635a5bef02 100644
--- a/tools/testing/radix-tree/linux/radix-tree.h
+++ b/tools/testing/radix-tree/linux/radix-tree.h
@@ -2,7 +2,6 @@
 #ifndef _TEST_RADIX_TREE_H
 #define _TEST_RADIX_TREE_H
 
-#include "generated/map-shift.h"
 #include "../../../../include/linux/radix-tree.h"
 
 extern int kmalloc_verbose;
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 7bf405638b0b..2b4f4dba1882 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -39,12 +39,11 @@ static void __multiorder_tag_test(int index, int order)
 
 	/*
 	 * Verify we get collisions for covered indices.  We try and fail to
-	 * insert an exceptional entry so we don't leak memory via
+	 * insert a value entry so we don't leak memory via
 	 * item_insert_order().
 	 */
 	for_each_index(i, base, order) {
-		err = __radix_tree_insert(&tree, i, order,
-				(void *)(0xA0 | RADIX_TREE_EXCEPTIONAL_ENTRY));
+		err = __radix_tree_insert(&tree, i, order, xa_mk_value(0xA0));
 		assert(err == -EEXIST);
 	}
 
@@ -380,8 +379,8 @@ static void multiorder_join1(unsigned long index,
 }
 
 /*
- * Check that the accounting of exceptional entries is handled correctly
- * by joining an exceptional entry to a normal pointer.
+ * Check that the accounting of value entries is handled correctly
+ * by joining a value entry to a normal pointer.
  */
 static void multiorder_join2(unsigned order1, unsigned order2)
 {
@@ -391,9 +390,9 @@ static void multiorder_join2(unsigned order1, unsigned order2)
 	void *item2;
 
 	item_insert_order(&tree, 0, order2);
-	radix_tree_insert(&tree, 1 << order2, (void *)0x12UL);
+	radix_tree_insert(&tree, 1 << order2, xa_mk_value(5));
 	item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL);
-	assert(item2 == (void *)0x12UL);
+	assert(item2 == xa_mk_value(5));
 	assert(node->exceptional == 1);
 
 	item2 = radix_tree_lookup(&tree, 0);
@@ -407,7 +406,7 @@ static void multiorder_join2(unsigned order1, unsigned order2)
 }
 
 /*
- * This test revealed an accounting bug for exceptional entries at one point.
+ * This test revealed an accounting bug for value entries at one point.
  * Nodes were being freed back into the pool with an elevated exception count
  * by radix_tree_join() and then radix_tree_split() was failing to zero the
  * count of exceptional entries.
@@ -421,16 +420,16 @@ static void multiorder_join3(unsigned int order)
 	unsigned long i;
 
 	for (i = 0; i < (1 << order); i++) {
-		radix_tree_insert(&tree, i, (void *)0x12UL);
+		radix_tree_insert(&tree, i, xa_mk_value(5));
 	}
 
-	radix_tree_join(&tree, 0, order, (void *)0x16UL);
+	radix_tree_join(&tree, 0, order, xa_mk_value(7));
 	rcu_barrier();
 
 	radix_tree_split(&tree, 0, 0);
 
 	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-		radix_tree_iter_replace(&tree, &iter, slot, (void *)0x12UL);
+		radix_tree_iter_replace(&tree, &iter, slot, xa_mk_value(5));
 	}
 
 	__radix_tree_lookup(&tree, 0, &node, NULL);
@@ -517,10 +516,10 @@ static void __multiorder_split2(int old_order, int new_order)
 	struct radix_tree_node *node;
 	void *item;
 
-	__radix_tree_insert(&tree, 0, old_order, (void *)0x12);
+	__radix_tree_insert(&tree, 0, old_order, xa_mk_value(5));
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item == (void *)0x12);
+	assert(item == xa_mk_value(5));
 	assert(node->exceptional > 0);
 
 	radix_tree_split(&tree, 0, new_order);
@@ -530,7 +529,7 @@ static void __multiorder_split2(int old_order, int new_order)
 	}
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item != (void *)0x12);
+	assert(item != xa_mk_value(5));
 	assert(node->exceptional == 0);
 
 	item_kill_tree(&tree);
@@ -544,40 +543,40 @@ static void __multiorder_split3(int old_order, int new_order)
 	struct radix_tree_node *node;
 	void *item;
 
-	__radix_tree_insert(&tree, 0, old_order, (void *)0x12);
+	__radix_tree_insert(&tree, 0, old_order, xa_mk_value(5));
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item == (void *)0x12);
+	assert(item == xa_mk_value(5));
 	assert(node->exceptional > 0);
 
 	radix_tree_split(&tree, 0, new_order);
 	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-		radix_tree_iter_replace(&tree, &iter, slot, (void *)0x16);
+		radix_tree_iter_replace(&tree, &iter, slot, xa_mk_value(7));
 	}
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item == (void *)0x16);
+	assert(item == xa_mk_value(7));
 	assert(node->exceptional > 0);
 
 	item_kill_tree(&tree);
 
-	__radix_tree_insert(&tree, 0, old_order, (void *)0x12);
+	__radix_tree_insert(&tree, 0, old_order, xa_mk_value(5));
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item == (void *)0x12);
+	assert(item == xa_mk_value(5));
 	assert(node->exceptional > 0);
 
 	radix_tree_split(&tree, 0, new_order);
 	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
 		if (iter.index == (1 << new_order))
 			radix_tree_iter_replace(&tree, &iter, slot,
-						(void *)0x16);
+						xa_mk_value(7));
 		else
 			radix_tree_iter_replace(&tree, &iter, slot, NULL);
 	}
 
 	item = __radix_tree_lookup(&tree, 1 << new_order, &node, NULL);
-	assert(item == (void *)0x16);
+	assert(item == xa_mk_value(7));
 	assert(node->count == node->exceptional);
 	do {
 		node = node->parent;
@@ -610,13 +609,13 @@ static void multiorder_account(void)
 
 	item_insert_order(&tree, 0, 5);
 
-	__radix_tree_insert(&tree, 1 << 5, 5, (void *)0x12);
+	__radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5));
 	__radix_tree_lookup(&tree, 0, &node, NULL);
 	assert(node->count == node->exceptional * 2);
 	radix_tree_delete(&tree, 1 << 5);
 	assert(node->exceptional == 0);
 
-	__radix_tree_insert(&tree, 1 << 5, 5, (void *)0x12);
+	__radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5));
 	__radix_tree_lookup(&tree, 1 << 5, &node, &slot);
 	assert(node->count == node->exceptional * 2);
 	__radix_tree_replace(&tree, node, slot, NULL, NULL);
diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index def6015570b2..62de66c314b7 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -295,7 +295,7 @@ void item_kill_tree(struct radix_tree_root *root)
 	int nfound;
 
 	radix_tree_for_each_slot(slot, root, &iter, 0) {
-		if (radix_tree_exceptional_entry(*slot))
+		if (xa_is_value(*slot))
 			radix_tree_delete(root, iter.index);
 	}
 
-- 
cgit 


From 02c02bf12c5d838603eed44195d3e91f094e2ab2 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Fri, 3 Nov 2017 23:09:45 -0400
Subject: xarray: Change definition of sibling entries

Instead of storing a pointer to the slot containing the canonical entry,
store the offset of the slot.  Produces slightly more efficient code
(~300 bytes) and simplifies the implementation.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
Reviewed-by: Josef Bacik <jbacik@fb.com>
---
 include/linux/radix-tree.h                    |  5 +-
 include/linux/xarray.h                        | 92 +++++++++++++++++++++++++++
 lib/Kconfig                                   |  7 ++
 lib/radix-tree.c                              | 64 ++++++-------------
 tools/testing/radix-tree/Makefile             |  2 +-
 tools/testing/radix-tree/generated/autoconf.h |  1 +
 6 files changed, 121 insertions(+), 50 deletions(-)

(limited to 'tools/testing')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index e9e76ab4fbbf..60f3d8eb2cb7 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -59,10 +59,7 @@ static inline bool radix_tree_is_internal_node(void *ptr)
 
 #define RADIX_TREE_MAX_TAGS 3
 
-#ifndef RADIX_TREE_MAP_SHIFT
-#define RADIX_TREE_MAP_SHIFT	(CONFIG_BASE_SMALL ? 4 : 6)
-#endif
-
+#define RADIX_TREE_MAP_SHIFT	XA_CHUNK_SHIFT
 #define RADIX_TREE_MAP_SIZE	(1UL << RADIX_TREE_MAP_SHIFT)
 #define RADIX_TREE_MAP_MASK	(RADIX_TREE_MAP_SIZE-1)
 
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 5c8acfc4ff55..4d1cd7a083e8 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -22,6 +22,12 @@
  * x1: Value entry or tagged pointer
  *
  * Attempting to store internal entries in the XArray is a bug.
+ *
+ * Most internal entries are pointers to the next node in the tree.
+ * The following internal entries have a special meaning:
+ *
+ * 0-62: Sibling entries
+ * 256: Retry entry
  */
 
 #define BITS_PER_XA_VALUE	(BITS_PER_LONG - 1)
@@ -111,6 +117,42 @@ static inline unsigned int xa_pointer_tag(void *entry)
 	return (unsigned long)entry & 3UL;
 }
 
+/*
+ * xa_mk_internal() - Create an internal entry.
+ * @v: Value to turn into an internal entry.
+ *
+ * Context: Any context.
+ * Return: An XArray internal entry corresponding to this value.
+ */
+static inline void *xa_mk_internal(unsigned long v)
+{
+	return (void *)((v << 2) | 2);
+}
+
+/*
+ * xa_to_internal() - Extract the value from an internal entry.
+ * @entry: XArray entry.
+ *
+ * Context: Any context.
+ * Return: The value which was stored in the internal entry.
+ */
+static inline unsigned long xa_to_internal(const void *entry)
+{
+	return (unsigned long)entry >> 2;
+}
+
+/*
+ * xa_is_internal() - Is the entry an internal entry?
+ * @entry: XArray entry.
+ *
+ * Context: Any context.
+ * Return: %true if the entry is an internal entry.
+ */
+static inline bool xa_is_internal(const void *entry)
+{
+	return ((unsigned long)entry & 3) == 2;
+}
+
 #define xa_trylock(xa)		spin_trylock(&(xa)->xa_lock)
 #define xa_lock(xa)		spin_lock(&(xa)->xa_lock)
 #define xa_unlock(xa)		spin_unlock(&(xa)->xa_lock)
@@ -123,4 +165,54 @@ static inline unsigned int xa_pointer_tag(void *entry)
 #define xa_unlock_irqrestore(xa, flags) \
 				spin_unlock_irqrestore(&(xa)->xa_lock, flags)
 
+/* Everything below here is the Advanced API.  Proceed with caution. */
+
+/*
+ * The xarray is constructed out of a set of 'chunks' of pointers.  Choosing
+ * the best chunk size requires some tradeoffs.  A power of two recommends
+ * itself so that we can walk the tree based purely on shifts and masks.
+ * Generally, the larger the better; as the number of slots per level of the
+ * tree increases, the less tall the tree needs to be.  But that needs to be
+ * balanced against the memory consumption of each node.  On a 64-bit system,
+ * xa_node is currently 576 bytes, and we get 7 of them per 4kB page.  If we
+ * doubled the number of slots per node, we'd get only 3 nodes per 4kB page.
+ */
+#ifndef XA_CHUNK_SHIFT
+#define XA_CHUNK_SHIFT		(CONFIG_BASE_SMALL ? 4 : 6)
+#endif
+#define XA_CHUNK_SIZE		(1UL << XA_CHUNK_SHIFT)
+#define XA_CHUNK_MASK		(XA_CHUNK_SIZE - 1)
+
+/* Private */
+static inline bool xa_is_node(const void *entry)
+{
+	return xa_is_internal(entry) && (unsigned long)entry > 4096;
+}
+
+/* Private */
+static inline void *xa_mk_sibling(unsigned int offset)
+{
+	return xa_mk_internal(offset);
+}
+
+/* Private */
+static inline unsigned long xa_to_sibling(const void *entry)
+{
+	return xa_to_internal(entry);
+}
+
+/**
+ * xa_is_sibling() - Is the entry a sibling entry?
+ * @entry: Entry retrieved from the XArray
+ *
+ * Return: %true if the entry is a sibling entry.
+ */
+static inline bool xa_is_sibling(const void *entry)
+{
+	return IS_ENABLED(CONFIG_XARRAY_MULTI) && xa_is_internal(entry) &&
+		(entry < xa_mk_sibling(XA_CHUNK_SIZE - 1));
+}
+
+#define XA_RETRY_ENTRY		xa_mk_internal(256)
+
 #endif /* _LINUX_XARRAY_H */
diff --git a/lib/Kconfig b/lib/Kconfig
index a3928d4438b5..40bfa6ccd294 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -399,8 +399,15 @@ config INTERVAL_TREE
 
 	  for more information.
 
+config XARRAY_MULTI
+	bool
+	help
+	  Support entries which occupy multiple consecutive indices in the
+	  XArray.
+
 config RADIX_TREE_MULTIORDER
 	bool
+	select XARRAY_MULTI
 
 config ASSOCIATIVE_ARRAY
 	bool
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index b6c0e7f3a894..59b28111eabc 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -38,6 +38,7 @@
 #include <linux/rcupdate.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/xarray.h>
 
 
 /* Number of nodes in fully populated tree of given height */
@@ -98,24 +99,7 @@ static inline void *node_to_entry(void *ptr)
 	return (void *)((unsigned long)ptr | RADIX_TREE_INTERNAL_NODE);
 }
 
-#define RADIX_TREE_RETRY	node_to_entry(NULL)
-
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-/* Sibling slots point directly to another slot in the same node */
-static inline
-bool is_sibling_entry(const struct radix_tree_node *parent, void *node)
-{
-	void __rcu **ptr = node;
-	return (parent->slots <= ptr) &&
-			(ptr < parent->slots + RADIX_TREE_MAP_SIZE);
-}
-#else
-static inline
-bool is_sibling_entry(const struct radix_tree_node *parent, void *node)
-{
-	return false;
-}
-#endif
+#define RADIX_TREE_RETRY	XA_RETRY_ENTRY
 
 static inline unsigned long
 get_slot_offset(const struct radix_tree_node *parent, void __rcu **slot)
@@ -129,16 +113,10 @@ static unsigned int radix_tree_descend(const struct radix_tree_node *parent,
 	unsigned int offset = (index >> parent->shift) & RADIX_TREE_MAP_MASK;
 	void __rcu **entry = rcu_dereference_raw(parent->slots[offset]);
 
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-	if (radix_tree_is_internal_node(entry)) {
-		if (is_sibling_entry(parent, entry)) {
-			void __rcu **sibentry;
-			sibentry = (void __rcu **) entry_to_node(entry);
-			offset = get_slot_offset(parent, sibentry);
-			entry = rcu_dereference_raw(*sibentry);
-		}
+	if (xa_is_sibling(entry)) {
+		offset = xa_to_sibling(entry);
+		entry = rcu_dereference_raw(parent->slots[offset]);
 	}
-#endif
 
 	*nodep = (void *)entry;
 	return offset;
@@ -300,10 +278,10 @@ static void dump_node(struct radix_tree_node *node, unsigned long index)
 		} else if (!radix_tree_is_internal_node(entry)) {
 			pr_debug("radix entry %p offset %ld indices %lu-%lu parent %p\n",
 					entry, i, first, last, node);
-		} else if (is_sibling_entry(node, entry)) {
+		} else if (xa_is_sibling(entry)) {
 			pr_debug("radix sblng %p offset %ld indices %lu-%lu parent %p val %p\n",
 					entry, i, first, last, node,
-					*(void **)entry_to_node(entry));
+					node->slots[xa_to_sibling(entry)]);
 		} else {
 			dump_node(entry_to_node(entry), first);
 		}
@@ -881,8 +859,7 @@ static void radix_tree_free_nodes(struct radix_tree_node *node)
 
 	for (;;) {
 		void *entry = rcu_dereference_raw(child->slots[offset]);
-		if (radix_tree_is_internal_node(entry) && child->shift &&
-				!is_sibling_entry(child, entry)) {
+		if (xa_is_node(entry) && child->shift) {
 			child = entry_to_node(entry);
 			offset = 0;
 			continue;
@@ -904,7 +881,7 @@ static void radix_tree_free_nodes(struct radix_tree_node *node)
 static inline int insert_entries(struct radix_tree_node *node,
 		void __rcu **slot, void *item, unsigned order, bool replace)
 {
-	struct radix_tree_node *child;
+	void *sibling;
 	unsigned i, n, tag, offset, tags = 0;
 
 	if (node) {
@@ -922,7 +899,7 @@ static inline int insert_entries(struct radix_tree_node *node,
 		offset = offset & ~(n - 1);
 		slot = &node->slots[offset];
 	}
-	child = node_to_entry(slot);
+	sibling = xa_mk_sibling(offset);
 
 	for (i = 0; i < n; i++) {
 		if (slot[i]) {
@@ -939,7 +916,7 @@ static inline int insert_entries(struct radix_tree_node *node,
 	for (i = 0; i < n; i++) {
 		struct radix_tree_node *old = rcu_dereference_raw(slot[i]);
 		if (i) {
-			rcu_assign_pointer(slot[i], child);
+			rcu_assign_pointer(slot[i], sibling);
 			for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
 				if (tags & (1 << tag))
 					tag_clear(node, tag, offset + i);
@@ -949,9 +926,7 @@ static inline int insert_entries(struct radix_tree_node *node,
 				if (tags & (1 << tag))
 					tag_set(node, tag, offset);
 		}
-		if (radix_tree_is_internal_node(old) &&
-					!is_sibling_entry(node, old) &&
-					(old != RADIX_TREE_RETRY))
+		if (xa_is_node(old))
 			radix_tree_free_nodes(old);
 		if (xa_is_value(old))
 			node->exceptional--;
@@ -1112,10 +1087,10 @@ static inline void replace_sibling_entries(struct radix_tree_node *node,
 				void __rcu **slot, int count, int exceptional)
 {
 #ifdef CONFIG_RADIX_TREE_MULTIORDER
-	void *ptr = node_to_entry(slot);
-	unsigned offset = get_slot_offset(node, slot) + 1;
+	unsigned offset = get_slot_offset(node, slot);
+	void *ptr = xa_mk_sibling(offset);
 
-	while (offset < RADIX_TREE_MAP_SIZE) {
+	while (++offset < RADIX_TREE_MAP_SIZE) {
 		if (rcu_dereference_raw(node->slots[offset]) != ptr)
 			break;
 		if (count < 0) {
@@ -1123,7 +1098,6 @@ static inline void replace_sibling_entries(struct radix_tree_node *node,
 			node->count--;
 		}
 		node->exceptional += exceptional;
-		offset++;
 	}
 #endif
 }
@@ -1319,8 +1293,7 @@ int radix_tree_split(struct radix_tree_root *root, unsigned long index,
 			tags |= 1 << tag;
 
 	for (end = offset + 1; end < RADIX_TREE_MAP_SIZE; end++) {
-		if (!is_sibling_entry(parent,
-				rcu_dereference_raw(parent->slots[end])))
+		if (!xa_is_sibling(rcu_dereference_raw(parent->slots[end])))
 			break;
 		for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
 			if (tags & (1 << tag))
@@ -1618,7 +1591,7 @@ static void __rcu **skip_siblings(struct radix_tree_node **nodep,
 {
 	while (iter->index < iter->next_index) {
 		*nodep = rcu_dereference_raw(*slot);
-		if (*nodep && !is_sibling_entry(iter->node, *nodep))
+		if (*nodep && !xa_is_sibling(*nodep))
 			return slot;
 		slot++;
 		iter->index = __radix_tree_iter_add(iter, 1);
@@ -1769,7 +1742,7 @@ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root,
 				while (++offset	< RADIX_TREE_MAP_SIZE) {
 					void *slot = rcu_dereference_raw(
 							node->slots[offset]);
-					if (is_sibling_entry(node, slot))
+					if (xa_is_sibling(slot))
 						continue;
 					if (slot)
 						break;
@@ -2283,6 +2256,7 @@ void __init radix_tree_init(void)
 
 	BUILD_BUG_ON(RADIX_TREE_MAX_TAGS + __GFP_BITS_SHIFT > 32);
 	BUILD_BUG_ON(ROOT_IS_IDR & ~GFP_ZONEMASK);
+	BUILD_BUG_ON(XA_CHUNK_SIZE > 255);
 	radix_tree_node_cachep = kmem_cache_create("radix_tree_node",
 			sizeof(struct radix_tree_node), 0,
 			SLAB_PANIC | SLAB_RECLAIM_ACCOUNT,
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index 37baecc3766f..12adcf9ffe86 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -46,6 +46,6 @@ idr.c: ../../../lib/idr.c
 
 generated/map-shift.h:
 	@if ! grep -qws $(SHIFT) generated/map-shift.h; then		\
-		echo "#define RADIX_TREE_MAP_SHIFT $(SHIFT)" >		\
+		echo "#define XA_CHUNK_SHIFT $(SHIFT)" >		\
 				generated/map-shift.h;			\
 	fi
diff --git a/tools/testing/radix-tree/generated/autoconf.h b/tools/testing/radix-tree/generated/autoconf.h
index cf88dc5b8832..ca8e03ad19ac 100644
--- a/tools/testing/radix-tree/generated/autoconf.h
+++ b/tools/testing/radix-tree/generated/autoconf.h
@@ -1 +1,2 @@
 #define CONFIG_RADIX_TREE_MULTIORDER 1
+#define CONFIG_XARRAY_MULTI 1
-- 
cgit 


From a3c6054f81e2c436d6b53b8060df996fec0cbfdb Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Fri, 28 Sep 2018 14:45:53 +0000
Subject: selftests/bpf: add verifier per-cpu cgroup storage tests

This commits adds verifier tests covering per-cpu cgroup storage
functionality. There are 6 new tests, which are exactly the same
as for shared cgroup storage, but do use per-cpu cgroup storage
map.

Expected output:
  $ ./test_verifier
  #0/u add+sub+mul OK
  #0/p add+sub+mul OK
  ...
  #286/p invalid cgroup storage access 6 OK
  #287/p valid per-cpu cgroup storage access OK
  #288/p invalid per-cpu cgroup storage access 1 OK
  #289/p invalid per-cpu cgroup storage access 2 OK
  #290/p invalid per-cpu cgroup storage access 3 OK
  #291/p invalid per-cpu cgroup storage access 4 OK
  #292/p invalid per-cpu cgroup storage access 5 OK
  #293/p invalid per-cpu cgroup storage access 6 OK
  #294/p multiple registers share map_lookup_elem result OK
  ...
  #662/p mov64 src == dst OK
  #663/p mov64 src != dst OK
  Summary: 914 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_verifier.c | 139 ++++++++++++++++++++++++++--
 1 file changed, 133 insertions(+), 6 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 67c412d19c09..c7d25f23baf9 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -68,6 +68,7 @@ struct bpf_test {
 	int fixup_prog2[MAX_FIXUPS];
 	int fixup_map_in_map[MAX_FIXUPS];
 	int fixup_cgroup_storage[MAX_FIXUPS];
+	int fixup_percpu_cgroup_storage[MAX_FIXUPS];
 	const char *errstr;
 	const char *errstr_unpriv;
 	uint32_t retval;
@@ -4676,7 +4677,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
 	},
 	{
-		"invalid per-cgroup storage access 3",
+		"invalid cgroup storage access 3",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_2, 0),
 			BPF_LD_MAP_FD(BPF_REG_1, 0),
@@ -4743,6 +4744,121 @@ static struct bpf_test tests[] = {
 		.errstr = "get_local_storage() doesn't support non-zero flags",
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
 	},
+	{
+		"valid per-cpu cgroup storage access",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_percpu_cgroup_storage = { 1 },
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid per-cpu cgroup storage access 1",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 1 },
+		.result = REJECT,
+		.errstr = "cannot pass map_type 1 into func bpf_get_local_storage",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid per-cpu cgroup storage access 2",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "fd 1 is not pointing to valid bpf_map",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid per-cpu cgroup storage access 3",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 256),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_percpu_cgroup_storage = { 1 },
+		.result = REJECT,
+		.errstr = "invalid access to map value, value_size=64 off=256 size=4",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid per-cpu cgroup storage access 4",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, -2),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_cgroup_storage = { 1 },
+		.result = REJECT,
+		.errstr = "invalid access to map value, value_size=64 off=-2 size=4",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid per-cpu cgroup storage access 5",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 7),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_percpu_cgroup_storage = { 1 },
+		.result = REJECT,
+		.errstr = "get_local_storage() doesn't support non-zero flags",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid per-cpu cgroup storage access 6",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_percpu_cgroup_storage = { 1 },
+		.result = REJECT,
+		.errstr = "get_local_storage() doesn't support non-zero flags",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
 	{
 		"multiple registers share map_lookup_elem result",
 		.insns = {
@@ -12615,15 +12731,17 @@ static int create_map_in_map(void)
 	return outer_map_fd;
 }
 
-static int create_cgroup_storage(void)
+static int create_cgroup_storage(bool percpu)
 {
+	enum bpf_map_type type = percpu ? BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE :
+		BPF_MAP_TYPE_CGROUP_STORAGE;
 	int fd;
 
-	fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE,
-			    sizeof(struct bpf_cgroup_storage_key),
+	fd = bpf_create_map(type, sizeof(struct bpf_cgroup_storage_key),
 			    TEST_DATA_LEN, 0, 0);
 	if (fd < 0)
-		printf("Failed to create array '%s'!\n", strerror(errno));
+		printf("Failed to create cgroup storage '%s'!\n",
+		       strerror(errno));
 
 	return fd;
 }
@@ -12641,6 +12759,7 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
 	int *fixup_prog2 = test->fixup_prog2;
 	int *fixup_map_in_map = test->fixup_map_in_map;
 	int *fixup_cgroup_storage = test->fixup_cgroup_storage;
+	int *fixup_percpu_cgroup_storage = test->fixup_percpu_cgroup_storage;
 
 	if (test->fill_helper)
 		test->fill_helper(test);
@@ -12710,12 +12829,20 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
 	}
 
 	if (*fixup_cgroup_storage) {
-		map_fds[7] = create_cgroup_storage();
+		map_fds[7] = create_cgroup_storage(false);
 		do {
 			prog[*fixup_cgroup_storage].imm = map_fds[7];
 			fixup_cgroup_storage++;
 		} while (*fixup_cgroup_storage);
 	}
+
+	if (*fixup_percpu_cgroup_storage) {
+		map_fds[8] = create_cgroup_storage(true);
+		do {
+			prog[*fixup_percpu_cgroup_storage].imm = map_fds[8];
+			fixup_percpu_cgroup_storage++;
+		} while (*fixup_percpu_cgroup_storage);
+	}
 }
 
 static void do_test_single(struct bpf_test *test, bool unpriv,
-- 
cgit 


From 919646d2a3a90465cf8b30a7616c63005bef7570 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Fri, 28 Sep 2018 14:45:55 +0000
Subject: selftests/bpf: extend the storage test to test per-cpu cgroup storage

This test extends the cgroup storage test to use per-cpu flavor
of the cgroup storage as well.

The test initializes a per-cpu cgroup storage to some non-zero initial
value (1000), and then simple bumps a per-cpu counter each time
the shared counter is atomically incremented. Then it reads all
per-cpu areas from the userspace side, and checks that the sum
of values adds to the expected sum.

Expected output:
  $ ./test_cgroup_storage
  test_cgroup_storage:PASS

Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_cgroup_storage.c | 60 +++++++++++++++++++++--
 1 file changed, 57 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c
index 4e196e3bfecf..f44834155f25 100644
--- a/tools/testing/selftests/bpf/test_cgroup_storage.c
+++ b/tools/testing/selftests/bpf/test_cgroup_storage.c
@@ -4,6 +4,7 @@
 #include <linux/filter.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <sys/sysinfo.h>
 
 #include "bpf_rlimit.h"
 #include "cgroup_helpers.h"
@@ -15,6 +16,14 @@ char bpf_log_buf[BPF_LOG_BUF_SIZE];
 int main(int argc, char **argv)
 {
 	struct bpf_insn prog[] = {
+		BPF_LD_MAP_FD(BPF_REG_1, 0), /* percpu map fd */
+		BPF_MOV64_IMM(BPF_REG_2, 0), /* flags, not used */
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+			     BPF_FUNC_get_local_storage),
+		BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 0x1),
+		BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_3, 0),
+
 		BPF_LD_MAP_FD(BPF_REG_1, 0), /* map fd */
 		BPF_MOV64_IMM(BPF_REG_2, 0), /* flags, not used */
 		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
@@ -28,9 +37,18 @@ int main(int argc, char **argv)
 	};
 	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
 	int error = EXIT_FAILURE;
-	int map_fd, prog_fd, cgroup_fd;
+	int map_fd, percpu_map_fd, prog_fd, cgroup_fd;
 	struct bpf_cgroup_storage_key key;
 	unsigned long long value;
+	unsigned long long *percpu_value;
+	int cpu, nproc;
+
+	nproc = get_nprocs_conf();
+	percpu_value = malloc(sizeof(*percpu_value) * nproc);
+	if (!percpu_value) {
+		printf("Not enough memory for per-cpu area (%d cpus)\n", nproc);
+		goto err;
+	}
 
 	map_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE, sizeof(key),
 				sizeof(value), 0, 0);
@@ -39,7 +57,15 @@ int main(int argc, char **argv)
 		goto out;
 	}
 
-	prog[0].imm = map_fd;
+	percpu_map_fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+				       sizeof(key), sizeof(value), 0, 0);
+	if (percpu_map_fd < 0) {
+		printf("Failed to create map: %s\n", strerror(errno));
+		goto out;
+	}
+
+	prog[0].imm = percpu_map_fd;
+	prog[7].imm = map_fd;
 	prog_fd = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
 				   prog, insns_cnt, "GPL", 0,
 				   bpf_log_buf, BPF_LOG_BUF_SIZE);
@@ -77,7 +103,15 @@ int main(int argc, char **argv)
 	}
 
 	if (bpf_map_lookup_elem(map_fd, &key, &value)) {
-		printf("Failed to lookup cgroup storage\n");
+		printf("Failed to lookup cgroup storage 0\n");
+		goto err;
+	}
+
+	for (cpu = 0; cpu < nproc; cpu++)
+		percpu_value[cpu] = 1000;
+
+	if (bpf_map_update_elem(percpu_map_fd, &key, percpu_value, 0)) {
+		printf("Failed to update the data in the cgroup storage\n");
 		goto err;
 	}
 
@@ -120,11 +154,31 @@ int main(int argc, char **argv)
 		goto err;
 	}
 
+	/* Check the final value of the counter in the percpu local storage */
+
+	for (cpu = 0; cpu < nproc; cpu++)
+		percpu_value[cpu] = 0;
+
+	if (bpf_map_lookup_elem(percpu_map_fd, &key, percpu_value)) {
+		printf("Failed to lookup the per-cpu cgroup storage\n");
+		goto err;
+	}
+
+	value = 0;
+	for (cpu = 0; cpu < nproc; cpu++)
+		value += percpu_value[cpu];
+
+	if (value != nproc * 1000 + 6) {
+		printf("Unexpected data in the per-cpu cgroup storage\n");
+		goto err;
+	}
+
 	error = 0;
 	printf("test_cgroup_storage:PASS\n");
 
 err:
 	cleanup_cgroup_environment();
+	free(percpu_value);
 
 out:
 	return error;
-- 
cgit 


From 371e4fcc9d96ab1c8d72d59ca4ee3537402d1584 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Fri, 28 Sep 2018 14:46:00 +0000
Subject: selftests/bpf: cgroup local storage-based network counters

This commit adds a bpf kselftest, which demonstrates how percpu
and shared cgroup local storage can be used for efficient lookup-free
network accounting.

Cgroup local storage provides generic memory area with a very efficient
lookup free access. To avoid expensive atomic operations for each
packet, per-cpu cgroup local storage is used. Each packet is initially
charged to a per-cpu counter, and only if the counter reaches certain
value (32 in this case), the charge is moved into the global atomic
counter. This allows to amortize atomic operations, keeping reasonable
accuracy.

The test also implements a naive network traffic throttling, mostly to
demonstrate the possibility of bpf cgroup--based network bandwidth
control.

Expected output:
  ./test_netcnt
  test_netcnt:PASS

Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/Makefile        |   6 +-
 tools/testing/selftests/bpf/netcnt_common.h |  24 +++++
 tools/testing/selftests/bpf/netcnt_prog.c   |  71 +++++++++++++
 tools/testing/selftests/bpf/test_netcnt.c   | 158 ++++++++++++++++++++++++++++
 4 files changed, 257 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/netcnt_common.h
 create mode 100644 tools/testing/selftests/bpf/netcnt_prog.c
 create mode 100644 tools/testing/selftests/bpf/test_netcnt.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 059d64a0f897..f802de526f57 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -23,7 +23,8 @@ $(TEST_CUSTOM_PROGS): $(OUTPUT)/%: %.c
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
 	test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
 	test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \
-	test_socket_cookie test_cgroup_storage test_select_reuseport test_section_names
+	test_socket_cookie test_cgroup_storage test_select_reuseport test_section_names \
+	test_netcnt
 
 TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
 	test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o     \
@@ -35,7 +36,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \
 	test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
 	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
-	test_skb_cgroup_id_kern.o bpf_flow.o
+	test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
@@ -72,6 +73,7 @@ $(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
 $(OUTPUT)/test_progs: trace_helpers.c
 $(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
 $(OUTPUT)/test_cgroup_storage: cgroup_helpers.c
+$(OUTPUT)/test_netcnt: cgroup_helpers.c
 
 .PHONY: force
 
diff --git a/tools/testing/selftests/bpf/netcnt_common.h b/tools/testing/selftests/bpf/netcnt_common.h
new file mode 100644
index 000000000000..81084c1c2c23
--- /dev/null
+++ b/tools/testing/selftests/bpf/netcnt_common.h
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef __NETCNT_COMMON_H
+#define __NETCNT_COMMON_H
+
+#include <linux/types.h>
+
+#define MAX_PERCPU_PACKETS 32
+
+struct percpu_net_cnt {
+	__u64 packets;
+	__u64 bytes;
+
+	__u64 prev_ts;
+
+	__u64 prev_packets;
+	__u64 prev_bytes;
+};
+
+struct net_cnt {
+	__u64 packets;
+	__u64 bytes;
+};
+
+#endif
diff --git a/tools/testing/selftests/bpf/netcnt_prog.c b/tools/testing/selftests/bpf/netcnt_prog.c
new file mode 100644
index 000000000000..1198abca1360
--- /dev/null
+++ b/tools/testing/selftests/bpf/netcnt_prog.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <linux/version.h>
+
+#include "bpf_helpers.h"
+#include "netcnt_common.h"
+
+#define MAX_BPS	(3 * 1024 * 1024)
+
+#define REFRESH_TIME_NS	100000000
+#define NS_PER_SEC	1000000000
+
+struct bpf_map_def SEC("maps") percpu_netcnt = {
+	.type = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+	.key_size = sizeof(struct bpf_cgroup_storage_key),
+	.value_size = sizeof(struct percpu_net_cnt),
+};
+
+struct bpf_map_def SEC("maps") netcnt = {
+	.type = BPF_MAP_TYPE_CGROUP_STORAGE,
+	.key_size = sizeof(struct bpf_cgroup_storage_key),
+	.value_size = sizeof(struct net_cnt),
+};
+
+SEC("cgroup/skb")
+int bpf_nextcnt(struct __sk_buff *skb)
+{
+	struct percpu_net_cnt *percpu_cnt;
+	char fmt[] = "%d %llu %llu\n";
+	struct net_cnt *cnt;
+	__u64 ts, dt;
+	int ret;
+
+	cnt = bpf_get_local_storage(&netcnt, 0);
+	percpu_cnt = bpf_get_local_storage(&percpu_netcnt, 0);
+
+	percpu_cnt->packets++;
+	percpu_cnt->bytes += skb->len;
+
+	if (percpu_cnt->packets > MAX_PERCPU_PACKETS) {
+		__sync_fetch_and_add(&cnt->packets,
+				     percpu_cnt->packets);
+		percpu_cnt->packets = 0;
+
+		__sync_fetch_and_add(&cnt->bytes,
+				     percpu_cnt->bytes);
+		percpu_cnt->bytes = 0;
+	}
+
+	ts = bpf_ktime_get_ns();
+	dt = ts - percpu_cnt->prev_ts;
+
+	dt *= MAX_BPS;
+	dt /= NS_PER_SEC;
+
+	if (cnt->bytes + percpu_cnt->bytes - percpu_cnt->prev_bytes < dt)
+		ret = 1;
+	else
+		ret = 0;
+
+	if (dt > REFRESH_TIME_NS) {
+		percpu_cnt->prev_ts = ts;
+		percpu_cnt->prev_packets = cnt->packets;
+		percpu_cnt->prev_bytes = cnt->bytes;
+	}
+
+	return !!ret;
+}
+
+char _license[] SEC("license") = "GPL";
+__u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/tools/testing/selftests/bpf/test_netcnt.c b/tools/testing/selftests/bpf/test_netcnt.c
new file mode 100644
index 000000000000..7887df693399
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_netcnt.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <assert.h>
+#include <sys/sysinfo.h>
+#include <sys/time.h>
+
+#include <linux/bpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "cgroup_helpers.h"
+#include "bpf_rlimit.h"
+#include "netcnt_common.h"
+
+#define BPF_PROG "./netcnt_prog.o"
+#define TEST_CGROUP "/test-network-counters/"
+
+static int bpf_find_map(const char *test, struct bpf_object *obj,
+			const char *name)
+{
+	struct bpf_map *map;
+
+	map = bpf_object__find_map_by_name(obj, name);
+	if (!map) {
+		printf("%s:FAIL:map '%s' not found\n", test, name);
+		return -1;
+	}
+	return bpf_map__fd(map);
+}
+
+int main(int argc, char **argv)
+{
+	struct percpu_net_cnt *percpu_netcnt;
+	struct bpf_cgroup_storage_key key;
+	int map_fd, percpu_map_fd;
+	int error = EXIT_FAILURE;
+	struct net_cnt netcnt;
+	struct bpf_object *obj;
+	int prog_fd, cgroup_fd;
+	unsigned long packets;
+	unsigned long bytes;
+	int cpu, nproc;
+	__u32 prog_cnt;
+
+	nproc = get_nprocs_conf();
+	percpu_netcnt = malloc(sizeof(*percpu_netcnt) * nproc);
+	if (!percpu_netcnt) {
+		printf("Not enough memory for per-cpu area (%d cpus)\n", nproc);
+		goto err;
+	}
+
+	if (bpf_prog_load(BPF_PROG, BPF_PROG_TYPE_CGROUP_SKB,
+			  &obj, &prog_fd)) {
+		printf("Failed to load bpf program\n");
+		goto out;
+	}
+
+	if (setup_cgroup_environment()) {
+		printf("Failed to load bpf program\n");
+		goto err;
+	}
+
+	/* Create a cgroup, get fd, and join it */
+	cgroup_fd = create_and_get_cgroup(TEST_CGROUP);
+	if (!cgroup_fd) {
+		printf("Failed to create test cgroup\n");
+		goto err;
+	}
+
+	if (join_cgroup(TEST_CGROUP)) {
+		printf("Failed to join cgroup\n");
+		goto err;
+	}
+
+	/* Attach bpf program */
+	if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0)) {
+		printf("Failed to attach bpf program");
+		goto err;
+	}
+
+	assert(system("ping localhost -6 -c 10000 -f -q > /dev/null") == 0);
+
+	if (bpf_prog_query(cgroup_fd, BPF_CGROUP_INET_EGRESS, 0, NULL, NULL,
+			   &prog_cnt)) {
+		printf("Failed to query attached programs");
+		goto err;
+	}
+
+	map_fd = bpf_find_map(__func__, obj, "netcnt");
+	if (map_fd < 0) {
+		printf("Failed to find bpf map with net counters");
+		goto err;
+	}
+
+	percpu_map_fd = bpf_find_map(__func__, obj, "percpu_netcnt");
+	if (percpu_map_fd < 0) {
+		printf("Failed to find bpf map with percpu net counters");
+		goto err;
+	}
+
+	if (bpf_map_get_next_key(map_fd, NULL, &key)) {
+		printf("Failed to get key in cgroup storage\n");
+		goto err;
+	}
+
+	if (bpf_map_lookup_elem(map_fd, &key, &netcnt)) {
+		printf("Failed to lookup cgroup storage\n");
+		goto err;
+	}
+
+	if (bpf_map_lookup_elem(percpu_map_fd, &key, &percpu_netcnt[0])) {
+		printf("Failed to lookup percpu cgroup storage\n");
+		goto err;
+	}
+
+	/* Some packets can be still in per-cpu cache, but not more than
+	 * MAX_PERCPU_PACKETS.
+	 */
+	packets = netcnt.packets;
+	bytes = netcnt.bytes;
+	for (cpu = 0; cpu < nproc; cpu++) {
+		if (percpu_netcnt[cpu].packets > MAX_PERCPU_PACKETS) {
+			printf("Unexpected percpu value: %llu\n",
+			       percpu_netcnt[cpu].packets);
+			goto err;
+		}
+
+		packets += percpu_netcnt[cpu].packets;
+		bytes += percpu_netcnt[cpu].bytes;
+	}
+
+	/* No packets should be lost */
+	if (packets != 10000) {
+		printf("Unexpected packet count: %lu\n", packets);
+		goto err;
+	}
+
+	/* Let's check that bytes counter matches the number of packets
+	 * multiplied by the size of ipv6 ICMP packet.
+	 */
+	if (bytes != packets * 104) {
+		printf("Unexpected bytes count: %lu\n", bytes);
+		goto err;
+	}
+
+	error = 0;
+	printf("test_netcnt:PASS\n");
+
+err:
+	cleanup_cgroup_environment();
+	free(percpu_netcnt);
+
+out:
+	return error;
+}
-- 
cgit 


From 0ed3015c9964dab7a1693b3e40650f329c16691e Mon Sep 17 00:00:00 2001
From: Vakul Garg <vakul.garg@nxp.com>
Date: Fri, 28 Sep 2018 21:48:08 +0530
Subject: selftests/tls: Fix recv(MSG_PEEK) & splice() test cases

TLS test cases splice_from_pipe, send_and_splice &
recv_peek_multiple_records expect to receive a given nummber of bytes
and then compare them against the number of bytes which were sent.
Therefore, system call recv() must not return before receiving the
requested number of bytes, otherwise the subsequent memcmp() fails.
This patch passes MSG_WAITALL flag to recv() so that it does not return
prematurely before requested number of bytes are copied to receive
buffer.

Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/tls.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 11d54c36ae49..fac68d710f35 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -288,7 +288,7 @@ TEST_F(tls, splice_from_pipe)
 	ASSERT_GE(pipe(p), 0);
 	EXPECT_GE(write(p[1], mem_send, send_len), 0);
 	EXPECT_GE(splice(p[0], NULL, self->fd, NULL, send_len, 0), 0);
-	EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+	EXPECT_EQ(recv(self->cfd, mem_recv, send_len, MSG_WAITALL), send_len);
 	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
 }
 
@@ -322,13 +322,13 @@ TEST_F(tls, send_and_splice)
 
 	ASSERT_GE(pipe(p), 0);
 	EXPECT_EQ(send(self->fd, test_str, send_len2, 0), send_len2);
-	EXPECT_NE(recv(self->cfd, buf, send_len2, 0), -1);
+	EXPECT_EQ(recv(self->cfd, buf, send_len2, MSG_WAITALL), send_len2);
 	EXPECT_EQ(memcmp(test_str, buf, send_len2), 0);
 
 	EXPECT_GE(write(p[1], mem_send, send_len), send_len);
 	EXPECT_GE(splice(p[0], NULL, self->fd, NULL, send_len, 0), send_len);
 
-	EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+	EXPECT_EQ(recv(self->cfd, mem_recv, send_len, MSG_WAITALL), send_len);
 	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
 }
 
@@ -516,17 +516,17 @@ TEST_F(tls, recv_peek_multiple_records)
 	len = strlen(test_str_second) + 1;
 	EXPECT_EQ(send(self->fd, test_str_second, len, 0), len);
 
-	len = sizeof(buf);
+	len = strlen(test_str_first);
 	memset(buf, 0, len);
-	EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1);
+	EXPECT_EQ(recv(self->cfd, buf, len, MSG_PEEK | MSG_WAITALL), len);
 
 	/* MSG_PEEK can only peek into the current record. */
-	len = strlen(test_str_first) + 1;
+	len = strlen(test_str_first);
 	EXPECT_EQ(memcmp(test_str_first, buf, len), 0);
 
-	len = sizeof(buf);
+	len = strlen(test_str) + 1;
 	memset(buf, 0, len);
-	EXPECT_NE(recv(self->cfd, buf, len, 0), -1);
+	EXPECT_EQ(recv(self->cfd, buf, len, MSG_WAITALL), len);
 
 	/* Non-MSG_PEEK will advance strparser (and therefore record)
 	 * however.
@@ -543,9 +543,9 @@ TEST_F(tls, recv_peek_multiple_records)
 	len = strlen(test_str_second) + 1;
 	EXPECT_EQ(send(self->fd, test_str_second, len, 0), len);
 
-	len = sizeof(buf);
+	len = strlen(test_str) + 1;
 	memset(buf, 0, len);
-	EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1);
+	EXPECT_EQ(recv(self->cfd, buf, len, MSG_PEEK | MSG_WAITALL), len);
 
 	len = strlen(test_str) + 1;
 	EXPECT_EQ(memcmp(test_str, buf, len), 0);
-- 
cgit 


From 7c03e7035ac1cf2a6165754e4f3a49c2f1977838 Mon Sep 17 00:00:00 2001
From: Andy Lutomirski <luto@kernel.org>
Date: Mon, 1 Oct 2018 12:52:16 -0700
Subject: selftests/x86: Add clock_gettime() tests to test_vdso

Now that the vDSO implementation of clock_gettime() is getting
reworked, add a selftest for it.  This tests that its output is
consistent with the syscall version.

This is marked for stable to serve as a test for commit

  715bd9d12f84 ("x86/vdso: Fix asm constraints on vDSO syscall fallbacks")

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/082399674de2619b2befd8c0dde49b260605b126.1538422295.git.luto@kernel.org
---
 tools/testing/selftests/x86/test_vdso.c | 99 +++++++++++++++++++++++++++++++++
 1 file changed, 99 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/x86/test_vdso.c b/tools/testing/selftests/x86/test_vdso.c
index 235259011704..49f7294fb382 100644
--- a/tools/testing/selftests/x86/test_vdso.c
+++ b/tools/testing/selftests/x86/test_vdso.c
@@ -17,6 +17,7 @@
 #include <errno.h>
 #include <sched.h>
 #include <stdbool.h>
+#include <limits.h>
 
 #ifndef SYS_getcpu
 # ifdef __x86_64__
@@ -31,6 +32,10 @@
 
 int nerrs = 0;
 
+typedef int (*vgettime_t)(clockid_t, struct timespec *);
+
+vgettime_t vdso_clock_gettime;
+
 typedef long (*getcpu_t)(unsigned *, unsigned *, void *);
 
 getcpu_t vgetcpu;
@@ -95,6 +100,10 @@ static void fill_function_pointers()
 		printf("Warning: failed to find getcpu in vDSO\n");
 
 	vgetcpu = (getcpu_t) vsyscall_getcpu();
+
+	vdso_clock_gettime = (vgettime_t)dlsym(vdso, "__vdso_clock_gettime");
+	if (!vdso_clock_gettime)
+		printf("Warning: failed to find clock_gettime in vDSO\n");
 }
 
 static long sys_getcpu(unsigned * cpu, unsigned * node,
@@ -103,6 +112,11 @@ static long sys_getcpu(unsigned * cpu, unsigned * node,
 	return syscall(__NR_getcpu, cpu, node, cache);
 }
 
+static inline int sys_clock_gettime(clockid_t id, struct timespec *ts)
+{
+	return syscall(__NR_clock_gettime, id, ts);
+}
+
 static void test_getcpu(void)
 {
 	printf("[RUN]\tTesting getcpu...\n");
@@ -155,10 +169,95 @@ static void test_getcpu(void)
 	}
 }
 
+static bool ts_leq(const struct timespec *a, const struct timespec *b)
+{
+	if (a->tv_sec != b->tv_sec)
+		return a->tv_sec < b->tv_sec;
+	else
+		return a->tv_nsec <= b->tv_nsec;
+}
+
+static char const * const clocknames[] = {
+	[0] = "CLOCK_REALTIME",
+	[1] = "CLOCK_MONOTONIC",
+	[2] = "CLOCK_PROCESS_CPUTIME_ID",
+	[3] = "CLOCK_THREAD_CPUTIME_ID",
+	[4] = "CLOCK_MONOTONIC_RAW",
+	[5] = "CLOCK_REALTIME_COARSE",
+	[6] = "CLOCK_MONOTONIC_COARSE",
+	[7] = "CLOCK_BOOTTIME",
+	[8] = "CLOCK_REALTIME_ALARM",
+	[9] = "CLOCK_BOOTTIME_ALARM",
+	[10] = "CLOCK_SGI_CYCLE",
+	[11] = "CLOCK_TAI",
+};
+
+static void test_one_clock_gettime(int clock, const char *name)
+{
+	struct timespec start, vdso, end;
+	int vdso_ret, end_ret;
+
+	printf("[RUN]\tTesting clock_gettime for clock %s (%d)...\n", name, clock);
+
+	if (sys_clock_gettime(clock, &start) < 0) {
+		if (errno == EINVAL) {
+			vdso_ret = vdso_clock_gettime(clock, &vdso);
+			if (vdso_ret == -EINVAL) {
+				printf("[OK]\tNo such clock.\n");
+			} else {
+				printf("[FAIL]\tNo such clock, but __vdso_clock_gettime returned %d\n", vdso_ret);
+				nerrs++;
+			}
+		} else {
+			printf("[WARN]\t clock_gettime(%d) syscall returned error %d\n", clock, errno);
+		}
+		return;
+	}
+
+	vdso_ret = vdso_clock_gettime(clock, &vdso);
+	end_ret = sys_clock_gettime(clock, &end);
+
+	if (vdso_ret != 0 || end_ret != 0) {
+		printf("[FAIL]\tvDSO returned %d, syscall errno=%d\n",
+		       vdso_ret, errno);
+		nerrs++;
+		return;
+	}
+
+	printf("\t%llu.%09ld %llu.%09ld %llu.%09ld\n",
+	       (unsigned long long)start.tv_sec, start.tv_nsec,
+	       (unsigned long long)vdso.tv_sec, vdso.tv_nsec,
+	       (unsigned long long)end.tv_sec, end.tv_nsec);
+
+	if (!ts_leq(&start, &vdso) || !ts_leq(&vdso, &end)) {
+		printf("[FAIL]\tTimes are out of sequence\n");
+		nerrs++;
+	}
+}
+
+static void test_clock_gettime(void)
+{
+	for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]);
+	     clock++) {
+		test_one_clock_gettime(clock, clocknames[clock]);
+	}
+
+	/* Also test some invalid clock ids */
+	test_one_clock_gettime(-1, "invalid");
+	test_one_clock_gettime(INT_MIN, "invalid");
+	test_one_clock_gettime(INT_MAX, "invalid");
+}
+
 int main(int argc, char **argv)
 {
 	fill_function_pointers();
 
+	test_clock_gettime();
+
+	/*
+	 * Test getcpu() last so that, if something goes wrong setting affinity,
+	 * we still run the other tests.
+	 */
 	test_getcpu();
 
 	return nerrs ? 1 : 0;
-- 
cgit 


From aad2eeaf46973a0968a75640cd1f8f1c650322a0 Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@wand.net.nz>
Date: Tue, 2 Oct 2018 13:35:30 -0700
Subject: bpf: Simplify ptr_min_max_vals adjustment

An upcoming commit will add another two pointer types that need very
similar behaviour, so generalise this function now.

Signed-off-by: Joe Stringer <joe@wand.net.nz>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/verifier.c                       | 22 ++++++++++------------
 tools/testing/selftests/bpf/test_verifier.c | 14 +++++++-------
 2 files changed, 17 insertions(+), 19 deletions(-)

(limited to 'tools/testing')

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9c82d8f58085..abf567200574 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2669,20 +2669,18 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		return -EACCES;
 	}
 
-	if (ptr_reg->type == PTR_TO_MAP_VALUE_OR_NULL) {
-		verbose(env, "R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n",
-			dst);
-		return -EACCES;
-	}
-	if (ptr_reg->type == CONST_PTR_TO_MAP) {
-		verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n",
-			dst);
+	switch (ptr_reg->type) {
+	case PTR_TO_MAP_VALUE_OR_NULL:
+		verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n",
+			dst, reg_type_str[ptr_reg->type]);
 		return -EACCES;
-	}
-	if (ptr_reg->type == PTR_TO_PACKET_END) {
-		verbose(env, "R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n",
-			dst);
+	case CONST_PTR_TO_MAP:
+	case PTR_TO_PACKET_END:
+		verbose(env, "R%d pointer arithmetic on %s prohibited\n",
+			dst, reg_type_str[ptr_reg->type]);
 		return -EACCES;
+	default:
+		break;
 	}
 
 	/* In case of 'scalar += pointer', dst_reg inherits pointer type and id.
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index c7d25f23baf9..a90be44f61e0 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -3638,7 +3638,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END",
+		.errstr = "R3 pointer arithmetic on pkt_end",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -4896,7 +4896,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map1 = { 4 },
-		.errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL",
+		.errstr = "R4 pointer arithmetic on map_value_or_null",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
 	},
@@ -4917,7 +4917,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map1 = { 4 },
-		.errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL",
+		.errstr = "R4 pointer arithmetic on map_value_or_null",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
 	},
@@ -4938,7 +4938,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map1 = { 4 },
-		.errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL",
+		.errstr = "R4 pointer arithmetic on map_value_or_null",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
 	},
@@ -7253,7 +7253,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map_in_map = { 3 },
-		.errstr = "R1 pointer arithmetic on CONST_PTR_TO_MAP prohibited",
+		.errstr = "R1 pointer arithmetic on map_ptr prohibited",
 		.result = REJECT,
 	},
 	{
@@ -8927,7 +8927,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END",
+		.errstr = "R3 pointer arithmetic on pkt_end",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
@@ -8946,7 +8946,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END",
+		.errstr = "R3 pointer arithmetic on pkt_end",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
-- 
cgit 


From 9d2be44a7f33d5ec4fbd3368317bcf5f404bb8f7 Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@wand.net.nz>
Date: Tue, 2 Oct 2018 13:35:31 -0700
Subject: bpf: Reuse canonical string formatter for ctx errs

The array "reg_type_str" provides canonical formatting of register
types, however a couple of places would previously check whether a
register represented the context and write the name "context" directly.
An upcoming commit will add another pointer type to these statements, so
to provide more accurate error messages in the verifier, update these
error messages to use "reg_type_str" instead.

Signed-off-by: Joe Stringer <joe@wand.net.nz>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/verifier.c                       |  7 +++----
 tools/testing/selftests/bpf/test_verifier.c | 10 +++++-----
 2 files changed, 8 insertions(+), 9 deletions(-)

(limited to 'tools/testing')

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index abf567200574..8b4e70eeced2 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1763,8 +1763,7 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins
 	if (is_ctx_reg(env, insn->dst_reg) ||
 	    is_pkt_reg(env, insn->dst_reg)) {
 		verbose(env, "BPF_XADD stores into R%d %s is not allowed\n",
-			insn->dst_reg, is_ctx_reg(env, insn->dst_reg) ?
-			"context" : "packet");
+			insn->dst_reg, reg_type_str[insn->dst_reg]);
 		return -EACCES;
 	}
 
@@ -4871,8 +4870,8 @@ static int do_check(struct bpf_verifier_env *env)
 				return err;
 
 			if (is_ctx_reg(env, insn->dst_reg)) {
-				verbose(env, "BPF_ST stores into R%d context is not allowed\n",
-					insn->dst_reg);
+				verbose(env, "BPF_ST stores into R%d %s is not allowed\n",
+					insn->dst_reg, reg_type_str[insn->dst_reg]);
 				return -EACCES;
 			}
 
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index a90be44f61e0..6e0b3f148cdb 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -3276,7 +3276,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_1, offsetof(struct __sk_buff, mark), 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "BPF_ST stores into R1 context is not allowed",
+		.errstr = "BPF_ST stores into R1 inv is not allowed",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -3288,7 +3288,7 @@ static struct bpf_test tests[] = {
 				     BPF_REG_0, offsetof(struct __sk_buff, mark), 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "BPF_XADD stores into R1 context is not allowed",
+		.errstr = "BPF_XADD stores into R1 inv is not allowed",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -5266,7 +5266,7 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R2 leaks addr into mem",
 		.result_unpriv = REJECT,
 		.result = REJECT,
-		.errstr = "BPF_XADD stores into R1 context is not allowed",
+		.errstr = "BPF_XADD stores into R1 inv is not allowed",
 	},
 	{
 		"leak pointer into ctx 2",
@@ -5281,7 +5281,7 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R10 leaks addr into mem",
 		.result_unpriv = REJECT,
 		.result = REJECT,
-		.errstr = "BPF_XADD stores into R1 context is not allowed",
+		.errstr = "BPF_XADD stores into R1 inv is not allowed",
 	},
 	{
 		"leak pointer into ctx 3",
@@ -12230,7 +12230,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = REJECT,
-		.errstr = "BPF_XADD stores into R2 packet",
+		.errstr = "BPF_XADD stores into R2 ctx",
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
 	{
-- 
cgit 


From 6acc9b432e6714d72d7d77ec7c27f6f8358d0c71 Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@wand.net.nz>
Date: Tue, 2 Oct 2018 13:35:36 -0700
Subject: bpf: Add helper to retrieve socket in BPF

This patch adds new BPF helper functions, bpf_sk_lookup_tcp() and
bpf_sk_lookup_udp() which allows BPF programs to find out if there is a
socket listening on this host, and returns a socket pointer which the
BPF program can then access to determine, for instance, whether to
forward or drop traffic. bpf_sk_lookup_xxx() may take a reference on the
socket, so when a BPF program makes use of this function, it must
subsequently pass the returned pointer into the newly added sk_release()
to return the reference.

By way of example, the following pseudocode would filter inbound
connections at XDP if there is no corresponding service listening for
the traffic:

  struct bpf_sock_tuple tuple;
  struct bpf_sock_ops *sk;

  populate_tuple(ctx, &tuple); // Extract the 5tuple from the packet
  sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof tuple, netns, 0);
  if (!sk) {
    // Couldn't find a socket listening for this traffic. Drop.
    return TC_ACT_SHOT;
  }
  bpf_sk_release(sk, 0);
  return TC_ACT_OK;

Signed-off-by: Joe Stringer <joe@wand.net.nz>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/uapi/linux/bpf.h                  |  93 +++++++++++++++++-
 kernel/bpf/verifier.c                     |   8 +-
 net/core/filter.c                         | 151 ++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h            |  93 +++++++++++++++++-
 tools/testing/selftests/bpf/bpf_helpers.h |  12 +++
 5 files changed, 354 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e2070d819e04..f9187b41dff6 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2144,6 +2144,77 @@ union bpf_attr {
  *		request in the skb.
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
+ *	Description
+ *		Look for TCP socket matching *tuple*, optionally in a child
+ *		network namespace *netns*. The return value must be checked,
+ *		and if non-NULL, released via **bpf_sk_release**\ ().
+ *
+ *		The *ctx* should point to the context of the program, such as
+ *		the skb or socket (depending on the hook in use). This is used
+ *		to determine the base network namespace for the lookup.
+ *
+ *		*tuple_size* must be one of:
+ *
+ *		**sizeof**\ (*tuple*\ **->ipv4**)
+ *			Look for an IPv4 socket.
+ *		**sizeof**\ (*tuple*\ **->ipv6**)
+ *			Look for an IPv6 socket.
+ *
+ *		If the *netns* is zero, then the socket lookup table in the
+ *		netns associated with the *ctx* will be used. For the TC hooks,
+ *		this in the netns of the device in the skb. For socket hooks,
+ *		this in the netns of the socket. If *netns* is non-zero, then
+ *		it specifies the ID of the netns relative to the netns
+ *		associated with the *ctx*.
+ *
+ *		All values for *flags* are reserved for future usage, and must
+ *		be left at zero.
+ *
+ *		This helper is available only if the kernel was compiled with
+ *		**CONFIG_NET** configuration option.
+ *	Return
+ *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *
+ * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
+ *	Description
+ *		Look for UDP socket matching *tuple*, optionally in a child
+ *		network namespace *netns*. The return value must be checked,
+ *		and if non-NULL, released via **bpf_sk_release**\ ().
+ *
+ *		The *ctx* should point to the context of the program, such as
+ *		the skb or socket (depending on the hook in use). This is used
+ *		to determine the base network namespace for the lookup.
+ *
+ *		*tuple_size* must be one of:
+ *
+ *		**sizeof**\ (*tuple*\ **->ipv4**)
+ *			Look for an IPv4 socket.
+ *		**sizeof**\ (*tuple*\ **->ipv6**)
+ *			Look for an IPv6 socket.
+ *
+ *		If the *netns* is zero, then the socket lookup table in the
+ *		netns associated with the *ctx* will be used. For the TC hooks,
+ *		this in the netns of the device in the skb. For socket hooks,
+ *		this in the netns of the socket. If *netns* is non-zero, then
+ *		it specifies the ID of the netns relative to the netns
+ *		associated with the *ctx*.
+ *
+ *		All values for *flags* are reserved for future usage, and must
+ *		be left at zero.
+ *
+ *		This helper is available only if the kernel was compiled with
+ *		**CONFIG_NET** configuration option.
+ *	Return
+ *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *
+ * int bpf_sk_release(struct bpf_sock *sk)
+ *	Description
+ *		Release the reference held by *sock*. *sock* must be a non-NULL
+ *		pointer that was returned from bpf_sk_lookup_xxx\ ().
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2229,7 +2300,10 @@ union bpf_attr {
 	FN(get_current_cgroup_id),	\
 	FN(get_local_storage),		\
 	FN(sk_select_reuseport),	\
-	FN(skb_ancestor_cgroup_id),
+	FN(skb_ancestor_cgroup_id),	\
+	FN(sk_lookup_tcp),		\
+	FN(sk_lookup_udp),		\
+	FN(sk_release),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2399,6 +2473,23 @@ struct bpf_sock {
 				 */
 };
 
+struct bpf_sock_tuple {
+	union {
+		struct {
+			__be32 saddr;
+			__be32 daddr;
+			__be16 sport;
+			__be16 dport;
+		} ipv4;
+		struct {
+			__be32 saddr[4];
+			__be32 daddr[4];
+			__be16 sport;
+			__be16 dport;
+		} ipv6;
+	};
+};
+
 #define XDP_PACKET_HEADROOM 256
 
 /* User return codes for XDP prog type.
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index cd0d8bc00bd1..73c81bef6ae8 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -153,6 +153,12 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
  * PTR_TO_MAP_VALUE, PTR_TO_SOCKET_OR_NULL becomes PTR_TO_SOCKET when the type
  * passes through a NULL-check conditional. For the branch wherein the state is
  * changed to CONST_IMM, the verifier releases the reference.
+ *
+ * For each helper function that allocates a reference, such as
+ * bpf_sk_lookup_tcp(), there is a corresponding release function, such as
+ * bpf_sk_release(). When a reference type passes into the release function,
+ * the verifier also releases the reference. If any unchecked or unreleased
+ * reference remains at the end of the program, the verifier rejects it.
  */
 
 /* verifier_state + insn_idx are pushed to stack when branch is encountered */
@@ -300,7 +306,7 @@ static bool arg_type_is_refcounted(enum bpf_arg_type type)
  */
 static bool is_release_function(enum bpf_func_id func_id)
 {
-	return false;
+	return func_id == BPF_FUNC_sk_release;
 }
 
 /* string representation of 'enum bpf_reg_type' */
diff --git a/net/core/filter.c b/net/core/filter.c
index b2cb186252e4..591c698bc517 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -58,13 +58,17 @@
 #include <net/busy_poll.h>
 #include <net/tcp.h>
 #include <net/xfrm.h>
+#include <net/udp.h>
 #include <linux/bpf_trace.h>
 #include <net/xdp_sock.h>
 #include <linux/inetdevice.h>
+#include <net/inet_hashtables.h>
+#include <net/inet6_hashtables.h>
 #include <net/ip_fib.h>
 #include <net/flow.h>
 #include <net/arp.h>
 #include <net/ipv6.h>
+#include <net/net_namespace.h>
 #include <linux/seg6_local.h>
 #include <net/seg6.h>
 #include <net/seg6_local.h>
@@ -4813,6 +4817,141 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = {
 };
 #endif /* CONFIG_IPV6_SEG6_BPF */
 
+struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
+		       struct sk_buff *skb, u8 family, u8 proto)
+{
+	int dif = skb->dev->ifindex;
+	bool refcounted = false;
+	struct sock *sk = NULL;
+
+	if (family == AF_INET) {
+		__be32 src4 = tuple->ipv4.saddr;
+		__be32 dst4 = tuple->ipv4.daddr;
+		int sdif = inet_sdif(skb);
+
+		if (proto == IPPROTO_TCP)
+			sk = __inet_lookup(net, &tcp_hashinfo, skb, 0,
+					   src4, tuple->ipv4.sport,
+					   dst4, tuple->ipv4.dport,
+					   dif, sdif, &refcounted);
+		else
+			sk = __udp4_lib_lookup(net, src4, tuple->ipv4.sport,
+					       dst4, tuple->ipv4.dport,
+					       dif, sdif, &udp_table, skb);
+#if IS_ENABLED(CONFIG_IPV6)
+	} else {
+		struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr;
+		struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr;
+		int sdif = inet6_sdif(skb);
+
+		if (proto == IPPROTO_TCP)
+			sk = __inet6_lookup(net, &tcp_hashinfo, skb, 0,
+					    src6, tuple->ipv6.sport,
+					    dst6, tuple->ipv6.dport,
+					    dif, sdif, &refcounted);
+		else
+			sk = __udp6_lib_lookup(net, src6, tuple->ipv6.sport,
+					       dst6, tuple->ipv6.dport,
+					       dif, sdif, &udp_table, skb);
+#endif
+	}
+
+	if (unlikely(sk && !refcounted && !sock_flag(sk, SOCK_RCU_FREE))) {
+		WARN_ONCE(1, "Found non-RCU, unreferenced socket!");
+		sk = NULL;
+	}
+	return sk;
+}
+
+/* bpf_sk_lookup performs the core lookup for different types of sockets,
+ * taking a reference on the socket if it doesn't have the flag SOCK_RCU_FREE.
+ * Returns the socket as an 'unsigned long' to simplify the casting in the
+ * callers to satisfy BPF_CALL declarations.
+ */
+static unsigned long
+bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+	      u8 proto, u64 netns_id, u64 flags)
+{
+	struct net *caller_net;
+	struct sock *sk = NULL;
+	u8 family = AF_UNSPEC;
+	struct net *net;
+
+	family = len == sizeof(tuple->ipv4) ? AF_INET : AF_INET6;
+	if (unlikely(family == AF_UNSPEC || netns_id > U32_MAX || flags))
+		goto out;
+
+	if (skb->dev)
+		caller_net = dev_net(skb->dev);
+	else
+		caller_net = sock_net(skb->sk);
+	if (netns_id) {
+		net = get_net_ns_by_id(caller_net, netns_id);
+		if (unlikely(!net))
+			goto out;
+		sk = sk_lookup(net, tuple, skb, family, proto);
+		put_net(net);
+	} else {
+		net = caller_net;
+		sk = sk_lookup(net, tuple, skb, family, proto);
+	}
+
+	if (sk)
+		sk = sk_to_full_sk(sk);
+out:
+	return (unsigned long) sk;
+}
+
+BPF_CALL_5(bpf_sk_lookup_tcp, struct sk_buff *, skb,
+	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+	return bpf_sk_lookup(skb, tuple, len, IPPROTO_TCP, netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_sk_lookup_tcp_proto = {
+	.func		= bpf_sk_lookup_tcp,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_PTR_TO_SOCKET_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+	.arg5_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_5(bpf_sk_lookup_udp, struct sk_buff *, skb,
+	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+	return bpf_sk_lookup(skb, tuple, len, IPPROTO_UDP, netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_sk_lookup_udp_proto = {
+	.func		= bpf_sk_lookup_udp,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_PTR_TO_SOCKET_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+	.arg5_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_1(bpf_sk_release, struct sock *, sk)
+{
+	if (!sock_flag(sk, SOCK_RCU_FREE))
+		sock_gen_put(sk);
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_sk_release_proto = {
+	.func		= bpf_sk_release,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_SOCKET,
+};
+
 bool bpf_helper_changes_pkt_data(void *func)
 {
 	if (func == bpf_skb_vlan_push ||
@@ -5019,6 +5158,12 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_ancestor_cgroup_id:
 		return &bpf_skb_ancestor_cgroup_id_proto;
 #endif
+	case BPF_FUNC_sk_lookup_tcp:
+		return &bpf_sk_lookup_tcp_proto;
+	case BPF_FUNC_sk_lookup_udp:
+		return &bpf_sk_lookup_udp_proto;
+	case BPF_FUNC_sk_release:
+		return &bpf_sk_release_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -5119,6 +5264,12 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_redirect_hash_proto;
 	case BPF_FUNC_get_local_storage:
 		return &bpf_get_local_storage_proto;
+	case BPF_FUNC_sk_lookup_tcp:
+		return &bpf_sk_lookup_tcp_proto;
+	case BPF_FUNC_sk_lookup_udp:
+		return &bpf_sk_lookup_udp_proto;
+	case BPF_FUNC_sk_release:
+		return &bpf_sk_release_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e2070d819e04..f9187b41dff6 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2144,6 +2144,77 @@ union bpf_attr {
  *		request in the skb.
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
+ *	Description
+ *		Look for TCP socket matching *tuple*, optionally in a child
+ *		network namespace *netns*. The return value must be checked,
+ *		and if non-NULL, released via **bpf_sk_release**\ ().
+ *
+ *		The *ctx* should point to the context of the program, such as
+ *		the skb or socket (depending on the hook in use). This is used
+ *		to determine the base network namespace for the lookup.
+ *
+ *		*tuple_size* must be one of:
+ *
+ *		**sizeof**\ (*tuple*\ **->ipv4**)
+ *			Look for an IPv4 socket.
+ *		**sizeof**\ (*tuple*\ **->ipv6**)
+ *			Look for an IPv6 socket.
+ *
+ *		If the *netns* is zero, then the socket lookup table in the
+ *		netns associated with the *ctx* will be used. For the TC hooks,
+ *		this in the netns of the device in the skb. For socket hooks,
+ *		this in the netns of the socket. If *netns* is non-zero, then
+ *		it specifies the ID of the netns relative to the netns
+ *		associated with the *ctx*.
+ *
+ *		All values for *flags* are reserved for future usage, and must
+ *		be left at zero.
+ *
+ *		This helper is available only if the kernel was compiled with
+ *		**CONFIG_NET** configuration option.
+ *	Return
+ *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *
+ * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
+ *	Description
+ *		Look for UDP socket matching *tuple*, optionally in a child
+ *		network namespace *netns*. The return value must be checked,
+ *		and if non-NULL, released via **bpf_sk_release**\ ().
+ *
+ *		The *ctx* should point to the context of the program, such as
+ *		the skb or socket (depending on the hook in use). This is used
+ *		to determine the base network namespace for the lookup.
+ *
+ *		*tuple_size* must be one of:
+ *
+ *		**sizeof**\ (*tuple*\ **->ipv4**)
+ *			Look for an IPv4 socket.
+ *		**sizeof**\ (*tuple*\ **->ipv6**)
+ *			Look for an IPv6 socket.
+ *
+ *		If the *netns* is zero, then the socket lookup table in the
+ *		netns associated with the *ctx* will be used. For the TC hooks,
+ *		this in the netns of the device in the skb. For socket hooks,
+ *		this in the netns of the socket. If *netns* is non-zero, then
+ *		it specifies the ID of the netns relative to the netns
+ *		associated with the *ctx*.
+ *
+ *		All values for *flags* are reserved for future usage, and must
+ *		be left at zero.
+ *
+ *		This helper is available only if the kernel was compiled with
+ *		**CONFIG_NET** configuration option.
+ *	Return
+ *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *
+ * int bpf_sk_release(struct bpf_sock *sk)
+ *	Description
+ *		Release the reference held by *sock*. *sock* must be a non-NULL
+ *		pointer that was returned from bpf_sk_lookup_xxx\ ().
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2229,7 +2300,10 @@ union bpf_attr {
 	FN(get_current_cgroup_id),	\
 	FN(get_local_storage),		\
 	FN(sk_select_reuseport),	\
-	FN(skb_ancestor_cgroup_id),
+	FN(skb_ancestor_cgroup_id),	\
+	FN(sk_lookup_tcp),		\
+	FN(sk_lookup_udp),		\
+	FN(sk_release),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2399,6 +2473,23 @@ struct bpf_sock {
 				 */
 };
 
+struct bpf_sock_tuple {
+	union {
+		struct {
+			__be32 saddr;
+			__be32 daddr;
+			__be16 sport;
+			__be16 dport;
+		} ipv4;
+		struct {
+			__be32 saddr[4];
+			__be32 daddr[4];
+			__be16 sport;
+			__be16 dport;
+		} ipv6;
+	};
+};
+
 #define XDP_PACKET_HEADROOM 256
 
 /* User return codes for XDP prog type.
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index e4be7730222d..1d407b3494f9 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -143,6 +143,18 @@ static unsigned long long (*bpf_skb_cgroup_id)(void *ctx) =
 	(void *) BPF_FUNC_skb_cgroup_id;
 static unsigned long long (*bpf_skb_ancestor_cgroup_id)(void *ctx, int level) =
 	(void *) BPF_FUNC_skb_ancestor_cgroup_id;
+static struct bpf_sock *(*bpf_sk_lookup_tcp)(void *ctx,
+					     struct bpf_sock_tuple *tuple,
+					     int size, unsigned int netns_id,
+					     unsigned long long flags) =
+	(void *) BPF_FUNC_sk_lookup_tcp;
+static struct bpf_sock *(*bpf_sk_lookup_udp)(void *ctx,
+					     struct bpf_sock_tuple *tuple,
+					     int size, unsigned int netns_id,
+					     unsigned long long flags) =
+	(void *) BPF_FUNC_sk_lookup_udp;
+static int (*bpf_sk_release)(struct bpf_sock *sk) =
+	(void *) BPF_FUNC_sk_release;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
-- 
cgit 


From 0c586079f852187d19fea60c9a4981ad29e22ba8 Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@wand.net.nz>
Date: Tue, 2 Oct 2018 13:35:37 -0700
Subject: selftests/bpf: Generalize dummy program types

Don't hardcode the dummy program types to SOCKET_FILTER type, as this
prevents testing bpf_tail_call in conjunction with other program types.
Instead, use the program type specified in the test case.

Signed-off-by: Joe Stringer <joe@wand.net.nz>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_verifier.c | 31 ++++++++++++++++-------------
 1 file changed, 17 insertions(+), 14 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 6e0b3f148cdb..163fd1c0062c 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -12652,18 +12652,18 @@ static int create_map(uint32_t type, uint32_t size_key,
 	return fd;
 }
 
-static int create_prog_dummy1(void)
+static int create_prog_dummy1(enum bpf_map_type prog_type)
 {
 	struct bpf_insn prog[] = {
 		BPF_MOV64_IMM(BPF_REG_0, 42),
 		BPF_EXIT_INSN(),
 	};
 
-	return bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog,
+	return bpf_load_program(prog_type, prog,
 				ARRAY_SIZE(prog), "GPL", 0, NULL, 0);
 }
 
-static int create_prog_dummy2(int mfd, int idx)
+static int create_prog_dummy2(enum bpf_map_type prog_type, int mfd, int idx)
 {
 	struct bpf_insn prog[] = {
 		BPF_MOV64_IMM(BPF_REG_3, idx),
@@ -12674,11 +12674,12 @@ static int create_prog_dummy2(int mfd, int idx)
 		BPF_EXIT_INSN(),
 	};
 
-	return bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog,
+	return bpf_load_program(prog_type, prog,
 				ARRAY_SIZE(prog), "GPL", 0, NULL, 0);
 }
 
-static int create_prog_array(uint32_t max_elem, int p1key)
+static int create_prog_array(enum bpf_map_type prog_type, uint32_t max_elem,
+			     int p1key)
 {
 	int p2key = 1;
 	int mfd, p1fd, p2fd;
@@ -12690,8 +12691,8 @@ static int create_prog_array(uint32_t max_elem, int p1key)
 		return -1;
 	}
 
-	p1fd = create_prog_dummy1();
-	p2fd = create_prog_dummy2(mfd, p2key);
+	p1fd = create_prog_dummy1(prog_type);
+	p2fd = create_prog_dummy2(prog_type, mfd, p2key);
 	if (p1fd < 0 || p2fd < 0)
 		goto out;
 	if (bpf_map_update_elem(mfd, &p1key, &p1fd, BPF_ANY) < 0)
@@ -12748,8 +12749,8 @@ static int create_cgroup_storage(bool percpu)
 
 static char bpf_vlog[UINT_MAX >> 8];
 
-static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
-			  int *map_fds)
+static void do_test_fixup(struct bpf_test *test, enum bpf_map_type prog_type,
+			  struct bpf_insn *prog, int *map_fds)
 {
 	int *fixup_map1 = test->fixup_map1;
 	int *fixup_map2 = test->fixup_map2;
@@ -12805,7 +12806,7 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
 	}
 
 	if (*fixup_prog1) {
-		map_fds[4] = create_prog_array(4, 0);
+		map_fds[4] = create_prog_array(prog_type, 4, 0);
 		do {
 			prog[*fixup_prog1].imm = map_fds[4];
 			fixup_prog1++;
@@ -12813,7 +12814,7 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
 	}
 
 	if (*fixup_prog2) {
-		map_fds[5] = create_prog_array(8, 7);
+		map_fds[5] = create_prog_array(prog_type, 8, 7);
 		do {
 			prog[*fixup_prog2].imm = map_fds[5];
 			fixup_prog2++;
@@ -12859,11 +12860,13 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	for (i = 0; i < MAX_NR_MAPS; i++)
 		map_fds[i] = -1;
 
-	do_test_fixup(test, prog, map_fds);
+	if (!prog_type)
+		prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+	do_test_fixup(test, prog_type, prog, map_fds);
 	prog_len = probe_filter_length(prog);
 
-	fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
-				     prog, prog_len, test->flags & F_LOAD_WITH_STRICT_ALIGNMENT,
+	fd_prog = bpf_verify_program(prog_type, prog, prog_len,
+				     test->flags & F_LOAD_WITH_STRICT_ALIGNMENT,
 				     "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 1);
 
 	expected_ret = unpriv && test->result_unpriv != UNDEF ?
-- 
cgit 


From b584ab8840fdc17f0d75ac62510396b8f657ed8f Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@wand.net.nz>
Date: Tue, 2 Oct 2018 13:35:38 -0700
Subject: selftests/bpf: Add tests for reference tracking

reference tracking: leak potential reference
reference tracking: leak potential reference on stack
reference tracking: leak potential reference on stack 2
reference tracking: zero potential reference
reference tracking: copy and zero potential references
reference tracking: release reference without check
reference tracking: release reference
reference tracking: release reference twice
reference tracking: release reference twice inside branch
reference tracking: alloc, check, free in one subbranch
reference tracking: alloc, check, free in both subbranches
reference tracking in call: free reference in subprog
reference tracking in call: free reference in subprog and outside
reference tracking in call: alloc & leak reference in subprog
reference tracking in call: alloc in subprog, release outside
reference tracking in call: sk_ptr leak into caller stack
reference tracking in call: sk_ptr spill into caller stack
reference tracking: allow LD_ABS
reference tracking: forbid LD_ABS while holding reference
reference tracking: allow LD_IND
reference tracking: forbid LD_IND while holding reference
reference tracking: check reference or tail call
reference tracking: release reference then tail call
reference tracking: leak possible reference over tail call
reference tracking: leak checked reference over tail call
reference tracking: mangle and release sock_or_null
reference tracking: mangle and release sock
reference tracking: access member
reference tracking: write to member
reference tracking: invalid 64-bit access of member
reference tracking: access after release
reference tracking: direct access for lookup
unpriv: spill/fill of different pointers stx - ctx and sock
unpriv: spill/fill of different pointers stx - leak sock
unpriv: spill/fill of different pointers stx - sock and ctx (read)
unpriv: spill/fill of different pointers stx - sock and ctx (write)

Signed-off-by: Joe Stringer <joe@wand.net.nz>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_verifier.c | 759 ++++++++++++++++++++++++++++
 1 file changed, 759 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 163fd1c0062c..bc9cd8537467 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -3,6 +3,7 @@
  *
  * Copyright (c) 2014 PLUMgrid, http://plumgrid.com
  * Copyright (c) 2017 Facebook
+ * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -178,6 +179,24 @@ static void bpf_fill_rand_ld_dw(struct bpf_test *self)
 	self->retval = (uint32_t)res;
 }
 
+/* BPF_SK_LOOKUP contains 13 instructions, if you need to fix up maps */
+#define BPF_SK_LOOKUP							\
+	/* struct bpf_sock_tuple tuple = {} */				\
+	BPF_MOV64_IMM(BPF_REG_2, 0),					\
+	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -8),			\
+	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -16),		\
+	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -24),		\
+	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -32),		\
+	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -40),		\
+	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -48),		\
+	/* sk = sk_lookup_tcp(ctx, &tuple, sizeof tuple, 0, 0) */	\
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),				\
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -48),				\
+	BPF_MOV64_IMM(BPF_REG_3, sizeof(struct bpf_sock_tuple)),	\
+	BPF_MOV64_IMM(BPF_REG_4, 0),					\
+	BPF_MOV64_IMM(BPF_REG_5, 0),					\
+	BPF_EMIT_CALL(BPF_FUNC_sk_lookup_tcp)
+
 static struct bpf_test tests[] = {
 	{
 		"add+sub+mul",
@@ -2707,6 +2726,137 @@ static struct bpf_test tests[] = {
 		.errstr = "same insn cannot be used with different pointers",
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
+	{
+		"unpriv: spill/fill of different pointers stx - ctx and sock",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
+			/* struct bpf_sock *sock = bpf_sock_lookup(...); */
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+			/* u64 foo; */
+			/* void *target = &foo; */
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+			/* if (skb == NULL) *target = sock; */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0),
+			/* else *target = skb; */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
+			/* struct __sk_buff *skb = *target; */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
+			/* skb->mark = 42; */
+			BPF_MOV64_IMM(BPF_REG_3, 42),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3,
+				    offsetof(struct __sk_buff, mark)),
+			/* if (sk) bpf_sk_release(sk) */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+				BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "type=ctx expected=sock",
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"unpriv: spill/fill of different pointers stx - leak sock",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
+			/* struct bpf_sock *sock = bpf_sock_lookup(...); */
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+			/* u64 foo; */
+			/* void *target = &foo; */
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+			/* if (skb == NULL) *target = sock; */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0),
+			/* else *target = skb; */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
+			/* struct __sk_buff *skb = *target; */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
+			/* skb->mark = 42; */
+			BPF_MOV64_IMM(BPF_REG_3, 42),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		//.errstr = "same insn cannot be used with different pointers",
+		.errstr = "Unreleased reference",
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"unpriv: spill/fill of different pointers stx - sock and ctx (read)",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
+			/* struct bpf_sock *sock = bpf_sock_lookup(...); */
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+			/* u64 foo; */
+			/* void *target = &foo; */
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+			/* if (skb) *target = skb */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
+			/* else *target = sock */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0),
+			/* struct bpf_sock *sk = *target; */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
+			/* if (sk) u32 foo = sk->mark; bpf_sk_release(sk); */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 2),
+				BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+					    offsetof(struct bpf_sock, mark)),
+				BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "same insn cannot be used with different pointers",
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"unpriv: spill/fill of different pointers stx - sock and ctx (write)",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
+			/* struct bpf_sock *sock = bpf_sock_lookup(...); */
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+			/* u64 foo; */
+			/* void *target = &foo; */
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+			/* if (skb) *target = skb */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
+			/* else *target = sock */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0),
+			/* struct bpf_sock *sk = *target; */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
+			/* if (sk) sk->mark = 42; bpf_sk_release(sk); */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3),
+				BPF_MOV64_IMM(BPF_REG_3, 42),
+				BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3,
+					    offsetof(struct bpf_sock, mark)),
+				BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		//.errstr = "same insn cannot be used with different pointers",
+		.errstr = "cannot write into socket",
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
 	{
 		"unpriv: spill/fill of different pointers ldx",
 		.insns = {
@@ -12557,6 +12707,214 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = ACCEPT,
 	},
+	{
+		"reference tracking: leak potential reference",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), /* leak reference */
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: leak potential reference on stack",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: leak potential reference on stack 2",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: zero potential reference",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_IMM(BPF_REG_0, 0), /* leak reference */
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: copy and zero potential references",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_7, 0), /* leak reference */
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: release reference without check",
+		.insns = {
+			BPF_SK_LOOKUP,
+			/* reference in r0 may be NULL */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "type=sock_or_null expected=sock",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: release reference",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: release reference 2",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: release reference twice",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "type=inv expected=sock",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: release reference twice inside branch",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), /* goto end */
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "type=inv expected=sock",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: alloc, check, free in one subbranch",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 16),
+			/* if (offsetof(skb, mark) > data_len) exit; */
+			BPF_JMP_REG(BPF_JLE, BPF_REG_0, BPF_REG_3, 1),
+			BPF_EXIT_INSN(),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_2,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_SK_LOOKUP,
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 1), /* mark == 0? */
+			/* Leak reference in R0 */
+			BPF_EXIT_INSN(),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), /* sk NULL? */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: alloc, check, free in both subbranches",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 16),
+			/* if (offsetof(skb, mark) > data_len) exit; */
+			BPF_JMP_REG(BPF_JLE, BPF_REG_0, BPF_REG_3, 1),
+			BPF_EXIT_INSN(),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_2,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_SK_LOOKUP,
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 4), /* mark == 0? */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), /* sk NULL? */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), /* sk NULL? */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking in call: free reference in subprog",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), /* unchecked reference */
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_2, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
 	{
 		"pass modified ctx pointer to helper, 1",
 		.insns = {
@@ -12627,6 +12985,407 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = ACCEPT,
 	},
+	{
+		"reference tracking in call: free reference in subprog and outside",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), /* unchecked reference */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_2, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "type=inv expected=sock",
+		.result = REJECT,
+	},
+	{
+		"reference tracking in call: alloc & leak reference in subprog",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_4),
+			BPF_SK_LOOKUP,
+			/* spill unchecked sk_ptr into stack of caller */
+			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking in call: alloc in subprog, release outside",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_SK_LOOKUP,
+			BPF_EXIT_INSN(), /* return sk */
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.retval = POINTER_VALUE,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking in call: sk_ptr leak into caller stack",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, -8),
+			BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_4, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5),
+			/* spill unchecked sk_ptr into stack of caller */
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, -8),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_5, 0),
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 2 */
+			BPF_SK_LOOKUP,
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking in call: sk_ptr spill into caller stack",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, -8),
+			BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_4, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 8),
+			/* spill unchecked sk_ptr into stack of caller */
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, -8),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_5, 0),
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_0, 0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+			/* now the sk_ptr is verified, free the reference */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_4, 0),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+
+			/* subprog 2 */
+			BPF_SK_LOOKUP,
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: allow LD_ABS",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_LD_ABS(BPF_B, 0),
+			BPF_LD_ABS(BPF_H, 0),
+			BPF_LD_ABS(BPF_W, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: forbid LD_ABS while holding reference",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_SK_LOOKUP,
+			BPF_LD_ABS(BPF_B, 0),
+			BPF_LD_ABS(BPF_H, 0),
+			BPF_LD_ABS(BPF_W, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "BPF_LD_[ABS|IND] cannot be mixed with socket references",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: allow LD_IND",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_MOV64_IMM(BPF_REG_7, 1),
+			BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"reference tracking: forbid LD_IND while holding reference",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_7, 1),
+			BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_4),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "BPF_LD_[ABS|IND] cannot be mixed with socket references",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: check reference or tail call",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
+			BPF_SK_LOOKUP,
+			/* if (sk) bpf_sk_release() */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 7),
+			/* bpf_tail_call() */
+			BPF_MOV64_IMM(BPF_REG_3, 2),
+			BPF_LD_MAP_FD(BPF_REG_2, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_tail_call),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_prog1 = { 17 },
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: release reference then tail call",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
+			BPF_SK_LOOKUP,
+			/* if (sk) bpf_sk_release() */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			/* bpf_tail_call() */
+			BPF_MOV64_IMM(BPF_REG_3, 2),
+			BPF_LD_MAP_FD(BPF_REG_2, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_tail_call),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_prog1 = { 18 },
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: leak possible reference over tail call",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
+			/* Look up socket and store in REG_6 */
+			BPF_SK_LOOKUP,
+			/* bpf_tail_call() */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_3, 2),
+			BPF_LD_MAP_FD(BPF_REG_2, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_tail_call),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			/* if (sk) bpf_sk_release() */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_prog1 = { 16 },
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "tail_call would lead to reference leak",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: leak checked reference over tail call",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
+			/* Look up socket and store in REG_6 */
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			/* if (!sk) goto end */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+			/* bpf_tail_call() */
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_LD_MAP_FD(BPF_REG_2, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_tail_call),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_prog1 = { 17 },
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "tail_call would lead to reference leak",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: mangle and release sock_or_null",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 5),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "R1 pointer arithmetic on sock_or_null prohibited",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: mangle and release sock",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 5),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "R1 pointer arithmetic on sock prohibited",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: access member",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_0, 4),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: write to member",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_LD_IMM64(BPF_REG_2, 42),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_2,
+				    offsetof(struct bpf_sock, mark)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_LD_IMM64(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "cannot write into socket",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: invalid 64-bit access of member",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "invalid bpf_sock access off=0 size=8",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: access after release",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "!read_ok",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: direct access for lookup",
+		.insns = {
+			/* Check that the packet is at least 64B long */
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 64),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 9),
+			/* sk = sk_lookup_tcp(ctx, skb->data, ...) */
+			BPF_MOV64_IMM(BPF_REG_3, sizeof(struct bpf_sock_tuple)),
+			BPF_MOV64_IMM(BPF_REG_4, 0),
+			BPF_MOV64_IMM(BPF_REG_5, 0),
+			BPF_EMIT_CALL(BPF_FUNC_sk_lookup_tcp),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_0, 4),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
-- 
cgit 


From de375f4e91e3074a09ad337ac4b32a2f21c24d96 Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@wand.net.nz>
Date: Tue, 2 Oct 2018 13:35:40 -0700
Subject: selftests/bpf: Add C tests for reference tracking

Add some tests that demonstrate and test the balanced lookup/free
nature of socket lookup. Section names that start with "fail" represent
programs that are expected to fail verification; all others should
succeed.

Signed-off-by: Joe Stringer <joe@wand.net.nz>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/Makefile              |   2 +-
 tools/testing/selftests/bpf/test_progs.c          |  38 +++++
 tools/testing/selftests/bpf/test_sk_lookup_kern.c | 180 ++++++++++++++++++++++
 3 files changed, 219 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/test_sk_lookup_kern.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index f802de526f57..1381ab81099c 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -36,7 +36,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \
 	test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
 	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
-	test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o
+	test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o test_sk_lookup_kern.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 63a671803ed6..e8becca9c521 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -1698,6 +1698,43 @@ static void test_task_fd_query_tp(void)
 				   "sys_enter_read");
 }
 
+static void test_reference_tracking()
+{
+	const char *file = "./test_sk_lookup_kern.o";
+	struct bpf_object *obj;
+	struct bpf_program *prog;
+	__u32 duration;
+	int err = 0;
+
+	obj = bpf_object__open(file);
+	if (IS_ERR(obj)) {
+		error_cnt++;
+		return;
+	}
+
+	bpf_object__for_each_program(prog, obj) {
+		const char *title;
+
+		/* Ignore .text sections */
+		title = bpf_program__title(prog, false);
+		if (strstr(title, ".text") != NULL)
+			continue;
+
+		bpf_program__set_type(prog, BPF_PROG_TYPE_SCHED_CLS);
+
+		/* Expect verifier failure if test name has 'fail' */
+		if (strstr(title, "fail") != NULL) {
+			libbpf_set_print(NULL, NULL, NULL);
+			err = !bpf_program__load(prog, "GPL", 0);
+			libbpf_set_print(printf, printf, NULL);
+		} else {
+			err = bpf_program__load(prog, "GPL", 0);
+		}
+		CHECK(err, title, "\n");
+	}
+	bpf_object__close(obj);
+}
+
 int main(void)
 {
 	jit_enabled = is_jit_enabled();
@@ -1719,6 +1756,7 @@ int main(void)
 	test_get_stack_raw_tp();
 	test_task_fd_query_rawtp();
 	test_task_fd_query_tp();
+	test_reference_tracking();
 
 	printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
 	return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS;
diff --git a/tools/testing/selftests/bpf/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/test_sk_lookup_kern.c
new file mode 100644
index 000000000000..b745bdc08c2b
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_sk_lookup_kern.c
@@ -0,0 +1,180 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
+
+#include <stddef.h>
+#include <stdbool.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/pkt_cls.h>
+#include <linux/tcp.h>
+#include <sys/socket.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+int _version SEC("version") = 1;
+char _license[] SEC("license") = "GPL";
+
+/* Fill 'tuple' with L3 info, and attempt to find L4. On fail, return NULL. */
+static struct bpf_sock_tuple *get_tuple(void *data, __u64 nh_off,
+					void *data_end, __u16 eth_proto,
+					bool *ipv4)
+{
+	struct bpf_sock_tuple *result;
+	__u8 proto = 0;
+	__u64 ihl_len;
+
+	if (eth_proto == bpf_htons(ETH_P_IP)) {
+		struct iphdr *iph = (struct iphdr *)(data + nh_off);
+
+		if (iph + 1 > data_end)
+			return NULL;
+		ihl_len = iph->ihl * 4;
+		proto = iph->protocol;
+		*ipv4 = true;
+		result = (struct bpf_sock_tuple *)&iph->saddr;
+	} else if (eth_proto == bpf_htons(ETH_P_IPV6)) {
+		struct ipv6hdr *ip6h = (struct ipv6hdr *)(data + nh_off);
+
+		if (ip6h + 1 > data_end)
+			return NULL;
+		ihl_len = sizeof(*ip6h);
+		proto = ip6h->nexthdr;
+		*ipv4 = true;
+		result = (struct bpf_sock_tuple *)&ip6h->saddr;
+	}
+
+	if (data + nh_off + ihl_len > data_end || proto != IPPROTO_TCP)
+		return NULL;
+
+	return result;
+}
+
+SEC("sk_lookup_success")
+int bpf_sk_lookup_test0(struct __sk_buff *skb)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *data = (void *)(long)skb->data;
+	struct ethhdr *eth = (struct ethhdr *)(data);
+	struct bpf_sock_tuple *tuple;
+	struct bpf_sock *sk;
+	size_t tuple_len;
+	bool ipv4;
+
+	if (eth + 1 > data_end)
+		return TC_ACT_SHOT;
+
+	tuple = get_tuple(data, sizeof(*eth), data_end, eth->h_proto, &ipv4);
+	if (!tuple || tuple + sizeof *tuple > data_end)
+		return TC_ACT_SHOT;
+
+	tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6);
+	sk = bpf_sk_lookup_tcp(skb, tuple, tuple_len, 0, 0);
+	if (sk)
+		bpf_sk_release(sk);
+	return sk ? TC_ACT_OK : TC_ACT_UNSPEC;
+}
+
+SEC("sk_lookup_success_simple")
+int bpf_sk_lookup_test1(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	struct bpf_sock *sk;
+
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	if (sk)
+		bpf_sk_release(sk);
+	return 0;
+}
+
+SEC("fail_use_after_free")
+int bpf_sk_lookup_uaf(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	struct bpf_sock *sk;
+	__u32 family = 0;
+
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	if (sk) {
+		bpf_sk_release(sk);
+		family = sk->family;
+	}
+	return family;
+}
+
+SEC("fail_modify_sk_pointer")
+int bpf_sk_lookup_modptr(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	struct bpf_sock *sk;
+	__u32 family;
+
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	if (sk) {
+		sk += 1;
+		bpf_sk_release(sk);
+	}
+	return 0;
+}
+
+SEC("fail_modify_sk_or_null_pointer")
+int bpf_sk_lookup_modptr_or_null(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	struct bpf_sock *sk;
+	__u32 family;
+
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	sk += 1;
+	if (sk)
+		bpf_sk_release(sk);
+	return 0;
+}
+
+SEC("fail_no_release")
+int bpf_sk_lookup_test2(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+
+	bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	return 0;
+}
+
+SEC("fail_release_twice")
+int bpf_sk_lookup_test3(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	struct bpf_sock *sk;
+
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	bpf_sk_release(sk);
+	bpf_sk_release(sk);
+	return 0;
+}
+
+SEC("fail_release_unchecked")
+int bpf_sk_lookup_test4(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	struct bpf_sock *sk;
+
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	bpf_sk_release(sk);
+	return 0;
+}
+
+void lookup_no_release(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+}
+
+SEC("fail_no_release_subcall")
+int bpf_sk_lookup_test5(struct __sk_buff *skb)
+{
+	lookup_no_release(skb);
+	return 0;
+}
-- 
cgit 


From fc35ef12dc8ba8633a99c9d9df03a5bb53f1dda3 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 20 Sep 2018 13:45:07 -0300
Subject: selftests/powerpc: New PTRACE_SYSEMU test

This patch adds a new test for the new PTRACE_SYSEMU ptrace request.

This test also relies on PTRACE_GETREGS and PTRACE_SETREGS requests to
run properly, since the trace instruction (gettid() syscall) is being
modified at run-time (by PTRACE_SETREGS) and re-executed three times.
PTRACE_GETREGS is being used to check that the registers are still
sane.

This test basically creates a child process that executes syscalls
and the parent process check if it is being traced appropriately.  The
parent process guarantees that the SYSCALLs are being traced, with
PTRACE_SYSEMU, and ptrace stops the child application before a syscall is
executed. The way the tests validates it, is by guaranteeing that the
system calls arguments, as argv[0] (r3) which is the same register that
will have the syscall return value on powerpc, are not being corrupted on
PTRACE_SYSEMU with a return value, i.e, it continues to have the current
arguments instead, meaning that the registers where not clobbered.

This test is basically the same test for x86 located at
tools/testing/selftests/x86/ptrace_syscall.c, limited to test PTRACE_SYSEMU
request, and ported to PowerPC.

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/ptrace/Makefile    |   2 +-
 .../selftests/powerpc/ptrace/ptrace-syscall.c      | 228 +++++++++++++++++++++
 2 files changed, 229 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/powerpc/ptrace/ptrace-syscall.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile
index 28f5b781a553..1ee59978508d 100644
--- a/tools/testing/selftests/powerpc/ptrace/Makefile
+++ b/tools/testing/selftests/powerpc/ptrace/Makefile
@@ -2,7 +2,7 @@
 TEST_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \
               ptrace-tar ptrace-tm-tar ptrace-tm-spd-tar ptrace-vsx ptrace-tm-vsx \
               ptrace-tm-spd-vsx ptrace-tm-spr ptrace-hwbreak ptrace-pkey core-pkey \
-              perf-hwbreak
+              perf-hwbreak ptrace-syscall
 
 include ../../lib.mk
 
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-syscall.c b/tools/testing/selftests/powerpc/ptrace/ptrace-syscall.c
new file mode 100644
index 000000000000..3353210dcdbd
--- /dev/null
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-syscall.c
@@ -0,0 +1,228 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A ptrace test for testing PTRACE_SYSEMU, PTRACE_SETREGS and
+ * PTRACE_GETREG.  This test basically create a child process that executes
+ * syscalls and the parent process check if it is being traced appropriated.
+ *
+ * This test is heavily based on tools/testing/selftests/x86/ptrace_syscall.c
+ * test, and it was adapted to run on Powerpc by
+ * Breno Leitao <leitao@debian.org>
+ */
+#define _GNU_SOURCE
+
+#include <sys/ptrace.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/syscall.h>
+#include <sys/user.h>
+#include <unistd.h>
+#include <errno.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <err.h>
+#include <string.h>
+#include <sys/auxv.h>
+#include "utils.h"
+
+/* Bitness-agnostic defines for user_regs_struct fields. */
+#define user_syscall_nr	gpr[0]
+#define user_arg0		gpr[3]
+#define user_arg1		gpr[4]
+#define user_arg2		gpr[5]
+#define user_arg3		gpr[6]
+#define user_arg4		gpr[7]
+#define user_arg5		gpr[8]
+#define user_ip		nip
+
+#define PTRACE_SYSEMU		0x1d
+
+static int nerrs;
+
+static void wait_trap(pid_t chld)
+{
+	siginfo_t si;
+
+	if (waitid(P_PID, chld, &si, WEXITED|WSTOPPED) != 0)
+		err(1, "waitid");
+	if (si.si_pid != chld)
+		errx(1, "got unexpected pid in event\n");
+	if (si.si_code != CLD_TRAPPED)
+		errx(1, "got unexpected event type %d\n", si.si_code);
+}
+
+static void test_ptrace_syscall_restart(void)
+{
+	int status;
+	struct pt_regs regs;
+	pid_t chld;
+
+	printf("[RUN]\tptrace-induced syscall restart\n");
+
+	chld = fork();
+	if (chld < 0)
+		err(1, "fork");
+
+	/*
+	 * Child process is running 4 syscalls after ptrace.
+	 *
+	 * 1) getpid()
+	 * 2) gettid()
+	 * 3) tgkill() -> Send SIGSTOP
+	 * 4) gettid() -> Where the tests will happen essentially
+	 */
+	if (chld == 0) {
+		if (ptrace(PTRACE_TRACEME, 0, 0, 0) != 0)
+			err(1, "PTRACE_TRACEME");
+
+		pid_t pid = getpid(), tid = syscall(SYS_gettid);
+
+		printf("\tChild will make one syscall\n");
+		syscall(SYS_tgkill, pid, tid, SIGSTOP);
+
+		syscall(SYS_gettid, 10, 11, 12, 13, 14, 15);
+		_exit(0);
+	}
+	/* Parent process below */
+
+	/* Wait for SIGSTOP sent by tgkill above. */
+	if (waitpid(chld, &status, 0) != chld || !WIFSTOPPED(status))
+		err(1, "waitpid");
+
+	printf("[RUN]\tSYSEMU\n");
+	if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0)
+		err(1, "PTRACE_SYSEMU");
+	wait_trap(chld);
+
+	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_GETREGS");
+
+	/*
+	 * Ptrace trapped prior to executing the syscall, thus r3 still has
+	 * the syscall number instead of the sys_gettid() result
+	 */
+	if (regs.user_syscall_nr != SYS_gettid ||
+	    regs.user_arg0 != 10 || regs.user_arg1 != 11 ||
+	    regs.user_arg2 != 12 || regs.user_arg3 != 13 ||
+	    regs.user_arg4 != 14 || regs.user_arg5 != 15) {
+		printf("[FAIL]\tInitial args are wrong (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n",
+			(unsigned long)regs.user_syscall_nr,
+			(unsigned long)regs.user_arg0,
+			(unsigned long)regs.user_arg1,
+			(unsigned long)regs.user_arg2,
+			(unsigned long)regs.user_arg3,
+			(unsigned long)regs.user_arg4,
+			(unsigned long)regs.user_arg5);
+		 nerrs++;
+	} else {
+		printf("[OK]\tInitial nr and args are correct\n"); }
+
+	printf("[RUN]\tRestart the syscall (ip = 0x%lx)\n",
+	       (unsigned long)regs.user_ip);
+
+	/*
+	 * Rewind to retry the same syscall again. This will basically test
+	 * the rewind process together with PTRACE_SETREGS and PTRACE_GETREGS.
+	 */
+	regs.user_ip -= 4;
+	if (ptrace(PTRACE_SETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_SETREGS");
+
+	if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0)
+		err(1, "PTRACE_SYSEMU");
+	wait_trap(chld);
+
+	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_GETREGS");
+
+	if (regs.user_syscall_nr != SYS_gettid ||
+	    regs.user_arg0 != 10 || regs.user_arg1 != 11 ||
+	    regs.user_arg2 != 12 || regs.user_arg3 != 13 ||
+	    regs.user_arg4 != 14 || regs.user_arg5 != 15) {
+		printf("[FAIL]\tRestart nr or args are wrong (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n",
+			(unsigned long)regs.user_syscall_nr,
+			(unsigned long)regs.user_arg0,
+			(unsigned long)regs.user_arg1,
+			(unsigned long)regs.user_arg2,
+			(unsigned long)regs.user_arg3,
+			(unsigned long)regs.user_arg4,
+			(unsigned long)regs.user_arg5);
+		nerrs++;
+	} else {
+		printf("[OK]\tRestarted nr and args are correct\n");
+	}
+
+	printf("[RUN]\tChange nr and args and restart the syscall (ip = 0x%lx)\n",
+	       (unsigned long)regs.user_ip);
+
+	/*
+	 * Inject a new syscall (getpid) in the same place the previous
+	 * syscall (gettid), rewind and re-execute.
+	 */
+	regs.user_syscall_nr = SYS_getpid;
+	regs.user_arg0 = 20;
+	regs.user_arg1 = 21;
+	regs.user_arg2 = 22;
+	regs.user_arg3 = 23;
+	regs.user_arg4 = 24;
+	regs.user_arg5 = 25;
+	regs.user_ip -= 4;
+
+	if (ptrace(PTRACE_SETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_SETREGS");
+
+	if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0)
+		err(1, "PTRACE_SYSEMU");
+	wait_trap(chld);
+
+	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_GETREGS");
+
+	/* Check that ptrace stopped at the new syscall that was
+	 * injected, and guarantee that it haven't executed, i.e, user_args
+	 * contain the arguments and not the syscall return value, for
+	 * instance.
+	 */
+	if (regs.user_syscall_nr != SYS_getpid
+		|| regs.user_arg0 != 20 || regs.user_arg1 != 21
+		|| regs.user_arg2 != 22 || regs.user_arg3 != 23
+		|| regs.user_arg4 != 24 || regs.user_arg5 != 25) {
+
+		printf("[FAIL]\tRestart nr or args are wrong (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n",
+			(unsigned long)regs.user_syscall_nr,
+			(unsigned long)regs.user_arg0,
+			(unsigned long)regs.user_arg1,
+			(unsigned long)regs.user_arg2,
+			(unsigned long)regs.user_arg3,
+			(unsigned long)regs.user_arg4,
+			(unsigned long)regs.user_arg5);
+		nerrs++;
+	} else {
+		printf("[OK]\tReplacement nr and args are correct\n");
+	}
+
+	if (ptrace(PTRACE_CONT, chld, 0, 0) != 0)
+		err(1, "PTRACE_CONT");
+
+	if (waitpid(chld, &status, 0) != chld)
+		err(1, "waitpid");
+
+	/* Guarantee that the process executed properly, returning 0 */
+	if (!WIFEXITED(status) || WEXITSTATUS(status) != 0) {
+		printf("[FAIL]\tChild failed\n");
+		nerrs++;
+	} else {
+		printf("[OK]\tChild exited cleanly\n");
+	}
+}
+
+int ptrace_syscall(void)
+{
+	test_ptrace_syscall_restart();
+
+	return nerrs;
+}
+
+int main(void)
+{
+	return test_harness(ptrace_syscall, "ptrace_syscall");
+}
-- 
cgit 


From 02e425668f5c9deb42787d10001a3b605993ad15 Mon Sep 17 00:00:00 2001
From: Andy Lutomirski <luto@kernel.org>
Date: Wed, 3 Oct 2018 16:23:49 -0700
Subject: x86/vdso: Fix vDSO syscall fallback asm constraint regression

When I added the missing memory outputs, I failed to update the
index of the first argument (ebx) on 32-bit builds, which broke the
fallbacks.  Somehow I must have screwed up my testing or gotten
lucky.

Add another test to cover gettimeofday() as well.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Fixes: 715bd9d12f84 ("x86/vdso: Fix asm constraints on vDSO syscall fallbacks")
Link: http://lkml.kernel.org/r/21bd45ab04b6d838278fa5bebfa9163eceffa13c.1538608971.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/entry/vdso/vclock_gettime.c    |  8 ++--
 tools/testing/selftests/x86/test_vdso.c | 73 +++++++++++++++++++++++++++++++++
 2 files changed, 77 insertions(+), 4 deletions(-)

(limited to 'tools/testing')

diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 134e2d2e8add..e48ca3afa091 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -68,11 +68,11 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 
 	asm (
 		"mov %%ebx, %%edx \n"
-		"mov %2, %%ebx \n"
+		"mov %[clock], %%ebx \n"
 		"call __kernel_vsyscall \n"
 		"mov %%edx, %%ebx \n"
 		: "=a" (ret), "=m" (*ts)
-		: "0" (__NR_clock_gettime), "g" (clock), "c" (ts)
+		: "0" (__NR_clock_gettime), [clock] "g" (clock), "c" (ts)
 		: "memory", "edx");
 	return ret;
 }
@@ -83,11 +83,11 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
 
 	asm (
 		"mov %%ebx, %%edx \n"
-		"mov %2, %%ebx \n"
+		"mov %[tv], %%ebx \n"
 		"call __kernel_vsyscall \n"
 		"mov %%edx, %%ebx \n"
 		: "=a" (ret), "=m" (*tv), "=m" (*tz)
-		: "0" (__NR_gettimeofday), "g" (tv), "c" (tz)
+		: "0" (__NR_gettimeofday), [tv] "g" (tv), "c" (tz)
 		: "memory", "edx");
 	return ret;
 }
diff --git a/tools/testing/selftests/x86/test_vdso.c b/tools/testing/selftests/x86/test_vdso.c
index 49f7294fb382..35edd61d1663 100644
--- a/tools/testing/selftests/x86/test_vdso.c
+++ b/tools/testing/selftests/x86/test_vdso.c
@@ -36,6 +36,10 @@ typedef int (*vgettime_t)(clockid_t, struct timespec *);
 
 vgettime_t vdso_clock_gettime;
 
+typedef long (*vgtod_t)(struct timeval *tv, struct timezone *tz);
+
+vgtod_t vdso_gettimeofday;
+
 typedef long (*getcpu_t)(unsigned *, unsigned *, void *);
 
 getcpu_t vgetcpu;
@@ -104,6 +108,11 @@ static void fill_function_pointers()
 	vdso_clock_gettime = (vgettime_t)dlsym(vdso, "__vdso_clock_gettime");
 	if (!vdso_clock_gettime)
 		printf("Warning: failed to find clock_gettime in vDSO\n");
+
+	vdso_gettimeofday = (vgtod_t)dlsym(vdso, "__vdso_gettimeofday");
+	if (!vdso_gettimeofday)
+		printf("Warning: failed to find gettimeofday in vDSO\n");
+
 }
 
 static long sys_getcpu(unsigned * cpu, unsigned * node,
@@ -117,6 +126,11 @@ static inline int sys_clock_gettime(clockid_t id, struct timespec *ts)
 	return syscall(__NR_clock_gettime, id, ts);
 }
 
+static inline int sys_gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+	return syscall(__NR_gettimeofday, tv, tz);
+}
+
 static void test_getcpu(void)
 {
 	printf("[RUN]\tTesting getcpu...\n");
@@ -177,6 +191,14 @@ static bool ts_leq(const struct timespec *a, const struct timespec *b)
 		return a->tv_nsec <= b->tv_nsec;
 }
 
+static bool tv_leq(const struct timeval *a, const struct timeval *b)
+{
+	if (a->tv_sec != b->tv_sec)
+		return a->tv_sec < b->tv_sec;
+	else
+		return a->tv_usec <= b->tv_usec;
+}
+
 static char const * const clocknames[] = {
 	[0] = "CLOCK_REALTIME",
 	[1] = "CLOCK_MONOTONIC",
@@ -248,11 +270,62 @@ static void test_clock_gettime(void)
 	test_one_clock_gettime(INT_MAX, "invalid");
 }
 
+static void test_gettimeofday(void)
+{
+	struct timeval start, vdso, end;
+	struct timezone sys_tz, vdso_tz;
+	int vdso_ret, end_ret;
+
+	if (!vdso_gettimeofday)
+		return;
+
+	printf("[RUN]\tTesting gettimeofday...\n");
+
+	if (sys_gettimeofday(&start, &sys_tz) < 0) {
+		printf("[FAIL]\tsys_gettimeofday failed (%d)\n", errno);
+		nerrs++;
+		return;
+	}
+
+	vdso_ret = vdso_gettimeofday(&vdso, &vdso_tz);
+	end_ret = sys_gettimeofday(&end, NULL);
+
+	if (vdso_ret != 0 || end_ret != 0) {
+		printf("[FAIL]\tvDSO returned %d, syscall errno=%d\n",
+		       vdso_ret, errno);
+		nerrs++;
+		return;
+	}
+
+	printf("\t%llu.%06ld %llu.%06ld %llu.%06ld\n",
+	       (unsigned long long)start.tv_sec, start.tv_usec,
+	       (unsigned long long)vdso.tv_sec, vdso.tv_usec,
+	       (unsigned long long)end.tv_sec, end.tv_usec);
+
+	if (!tv_leq(&start, &vdso) || !tv_leq(&vdso, &end)) {
+		printf("[FAIL]\tTimes are out of sequence\n");
+		nerrs++;
+	}
+
+	if (sys_tz.tz_minuteswest == vdso_tz.tz_minuteswest &&
+	    sys_tz.tz_dsttime == vdso_tz.tz_dsttime) {
+		printf("[OK]\ttimezones match: minuteswest=%d, dsttime=%d\n",
+		       sys_tz.tz_minuteswest, sys_tz.tz_dsttime);
+	} else {
+		printf("[FAIL]\ttimezones do not match\n");
+		nerrs++;
+	}
+
+	/* And make sure that passing NULL for tz doesn't crash. */
+	vdso_gettimeofday(&vdso, NULL);
+}
+
 int main(int argc, char **argv)
 {
 	fill_function_pointers();
 
 	test_clock_gettime();
+	test_gettimeofday();
 
 	/*
 	 * Test getcpu() last so that, if something goes wrong setting affinity,
-- 
cgit 


From a0e11da78f487bc26ca7b14e4c9b40638623ebf6 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Thu, 4 Oct 2018 20:07:55 -0700
Subject: fib_tests: Add tests for metrics on routes

Add ipv4 and ipv6 test cases for metrics (mtu) when fib entries are
created. Can be used with kmemleak to see leaks with both fib entries
and dst_entry.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_tests.sh | 157 +++++++++++++++++++++++++++----
 1 file changed, 138 insertions(+), 19 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 0f45633bd634..491332713dd9 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -9,11 +9,11 @@ ret=0
 ksft_skip=4
 
 # all tests in this script. Can be overridden with -t option
-TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric"
+TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics"
 VERBOSE=0
 PAUSE_ON_FAIL=no
 PAUSE=no
-IP="ip -netns testns"
+IP="ip -netns ns1"
 
 log_test()
 {
@@ -47,8 +47,10 @@ log_test()
 setup()
 {
 	set -e
-	ip netns add testns
+	ip netns add ns1
 	$IP link set dev lo up
+	ip netns exec ns1 sysctl -qw net.ipv4.ip_forward=1
+	ip netns exec ns1 sysctl -qw net.ipv6.conf.all.forwarding=1
 
 	$IP link add dummy0 type dummy
 	$IP link set dev dummy0 up
@@ -61,7 +63,8 @@ setup()
 cleanup()
 {
 	$IP link del dev dummy0 &> /dev/null
-	ip netns del testns
+	ip netns del ns1
+	ip netns del ns2 &> /dev/null
 }
 
 get_linklocal()
@@ -639,11 +642,14 @@ add_initial_route6()
 
 check_route6()
 {
-	local pfx="2001:db8:104::/64"
+	local pfx
 	local expected="$1"
 	local out
 	local rc=0
 
+	set -- $expected
+	pfx=$1
+
 	out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//')
 	[ "${out}" = "${expected}" ] && return 0
 
@@ -690,28 +696,33 @@ route_setup()
 	[ "${VERBOSE}" = "1" ] && set -x
 	set -e
 
-	$IP li add red up type vrf table 101
+	ip netns add ns2
+	ip -netns ns2 link set dev lo up
+	ip netns exec ns2 sysctl -qw net.ipv4.ip_forward=1
+	ip netns exec ns2 sysctl -qw net.ipv6.conf.all.forwarding=1
+
 	$IP li add veth1 type veth peer name veth2
 	$IP li add veth3 type veth peer name veth4
 
 	$IP li set veth1 up
 	$IP li set veth3 up
-	$IP li set veth2 vrf red up
-	$IP li set veth4 vrf red up
-	$IP li add dummy1 type dummy
-	$IP li set dummy1 vrf red up
+	$IP li set veth2 netns ns2 up
+	$IP li set veth4 netns ns2 up
+	ip -netns ns2 li add dummy1 type dummy
+	ip -netns ns2 li set dummy1 up
 
 	$IP -6 addr add 2001:db8:101::1/64 dev veth1
-	$IP -6 addr add 2001:db8:101::2/64 dev veth2
 	$IP -6 addr add 2001:db8:103::1/64 dev veth3
-	$IP -6 addr add 2001:db8:103::2/64 dev veth4
-	$IP -6 addr add 2001:db8:104::1/64 dev dummy1
-
 	$IP addr add 172.16.101.1/24 dev veth1
-	$IP addr add 172.16.101.2/24 dev veth2
 	$IP addr add 172.16.103.1/24 dev veth3
-	$IP addr add 172.16.103.2/24 dev veth4
-	$IP addr add 172.16.104.1/24 dev dummy1
+
+	ip -netns ns2 -6 addr add 2001:db8:101::2/64 dev veth2
+	ip -netns ns2 -6 addr add 2001:db8:103::2/64 dev veth4
+	ip -netns ns2 -6 addr add 2001:db8:104::1/64 dev dummy1
+
+	ip -netns ns2 addr add 172.16.101.2/24 dev veth2
+	ip -netns ns2 addr add 172.16.103.2/24 dev veth4
+	ip -netns ns2 addr add 172.16.104.1/24 dev dummy1
 
 	set +ex
 }
@@ -944,7 +955,7 @@ ipv6_addr_metric_test()
 	log_test $rc 0 "Modify metric of address"
 
 	# verify prefix route removed on down
-	run_cmd "ip netns exec testns sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1"
+	run_cmd "ip netns exec ns1 sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1"
 	run_cmd "$IP li set dev dummy2 down"
 	rc=$?
 	if [ $rc -eq 0 ]; then
@@ -967,6 +978,74 @@ ipv6_addr_metric_test()
 	cleanup
 }
 
+ipv6_route_metrics_test()
+{
+	local rc
+
+	echo
+	echo "IPv6 routes with metrics"
+
+	route_setup
+
+	#
+	# single path with metrics
+	#
+	run_cmd "$IP -6 ro add 2001:db8:111::/64 via 2001:db8:101::2 mtu 1400"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route6  "2001:db8:111::/64 via 2001:db8:101::2 dev veth1 metric 1024 mtu 1400"
+		rc=$?
+	fi
+	log_test $rc 0 "Single path route with mtu metric"
+
+
+	#
+	# multipath via separate routes with metrics
+	#
+	run_cmd "$IP -6 ro add 2001:db8:112::/64 via 2001:db8:101::2 mtu 1400"
+	run_cmd "$IP -6 ro append 2001:db8:112::/64 via 2001:db8:103::2"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route6 "2001:db8:112::/64 metric 1024 mtu 1400 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
+		rc=$?
+	fi
+	log_test $rc 0 "Multipath route via 2 single routes with mtu metric on first"
+
+	# second route is coalesced to first to make a multipath route.
+	# MTU of the second path is hidden from display!
+	run_cmd "$IP -6 ro add 2001:db8:113::/64 via 2001:db8:101::2"
+	run_cmd "$IP -6 ro append 2001:db8:113::/64 via 2001:db8:103::2 mtu 1400"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route6 "2001:db8:113::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
+		rc=$?
+	fi
+	log_test $rc 0 "Multipath route via 2 single routes with mtu metric on 2nd"
+
+	run_cmd "$IP -6 ro del 2001:db8:113::/64 via 2001:db8:101::2"
+	if [ $? -eq 0 ]; then
+		check_route6 "2001:db8:113::/64 via 2001:db8:103::2 dev veth3 metric 1024 mtu 1400"
+		log_test $? 0 "    MTU of second leg"
+	fi
+
+	#
+	# multipath with metrics
+	#
+	run_cmd "$IP -6 ro add 2001:db8:115::/64 mtu 1400 nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route6  "2001:db8:115::/64 metric 1024 mtu 1400 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
+		rc=$?
+	fi
+	log_test $rc 0 "Multipath route with mtu metric"
+
+	$IP -6 ro add 2001:db8:104::/64 via 2001:db8:101::2 mtu 1300
+	run_cmd "ip netns exec ns1 ping6 -w1 -c1 -s 1500 2001:db8:104::1"
+	log_test $? 0 "Using route with mtu metric"
+
+	route_cleanup
+}
+
 # add route for a prefix, flushing any existing routes first
 # expected to be the first step of a test
 add_route()
@@ -1005,11 +1084,15 @@ add_initial_route()
 
 check_route()
 {
-	local pfx="172.16.104.0/24"
+	local pfx
 	local expected="$1"
 	local out
 	local rc=0
 
+	set -- $expected
+	pfx=$1
+	[ "${pfx}" = "unreachable" ] && pfx=$2
+
 	out=$($IP ro ls match ${pfx})
 	[ "${out}" = "${expected}" ] && return 0
 
@@ -1319,6 +1402,40 @@ ipv4_addr_metric_test()
 	cleanup
 }
 
+ipv4_route_metrics_test()
+{
+	local rc
+
+	echo
+	echo "IPv4 route add / append tests"
+
+	route_setup
+
+	run_cmd "$IP ro add 172.16.111.0/24 via 172.16.101.2 mtu 1400"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route "172.16.111.0/24 via 172.16.101.2 dev veth1 mtu 1400"
+		rc=$?
+	fi
+	log_test $rc 0 "Single path route with mtu metric"
+
+
+	run_cmd "$IP ro add 172.16.112.0/24 mtu 1400 nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route "172.16.112.0/24 mtu 1400 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1"
+		rc=$?
+	fi
+	log_test $rc 0 "Multipath route with mtu metric"
+
+	$IP ro add 172.16.104.0/24 via 172.16.101.2 mtu 1300
+	run_cmd "ip netns exec ns1 ping -w1 -c1 -s 1500 172.16.104.1"
+	log_test $? 0 "Using route with mtu metric"
+
+	route_cleanup
+}
+
+
 ################################################################################
 # usage
 
@@ -1385,6 +1502,8 @@ do
 	ipv4_route_test|ipv4_rt)	ipv4_route_test;;
 	ipv6_addr_metric)		ipv6_addr_metric_test;;
 	ipv4_addr_metric)		ipv4_addr_metric_test;;
+	ipv6_route_metrics)		ipv6_route_metrics_test;;
+	ipv4_route_metrics)		ipv4_route_metrics_test;;
 
 	help) echo "Test names: $TESTS"; exit 0;;
 	esac
-- 
cgit 


From 226407dd0311eebfb55a63deae9a9dcf71f920af Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 5 Oct 2018 10:01:19 -0700
Subject: fib_tests: Add tests for invalid metric on route

Add ipv4 and ipv6 test cases with an invalid metrics option causing
ip_metrics_convert to fail. Tests clean up path during route add.

Also, add nodad to to ipv6 address add. When running ipv6_route_metrics
directly seeing an occasional failure on the "Using route with mtu metric"
test case.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_tests.sh | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 491332713dd9..802b4af18729 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -711,14 +711,14 @@ route_setup()
 	ip -netns ns2 li add dummy1 type dummy
 	ip -netns ns2 li set dummy1 up
 
-	$IP -6 addr add 2001:db8:101::1/64 dev veth1
-	$IP -6 addr add 2001:db8:103::1/64 dev veth3
+	$IP -6 addr add 2001:db8:101::1/64 dev veth1 nodad
+	$IP -6 addr add 2001:db8:103::1/64 dev veth3 nodad
 	$IP addr add 172.16.101.1/24 dev veth1
 	$IP addr add 172.16.103.1/24 dev veth3
 
-	ip -netns ns2 -6 addr add 2001:db8:101::2/64 dev veth2
-	ip -netns ns2 -6 addr add 2001:db8:103::2/64 dev veth4
-	ip -netns ns2 -6 addr add 2001:db8:104::1/64 dev dummy1
+	ip -netns ns2 -6 addr add 2001:db8:101::2/64 dev veth2 nodad
+	ip -netns ns2 -6 addr add 2001:db8:103::2/64 dev veth4 nodad
+	ip -netns ns2 -6 addr add 2001:db8:104::1/64 dev dummy1 nodad
 
 	ip -netns ns2 addr add 172.16.101.2/24 dev veth2
 	ip -netns ns2 addr add 172.16.103.2/24 dev veth4
@@ -1043,6 +1043,9 @@ ipv6_route_metrics_test()
 	run_cmd "ip netns exec ns1 ping6 -w1 -c1 -s 1500 2001:db8:104::1"
 	log_test $? 0 "Using route with mtu metric"
 
+	run_cmd "$IP -6 ro add 2001:db8:114::/64 via  2001:db8:101::2  congctl lock foo"
+	log_test $? 2 "Invalid metric (fails metric_convert)"
+
 	route_cleanup
 }
 
@@ -1432,6 +1435,9 @@ ipv4_route_metrics_test()
 	run_cmd "ip netns exec ns1 ping -w1 -c1 -s 1500 172.16.104.1"
 	log_test $? 0 "Using route with mtu metric"
 
+	run_cmd "$IP ro add 172.16.111.0/24 via 172.16.101.2 congctl lock foo"
+	log_test $? 2 "Invalid metric (fails metric_convert)"
+
 	route_cleanup
 }
 
-- 
cgit 


From cf5eafbfa586d030f9321cee516b91d089e38280 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Thu, 4 Oct 2018 18:34:38 +0200
Subject: tc-testing: fix build of eBPF programs

rely on uAPI headers in the current kernel tree, rather than requiring the
correct version installed on the test system. While at it, group all
sections in a single binary and test the 'section' parameter.

Reported-by: Lucas Bates <lucasb@mojatatu.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/bpf/Makefile    | 29 ++++++++++++++++++++++
 tools/testing/selftests/tc-testing/bpf/action.c    | 23 +++++++++++++++++
 .../selftests/tc-testing/tc-tests/actions/bpf.json | 16 ++++++------
 tools/testing/selftests/tc-testing/tdc_config.py   |  4 ++-
 4 files changed, 63 insertions(+), 9 deletions(-)
 create mode 100644 tools/testing/selftests/tc-testing/bpf/Makefile
 create mode 100644 tools/testing/selftests/tc-testing/bpf/action.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/tc-testing/bpf/Makefile b/tools/testing/selftests/tc-testing/bpf/Makefile
new file mode 100644
index 000000000000..dc92eb271d9a
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/bpf/Makefile
@@ -0,0 +1,29 @@
+# SPDX-License-Identifier: GPL-2.0
+
+APIDIR := ../../../../include/uapi
+TEST_GEN_FILES = action.o
+
+top_srcdir = ../../../../..
+include ../../lib.mk
+
+CLANG ?= clang
+LLC   ?= llc
+PROBE := $(shell $(LLC) -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1)
+
+ifeq ($(PROBE),)
+  CPU ?= probe
+else
+  CPU ?= generic
+endif
+
+CLANG_SYS_INCLUDES := $(shell $(CLANG) -v -E - </dev/null 2>&1 \
+	| sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }')
+
+CLANG_FLAGS = -I. -I$(APIDIR) \
+	      $(CLANG_SYS_INCLUDES) \
+	      -Wno-compare-distinct-pointer-types
+
+$(OUTPUT)/%.o: %.c
+	$(CLANG) $(CLANG_FLAGS) \
+		 -O2 -target bpf -emit-llvm -c $< -o - |      \
+	$(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
diff --git a/tools/testing/selftests/tc-testing/bpf/action.c b/tools/testing/selftests/tc-testing/bpf/action.c
new file mode 100644
index 000000000000..c32b99b80e19
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/bpf/action.c
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * Copyright (c) 2018 Davide Caratti, Red Hat inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+
+#include <linux/bpf.h>
+#include <linux/pkt_cls.h>
+
+__attribute__((section("action-ok"),used)) int action_ok(struct __sk_buff *s)
+{
+	return TC_ACT_OK;
+}
+
+__attribute__((section("action-ko"),used)) int action_ko(struct __sk_buff *s)
+{
+	s->data = 0x0;
+	return TC_ACT_OK;
+}
+
+char _license[] __attribute__((section("license"),used)) = "GPL";
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
index 6f289a49e5ec..1a9b282dd0be 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
@@ -55,7 +55,7 @@
             "bpf"
         ],
         "setup": [
-            "printf '#include <linux/bpf.h>\nchar l[] __attribute__((section(\"license\"),used))=\"GPL\"; __attribute__((section(\"action\"),used)) int m(struct __sk_buff *s) { return 2; }' | clang -O2 -x c -c - -target bpf -o _b.o",
+            "make -C bpf",
             [
                 "$TC action flush action bpf",
                 0,
@@ -63,14 +63,14 @@
                 255
             ]
         ],
-        "cmdUnderTest": "$TC action add action bpf object-file _b.o index 667",
+        "cmdUnderTest": "$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 _b.o:\\[action\\] id [0-9]* tag 3b185187f1855c4c( 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": [
             "$TC action flush action bpf",
-            "rm -f _b.o"
+            "make -C bpf clean"
         ]
     },
     {
@@ -81,7 +81,7 @@
             "bpf"
         ],
         "setup": [
-            "printf '#include <linux/bpf.h>\nchar l[] __attribute__((section(\"license\"),used))=\"GPL\"; __attribute__((section(\"action\"),used)) int m(struct __sk_buff *s) { s->data = 0x0; return 2; }' | clang -O2 -x c -c - -target bpf -o _c.o",
+            "make -C bpf",
             [
                 "$TC action flush action bpf",
                 0,
@@ -89,10 +89,10 @@
                 255
             ]
         ],
-        "cmdUnderTest": "$TC action add action bpf object-file _c.o index 667",
+        "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action.o section action-ko index 667",
         "expExitCode": "255",
         "verifyCmd": "$TC action get action bpf index 667",
-        "matchPattern": "action order [0-9]*: bpf _c.o:\\[action\\] id [0-9].*index 667 ref",
+        "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ko\\] id [0-9].*index 667 ref",
         "matchCount": "0",
         "teardown": [
             [
@@ -101,7 +101,7 @@
                 1,
                 255
             ],
-            "rm -f _c.o"
+            "make -C bpf clean"
         ]
     },
     {
diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py
index a023d0d62b25..d651bc1501bd 100644
--- a/tools/testing/selftests/tc-testing/tdc_config.py
+++ b/tools/testing/selftests/tc-testing/tdc_config.py
@@ -16,7 +16,9 @@ NAMES = {
           'DEV2': '',
           'BATCH_FILE': './batch.txt',
           # Name of the namespace to use
-          'NS': 'tcut'
+          'NS': 'tcut',
+          # Directory containing eBPF test programs
+          'EBPFDIR': './bpf'
         }
 
 
-- 
cgit 


From 4c2d39bd40c1f34975bec070a8e43fa573a9c327 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Thu, 4 Oct 2018 18:34:39 +0200
Subject: tc-testing: use a plugin to build eBPF program

use a TDC plugin, instead of building eBPF programs in the 'setup' stage.
'-B' argument can be used to build eBPF programs in $EBPFDIR directory,
in the 'pre-suite' stage. Binaries are then cleaned in 'post-suite' stage.

Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/README          |  2 +
 .../tc-testing/plugin-lib/buildebpfPlugin.py       | 66 ++++++++++++++++++++++
 .../selftests/tc-testing/tc-tests/actions/bpf.json |  8 +--
 3 files changed, 70 insertions(+), 6 deletions(-)
 create mode 100644 tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/tc-testing/README b/tools/testing/selftests/tc-testing/README
index 49a6f8c3fdae..f9281e8aa313 100644
--- a/tools/testing/selftests/tc-testing/README
+++ b/tools/testing/selftests/tc-testing/README
@@ -232,6 +232,8 @@ directory:
       and the other is a test whether the command leaked memory or not.
       (This one is a preliminary version, it may not work quite right yet,
       but the overall template is there and it should only need tweaks.)
+  - buildebpfPlugin.py:
+      builds all programs in $EBPFDIR.
 
 
 ACKNOWLEDGEMENTS
diff --git a/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py
new file mode 100644
index 000000000000..9f0ba10c44b4
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py
@@ -0,0 +1,66 @@
+'''
+build ebpf program
+'''
+
+import os
+import signal
+from string import Template
+import subprocess
+import time
+from TdcPlugin import TdcPlugin
+from tdc_config import *
+
+class SubPlugin(TdcPlugin):
+    def __init__(self):
+        self.sub_class = 'buildebpf/SubPlugin'
+        self.tap = ''
+        super().__init__()
+
+    def pre_suite(self, testcount, testidlist):
+        super().pre_suite(testcount, testidlist)
+
+        if self.args.buildebpf:
+            self._ebpf_makeall()
+
+    def post_suite(self, index):
+        super().post_suite(index)
+
+        self._ebpf_makeclean()
+
+    def add_args(self, parser):
+        super().add_args(parser)
+
+        self.argparser_group = self.argparser.add_argument_group(
+            'buildebpf',
+            'options for buildebpfPlugin')
+        self.argparser_group.add_argument(
+            '-B', '--buildebpf', action='store_true',
+            help='build eBPF programs')
+
+        return self.argparser
+
+    def _ebpf_makeall(self):
+        if self.args.buildebpf:
+            self._make('all')
+
+    def _ebpf_makeclean(self):
+        if self.args.buildebpf:
+            self._make('clean')
+
+    def _make(self, target):
+        command = 'make -C {} {}'.format(self.args.NAMES['EBPFDIR'], target)
+        proc = subprocess.Popen(command,
+            shell=True,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+            env=ENVIR)
+        (rawout, serr) = proc.communicate()
+
+        if proc.returncode != 0 and len(serr) > 0:
+            foutput = serr.decode("utf-8")
+        else:
+            foutput = rawout.decode("utf-8")
+
+        proc.stdout.close()
+        proc.stderr.close()
+        return proc, foutput
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 1a9b282dd0be..5970cee6d05f 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
@@ -55,7 +55,6 @@
             "bpf"
         ],
         "setup": [
-            "make -C bpf",
             [
                 "$TC action flush action bpf",
                 0,
@@ -69,8 +68,7 @@
         "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9]* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref",
         "matchCount": "1",
         "teardown": [
-            "$TC action flush action bpf",
-            "make -C bpf clean"
+            "$TC action flush action bpf"
         ]
     },
     {
@@ -81,7 +79,6 @@
             "bpf"
         ],
         "setup": [
-            "make -C bpf",
             [
                 "$TC action flush action bpf",
                 0,
@@ -100,8 +97,7 @@
                 0,
                 1,
                 255
-            ],
-            "make -C bpf clean"
+            ]
         ]
     },
     {
-- 
cgit 


From 6f8474922b443fd4a89a5dd5b891a3c6a144b9c7 Mon Sep 17 00:00:00 2001
From: Jakub Sitnicki <jakub@cloudflare.com>
Date: Fri, 5 Oct 2018 10:19:57 +0200
Subject: selftests: net: Clean up an unused variable

Address compiler warning:

ip_defrag.c: In function 'send_udp_frags':
ip_defrag.c:206:16: warning: unused variable 'udphdr' [-Wunused-variable]
  struct udphdr udphdr;
                ^~~~~~

Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/ip_defrag.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/ip_defrag.c b/tools/testing/selftests/net/ip_defrag.c
index 2366dc6bce71..61ae2782388e 100644
--- a/tools/testing/selftests/net/ip_defrag.c
+++ b/tools/testing/selftests/net/ip_defrag.c
@@ -203,7 +203,6 @@ static void send_udp_frags(int fd_raw, struct sockaddr *addr,
 {
 	struct ip *iphdr = (struct ip *)ip_frame;
 	struct ip6_hdr *ip6hdr = (struct ip6_hdr *)ip_frame;
-	struct udphdr udphdr;
 	int res;
 	int offset;
 	int frag_len;
-- 
cgit 


From 262f9d811c7608f1e74258ceecfe1fa213bdf912 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 5 Oct 2018 19:38:46 -0700
Subject: bpf: do not blindly change rlimit in reuseport net selftest

If the current process has unlimited RLIMIT_MEMLOCK,
we should should leave it as is.

Fixes: 941ff6f11c02 ("bpf: fix rlimit in reuseport net selftest")
Signed-off-by: John Sperbeck <jsperbeck@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/net/reuseport_bpf.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/reuseport_bpf.c b/tools/testing/selftests/net/reuseport_bpf.c
index cad14cd0ea92..b5277106df1f 100644
--- a/tools/testing/selftests/net/reuseport_bpf.c
+++ b/tools/testing/selftests/net/reuseport_bpf.c
@@ -437,14 +437,19 @@ void enable_fastopen(void)
 	}
 }
 
-static struct rlimit rlim_old, rlim_new;
+static struct rlimit rlim_old;
 
 static  __attribute__((constructor)) void main_ctor(void)
 {
 	getrlimit(RLIMIT_MEMLOCK, &rlim_old);
-	rlim_new.rlim_cur = rlim_old.rlim_cur + (1UL << 20);
-	rlim_new.rlim_max = rlim_old.rlim_max + (1UL << 20);
-	setrlimit(RLIMIT_MEMLOCK, &rlim_new);
+
+	if (rlim_old.rlim_cur != RLIM_INFINITY) {
+		struct rlimit rlim_new;
+
+		rlim_new.rlim_cur = rlim_old.rlim_cur + (1UL << 20);
+		rlim_new.rlim_max = rlim_old.rlim_max + (1UL << 20);
+		setrlimit(RLIMIT_MEMLOCK, &rlim_new);
+	}
 }
 
 static __attribute__((destructor)) void main_dtor(void)
-- 
cgit 


From 1e0a720779531cd2860777534e3674b518ac0a69 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Mon, 8 Oct 2018 14:37:03 +0200
Subject: selftests: pmtu: Introduce check_pmtu_value()

Introduce and use a function that checks PMTU values against
expected values and logs error messages, to remove some clutter.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/pmtu.sh | 49 +++++++++++++++++--------------------
 1 file changed, 22 insertions(+), 27 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 0ab9423d009f..6c38a7637744 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -229,6 +229,19 @@ route_get_dst_pmtu_from_exception() {
 	mtu_parse "$(route_get_dst_exception "${ns_cmd}" ${dst})"
 }
 
+check_pmtu_value() {
+	expected="${1}"
+	value="${2}"
+	event="${3}"
+
+	[ "${expected}" = "any" ] && [ -n "${value}" ] && return 0
+	[ "${value}" = "${expected}" ] && return 0
+	[ -z "${value}" ] &&    err "  PMTU exception wasn't created after ${event}" && return 1
+	[ -z "${expected}" ] && err "  PMTU exception shouldn't exist after ${event}" && return 1
+	err "  found PMTU exception with incorrect MTU ${value}, expected ${expected}, after ${event}"
+	return 1
+}
+
 test_pmtu_vti4_exception() {
 	setup namespaces veth vti4 xfrm4 || return 2
 
@@ -248,24 +261,13 @@ test_pmtu_vti4_exception() {
 	# exception is created
 	${ns_a} ping -q -M want -i 0.1 -w 2 -s ${ping_payload} ${vti4_b_addr} > /dev/null
 	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti4_b_addr})"
-	if [ "${pmtu}" != "" ]; then
-		err "  unexpected exception created with PMTU ${pmtu} for IP payload length ${esp_payload_rfc4106}"
-		return 1
-	fi
+	check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
 
 	# Now exceed link layer MTU by one byte, check that exception is created
+	# with the right PMTU value
 	${ns_a} ping -q -M want -i 0.1 -w 2 -s $((ping_payload + 1)) ${vti4_b_addr} > /dev/null
 	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti4_b_addr})"
-	if [ "${pmtu}" = "" ]; then
-		err "  exception not created for IP payload length $((esp_payload_rfc4106 + 1))"
-		return 1
-	fi
-
-	# ...with the right PMTU value
-	if [ ${pmtu} -ne ${esp_payload_rfc4106} ]; then
-		err "  wrong PMTU ${pmtu} in exception, expected: ${esp_payload_rfc4106}"
-		return 1
-	fi
+	check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))"
 }
 
 test_pmtu_vti6_exception() {
@@ -280,25 +282,18 @@ test_pmtu_vti6_exception() {
 	${ns_a} ${ping6} -q -i 0.1 -w 2 -s 60000 ${vti6_b_addr} > /dev/null
 
 	# Check that exception was created
-	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" = "" ]; then
-		err "  tunnel exceeding link layer MTU didn't create route exception"
-		return 1
-	fi
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+	check_pmtu_value any "${pmtu}" "creating tunnel exceeding link layer MTU" || return 1
 
 	# Decrease tunnel MTU, check for PMTU decrease in route exception
 	mtu "${ns_a}" vti6_a 3000
-
-	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" -ne 3000 ]; then
-		err "  decreasing tunnel MTU didn't decrease route exception PMTU"
-		fail=1
-	fi
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+	check_pmtu_value "3000" "${pmtu}" "decreasing tunnel MTU" || fail=1
 
 	# Increase tunnel MTU, check for PMTU increase in route exception
 	mtu "${ns_a}" vti6_a 9000
-	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" -ne 9000 ]; then
-		err "  increasing tunnel MTU didn't increase route exception PMTU"
-		fail=1
-	fi
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+	check_pmtu_value "9000" "${pmtu}" "increasing tunnel MTU" || fail=1
 
 	return ${fail}
 }
-- 
cgit 


From 72ebddd7fff81e03a0617754d3f5c45ae49cea43 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 8 Oct 2018 14:37:04 +0200
Subject: selftests: pmtu: extend MTU parsing helper to locked MTU

The mtu_parse helper introduced in commit f2c929feeccd ("selftests:
pmtu: Factor out MTU parsing helper") can only handle "mtu 1234", but
not "mtu lock 1234". Extend it, so that we can do IPv4 tests with PMTU
smaller than net.ipv4.route.min_pmtu

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/pmtu.sh | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 6c38a7637744..03e56a27f69c 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -196,7 +196,9 @@ mtu_parse() {
 
 	next=0
 	for i in ${input}; do
+		[ ${next} -eq 1 -a "${i}" = "lock" ] && next=2 && continue
 		[ ${next} -eq 1 ] && echo "${i}" && return
+		[ ${next} -eq 2 ] && echo "lock ${i}" && return
 		[ "${i}" = "mtu" ] && next=1
 	done
 }
-- 
cgit 


From e44e428f59e4299bd060ac5c1618c4ac8e77c75a Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 8 Oct 2018 14:37:05 +0200
Subject: selftests: pmtu: add basic IPv4 and IPv6 PMTU tests

Commit d1f1b9cbf34c ("selftests: net: Introduce first PMTU test") and
follow-ups introduced some PMTU tests, but they all rely on tunneling,
and, particularly, on VTI.

These new tests use simple routing to exercise the generation and
update of PMTU exceptions in IPv4 and IPv6.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/pmtu.sh | 207 +++++++++++++++++++++++++++++++++++-
 1 file changed, 203 insertions(+), 4 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 03e56a27f69c..b9cdb68df4c5 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -6,6 +6,26 @@
 #
 # Tests currently implemented:
 #
+# - pmtu_ipv4
+#	Set up two namespaces, A and B, with two paths between them over routers
+#	R1 and R2 (also implemented with namespaces), with different MTUs:
+#
+#	  segment a_r1    segment b_r1		a_r1: 2000
+#	.--------------R1--------------.	a_r2: 1500
+#	A                               B	a_r3: 2000
+#	'--------------R2--------------'	a_r4: 1400
+#	  segment a_r2    segment b_r2
+#
+#	Check that PMTU exceptions with the correct PMTU are created. Then
+#	decrease and increase the MTU of the local link for one of the paths,
+#	A to R1, checking that route exception PMTU changes accordingly over
+#	this path. Also check that locked exceptions are created when an ICMP
+#	message advertising a PMTU smaller than net.ipv4.route.min_pmtu is
+#	received
+#
+# - pmtu_ipv6
+#	Same as pmtu_ipv4, except for locked PMTU tests, using IPv6
+#
 # - pmtu_vti4_exception
 #	Set up vti tunnel on top of veth, with xfrm states and policies, in two
 #	namespaces with matching endpoints. Check that route exception is not
@@ -50,6 +70,8 @@ ksft_skip=4
 which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
 
 tests="
+	pmtu_ipv4_exception		ipv4: PMTU exceptions
+	pmtu_ipv6_exception		ipv6: PMTU exceptions
 	pmtu_vti6_exception		vti6: PMTU exceptions
 	pmtu_vti4_exception		vti4: PMTU exceptions
 	pmtu_vti4_default_mtu		vti4: default MTU assignment
@@ -60,8 +82,45 @@ tests="
 
 NS_A="ns-$(mktemp -u XXXXXX)"
 NS_B="ns-$(mktemp -u XXXXXX)"
+NS_R1="ns-$(mktemp -u XXXXXX)"
+NS_R2="ns-$(mktemp -u XXXXXX)"
 ns_a="ip netns exec ${NS_A}"
 ns_b="ip netns exec ${NS_B}"
+ns_r1="ip netns exec ${NS_R1}"
+ns_r2="ip netns exec ${NS_R2}"
+
+# Addressing and routing for tests with routers: four network segments, with
+# index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an
+# identifier ID, which is 1 for hosts (A and B), 2 for routers (R1 and R2).
+# Addresses are:
+# - IPv4: PREFIX4.SEGMENT.ID (/24)
+# - IPv6: PREFIX6:SEGMENT::ID (/64)
+prefix4="192.168"
+prefix6="fd00"
+a_r1=1
+a_r2=2
+b_r1=3
+b_r2=4
+#	ns	peer	segment
+routing_addrs="
+	A	R1	${a_r1}
+	A	R2	${a_r2}
+	B	R1	${b_r1}
+	B	R2	${b_r2}
+"
+# Traffic from A to B goes through R1 by default, and through R2, if destined to
+# B's address on the b_r2 segment.
+# Traffic from B to A goes through R1.
+#	ns	destination		gateway
+routes="
+	A	default			${prefix4}.${a_r1}.2
+	A	${prefix4}.${b_r2}.1	${prefix4}.${a_r2}.2
+	B	default			${prefix4}.${b_r1}.2
+
+	A	default			${prefix6}:${a_r1}::2
+	A	${prefix6}:${b_r2}::1	${prefix6}:${a_r2}::2
+	B	default			${prefix6}:${b_r1}::2
+"
 
 veth4_a_addr="192.168.1.1"
 veth4_b_addr="192.168.1.2"
@@ -94,9 +153,15 @@ err_flush() {
 	err_buf=
 }
 
+# Find the auto-generated name for this namespace
+nsname() {
+	eval echo \$NS_$1
+}
+
 setup_namespaces() {
-	ip netns add ${NS_A} || return 1
-	ip netns add ${NS_B}
+	for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
+		ip netns add ${n} || return 1
+	done
 }
 
 setup_veth() {
@@ -167,6 +232,49 @@ setup_xfrm6() {
 	setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr}
 }
 
+setup_routing() {
+	for i in ${NS_R1} ${NS_R2}; do
+		ip netns exec ${i} sysctl -q net/ipv4/ip_forward=1
+		ip netns exec ${i} sysctl -q net/ipv6/conf/all/forwarding=1
+	done
+
+	for i in ${routing_addrs}; do
+		[ "${ns}" = "" ]	&& ns="${i}"		&& continue
+		[ "${peer}" = "" ]	&& peer="${i}"		&& continue
+		[ "${segment}" = "" ]	&& segment="${i}"
+
+		ns_name="$(nsname ${ns})"
+		peer_name="$(nsname ${peer})"
+		if="veth_${ns}-${peer}"
+		ifpeer="veth_${peer}-${ns}"
+
+		# Create veth links
+		ip link add ${if} up netns ${ns_name} type veth peer name ${ifpeer} netns ${peer_name} || return 1
+		ip -n ${peer_name} link set dev ${ifpeer} up
+
+		# Add addresses
+		ip -n ${ns_name}   addr add ${prefix4}.${segment}.1/24  dev ${if}
+		ip -n ${ns_name}   addr add ${prefix6}:${segment}::1/64 dev ${if}
+
+		ip -n ${peer_name} addr add ${prefix4}.${segment}.2/24  dev ${ifpeer}
+		ip -n ${peer_name} addr add ${prefix6}:${segment}::2/64 dev ${ifpeer}
+
+		ns=""; peer=""; segment=""
+	done
+
+	for i in ${routes}; do
+		[ "${ns}" = "" ]	&& ns="${i}"		&& continue
+		[ "${addr}" = "" ]	&& addr="${i}"		&& continue
+		[ "${gw}" = "" ]	&& gw="${i}"
+
+		ns_name="$(nsname ${ns})"
+
+		ip -n ${ns_name} route add ${addr} via ${gw}
+
+		ns=""; addr=""; gw=""
+	done
+}
+
 setup() {
 	[ "$(id -u)" -ne 0 ] && echo "  need to run as root" && return $ksft_skip
 
@@ -178,8 +286,9 @@ setup() {
 
 cleanup() {
 	[ ${cleanup_done} -eq 1 ] && return
-	ip netns del ${NS_A} 2> /dev/null
-	ip netns del ${NS_B} 2> /dev/null
+	for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
+		ip netns del ${n} 2> /dev/null
+	done
 	cleanup_done=1
 }
 
@@ -244,6 +353,96 @@ check_pmtu_value() {
 	return 1
 }
 
+test_pmtu_ipvX() {
+	family=${1}
+
+	setup namespaces routing || return 2
+
+	if [ ${family} -eq 4 ]; then
+		ping=ping
+		dst1="${prefix4}.${b_r1}.1"
+		dst2="${prefix4}.${b_r2}.1"
+	else
+		ping=${ping6}
+		dst1="${prefix6}:${b_r1}::1"
+		dst2="${prefix6}:${b_r2}::1"
+	fi
+
+	# Set up initial MTU values
+	mtu "${ns_a}"  veth_A-R1 2000
+	mtu "${ns_r1}" veth_R1-A 2000
+	mtu "${ns_r1}" veth_R1-B 1400
+	mtu "${ns_b}"  veth_B-R1 1400
+
+	mtu "${ns_a}"  veth_A-R2 2000
+	mtu "${ns_r2}" veth_R2-A 2000
+	mtu "${ns_r2}" veth_R2-B 1500
+	mtu "${ns_b}"  veth_B-R2 1500
+
+	# Create route exceptions
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1800 ${dst1} > /dev/null
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1800 ${dst2} > /dev/null
+
+	# Check that exceptions have been created with the correct PMTU
+	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
+	check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1
+
+	# Decrease local MTU below PMTU, check for PMTU decrease in route exception
+	mtu "${ns_a}"  veth_A-R1 1300
+	mtu "${ns_r1}" veth_R1-A 1300
+	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
+	check_pmtu_value "1300" "${pmtu_1}" "decreasing local MTU" || return 1
+	# Second exception shouldn't be modified
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "1500" "${pmtu_2}" "changing local MTU on a link not on this path" || return 1
+
+	# Increase MTU, check for PMTU increase in route exception
+	mtu "${ns_a}"  veth_A-R1 1700
+	mtu "${ns_r1}" veth_R1-A 1700
+	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
+	check_pmtu_value "1700" "${pmtu_1}" "increasing local MTU" || return 1
+	# Second exception shouldn't be modified
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "1500" "${pmtu_2}" "changing local MTU on a link not on this path" || return 1
+
+	# Skip PMTU locking tests for IPv6
+	[ $family -eq 6 ] && return 0
+
+	# Decrease remote MTU on path via R2, get new exception
+	mtu "${ns_r2}" veth_R2-B 400
+	mtu "${ns_b}"  veth_B-R2 400
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1400 ${dst2} > /dev/null
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "lock 552" "${pmtu_2}" "exceeding MTU, with MTU < min_pmtu" || return 1
+
+	# Decrease local MTU below PMTU
+	mtu "${ns_a}"  veth_A-R2 500
+	mtu "${ns_r2}" veth_R2-A 500
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "500" "${pmtu_2}" "decreasing local MTU" || return 1
+
+	# Increase local MTU
+	mtu "${ns_a}"  veth_A-R2 1500
+	mtu "${ns_r2}" veth_R2-A 1500
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "1500" "${pmtu_2}" "increasing local MTU" || return 1
+
+	# Get new exception
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1400 ${dst2} > /dev/null
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "lock 552" "${pmtu_2}" "exceeding MTU, with MTU < min_pmtu" || return 1
+}
+
+test_pmtu_ipv4_exception() {
+	test_pmtu_ipvX 4
+}
+
+test_pmtu_ipv6_exception() {
+	test_pmtu_ipvX 6
+}
+
 test_pmtu_vti4_exception() {
 	setup namespaces veth vti4 xfrm4 || return 2
 
-- 
cgit 


From 4b0aaacee51eb6592a03fdefd5ce97558518e291 Mon Sep 17 00:00:00 2001
From: "Shuah Khan (Samsung OSG)" <shuah@kernel.org>
Date: Fri, 5 Oct 2018 16:17:43 -0600
Subject: selftests: usbip: add wait after attach and before checking port
 status

Add sleep between attach and "usbip port" check to make sure status is
updated. Running attach and query back shows incorrect status.

Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 tools/testing/selftests/drivers/usb/usbip/usbip_test.sh | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh b/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh
index a72df93cf1f8..128f0ab24307 100755
--- a/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh
+++ b/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh
@@ -141,6 +141,10 @@ echo "Import devices from localhost - should work"
 src/usbip attach -r localhost -b $busid;
 echo "=============================================================="
 
+# Wait for sysfs file to be updated. Without this sleep, usbip port
+# shows no imported devices.
+sleep 3;
+
 echo "List imported devices - expect to see imported devices";
 src/usbip port;
 echo "=============================================================="
-- 
cgit 


From 908142e61b2e9c2411e8bc4e5092a6ab06eca8e4 Mon Sep 17 00:00:00 2001
From: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Date: Tue, 9 Oct 2018 10:04:53 +0900
Subject: selftests/bpf: test_verifier, change names of fixup maps

Currently fixup map are named like fixup_map1, fixup_map2, and so on.
As suggested by Alexei let's change change map names such that we can
identify map type by looking at the name.

This patch is basically a find and replace change:
fixup_map1  ->  fixup_map_hash_8b
fixup_map2  ->  fixup_map_hash_48b
fixup_map3  ->  fixup_map_hash_16b
fixup_map4  ->  fixup_map_array_48b

Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_verifier.c | 380 ++++++++++++++--------------
 1 file changed, 190 insertions(+), 190 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index bc9cd8537467..65ae44c85d27 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -61,10 +61,10 @@ static bool unpriv_disabled = false;
 struct bpf_test {
 	const char *descr;
 	struct bpf_insn	insns[MAX_INSNS];
-	int fixup_map1[MAX_FIXUPS];
-	int fixup_map2[MAX_FIXUPS];
-	int fixup_map3[MAX_FIXUPS];
-	int fixup_map4[MAX_FIXUPS];
+	int fixup_map_hash_8b[MAX_FIXUPS];
+	int fixup_map_hash_48b[MAX_FIXUPS];
+	int fixup_map_hash_16b[MAX_FIXUPS];
+	int fixup_map_array_48b[MAX_FIXUPS];
 	int fixup_prog1[MAX_FIXUPS];
 	int fixup_prog2[MAX_FIXUPS];
 	int fixup_map_in_map[MAX_FIXUPS];
@@ -876,7 +876,7 @@ static struct bpf_test tests[] = {
 				     BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 2 },
+		.fixup_map_hash_8b = { 2 },
 		.errstr = "invalid indirect read from stack",
 		.result = REJECT,
 	},
@@ -1110,7 +1110,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "R0 invalid mem access 'map_value_or_null'",
 		.result = REJECT,
 	},
@@ -1127,7 +1127,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 4, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "misaligned value access",
 		.result = REJECT,
 		.flags = F_LOAD_WITH_STRICT_ALIGNMENT,
@@ -1147,7 +1147,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 1),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "R0 invalid mem access",
 		.errstr_unpriv = "R0 leaks addr",
 		.result = REJECT,
@@ -1237,7 +1237,7 @@ static struct bpf_test tests[] = {
 				     BPF_FUNC_map_delete_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 24 },
+		.fixup_map_hash_8b = { 24 },
 		.errstr_unpriv = "R1 pointer comparison",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
@@ -1391,7 +1391,7 @@ static struct bpf_test tests[] = {
 				    offsetof(struct __sk_buff, pkt_type)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.errstr = "different pointers",
 		.errstr_unpriv = "R1 pointer comparison",
 		.result = REJECT,
@@ -1414,7 +1414,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 			BPF_JMP_IMM(BPF_JA, 0, 0, -12),
 		},
-		.fixup_map1 = { 6 },
+		.fixup_map_hash_8b = { 6 },
 		.errstr = "different pointers",
 		.errstr_unpriv = "R1 pointer comparison",
 		.result = REJECT,
@@ -1438,7 +1438,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 			BPF_JMP_IMM(BPF_JA, 0, 0, -13),
 		},
-		.fixup_map1 = { 7 },
+		.fixup_map_hash_8b = { 7 },
 		.errstr = "different pointers",
 		.errstr_unpriv = "R1 pointer comparison",
 		.result = REJECT,
@@ -2575,7 +2575,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr_unpriv = "R4 leaks addr",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
@@ -2592,7 +2592,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "invalid indirect read from stack off -8+0 size 8",
 		.result = REJECT,
 	},
@@ -2894,7 +2894,7 @@ static struct bpf_test tests[] = {
 			BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
@@ -2934,7 +2934,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 1 },
+		.fixup_map_hash_8b = { 1 },
 		.errstr_unpriv = "R1 pointer comparison",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
@@ -4073,7 +4073,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 5 },
+		.fixup_map_hash_8b = { 5 },
 		.result_unpriv = ACCEPT,
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_XDP,
@@ -4089,7 +4089,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 1 },
+		.fixup_map_hash_8b = { 1 },
 		.result = REJECT,
 		.errstr = "invalid access to packet",
 		.prog_type = BPF_PROG_TYPE_XDP,
@@ -4117,7 +4117,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 11 },
+		.fixup_map_hash_8b = { 11 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
@@ -4139,7 +4139,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 7 },
+		.fixup_map_hash_8b = { 7 },
 		.result = REJECT,
 		.errstr = "invalid access to packet",
 		.prog_type = BPF_PROG_TYPE_XDP,
@@ -4161,7 +4161,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 6 },
+		.fixup_map_hash_8b = { 6 },
 		.result = REJECT,
 		.errstr = "invalid access to packet",
 		.prog_type = BPF_PROG_TYPE_XDP,
@@ -4184,7 +4184,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 5 },
+		.fixup_map_hash_8b = { 5 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -4199,7 +4199,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 1 },
+		.fixup_map_hash_8b = { 1 },
 		.result = REJECT,
 		.errstr = "invalid access to packet",
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
@@ -4227,7 +4227,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 11 },
+		.fixup_map_hash_8b = { 11 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -4249,7 +4249,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 7 },
+		.fixup_map_hash_8b = { 7 },
 		.result = REJECT,
 		.errstr = "invalid access to packet",
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
@@ -4271,7 +4271,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 6 },
+		.fixup_map_hash_8b = { 6 },
 		.result = REJECT,
 		.errstr = "invalid access to packet",
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
@@ -4555,7 +4555,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
@@ -4577,7 +4577,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
@@ -4601,7 +4601,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
@@ -4629,7 +4629,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
@@ -4649,7 +4649,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "invalid access to map value, value_size=48 off=48 size=8",
 		.result = REJECT,
 	},
@@ -4670,7 +4670,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R0 min value is outside of the array range",
 		.result = REJECT,
 		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -4692,7 +4692,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R0 unbounded memory access, make sure to bounds check any array access into a map",
 		.result = REJECT,
 		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -4717,7 +4717,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.errstr = "R0 unbounded memory access",
 		.result_unpriv = REJECT,
@@ -4744,7 +4744,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.errstr = "invalid access to map value, value_size=48 off=44 size=8",
 		.result_unpriv = REJECT,
@@ -4774,7 +4774,7 @@ static struct bpf_test tests[] = {
 				    offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3, 11 },
+		.fixup_map_hash_48b = { 3, 11 },
 		.errstr = "R0 pointer += pointer",
 		.result = REJECT,
 		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -4807,7 +4807,7 @@ static struct bpf_test tests[] = {
 			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 1 },
+		.fixup_map_hash_8b = { 1 },
 		.result = REJECT,
 		.errstr = "cannot pass map_type 1 into func bpf_get_local_storage",
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
@@ -4922,7 +4922,7 @@ static struct bpf_test tests[] = {
 			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 1 },
+		.fixup_map_hash_8b = { 1 },
 		.result = REJECT,
 		.errstr = "cannot pass map_type 1 into func bpf_get_local_storage",
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
@@ -5024,7 +5024,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
 	},
@@ -5045,7 +5045,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.errstr = "R4 pointer arithmetic on map_value_or_null",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
@@ -5066,7 +5066,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.errstr = "R4 pointer arithmetic on map_value_or_null",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
@@ -5087,7 +5087,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.errstr = "R4 pointer arithmetic on map_value_or_null",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
@@ -5113,7 +5113,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.result = REJECT,
 		.errstr = "R4 !read_ok",
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
@@ -5141,7 +5141,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
 	},
@@ -5162,7 +5162,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R0 unbounded memory access",
 		.result = REJECT,
 		.errstr_unpriv = "R0 leaks addr",
@@ -5412,7 +5412,7 @@ static struct bpf_test tests[] = {
 				      offsetof(struct __sk_buff, cb[0])),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 2 },
+		.fixup_map_hash_8b = { 2 },
 		.errstr_unpriv = "R2 leaks addr into mem",
 		.result_unpriv = REJECT,
 		.result = REJECT,
@@ -5442,7 +5442,7 @@ static struct bpf_test tests[] = {
 				      offsetof(struct __sk_buff, cb[0])),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 1 },
+		.fixup_map_hash_8b = { 1 },
 		.errstr_unpriv = "R2 leaks addr into ctx",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
@@ -5464,7 +5464,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.errstr_unpriv = "R6 leaks addr into mem",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
@@ -5484,7 +5484,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5503,7 +5503,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5521,7 +5521,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_trace_printk),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "invalid access to map value, value_size=48 off=0 size=0",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5541,7 +5541,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "invalid access to map value, value_size=48 off=0 size=56",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5561,7 +5561,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R2 min value is negative",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5585,7 +5585,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5606,7 +5606,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5626,7 +5626,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_trace_printk),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "invalid access to map value, value_size=48 off=4 size=0",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5650,7 +5650,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "invalid access to map value, value_size=48 off=4 size=52",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5672,7 +5672,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R2 min value is negative",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5694,7 +5694,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R2 min value is negative",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5719,7 +5719,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5741,7 +5741,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5761,7 +5761,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_trace_printk),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R1 min value is outside of the array range",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5786,7 +5786,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "invalid access to map value, value_size=48 off=4 size=52",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5809,7 +5809,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R2 min value is negative",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5832,7 +5832,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R2 min value is negative",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5858,7 +5858,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5881,7 +5881,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5903,7 +5903,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_trace_printk),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R1 min value is outside of the array range",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5925,7 +5925,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R1 unbounded memory access",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5951,7 +5951,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "invalid access to map value, value_size=48 off=4 size=45",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5975,7 +5975,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5998,7 +5998,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = REJECT,
 		.errstr = "R1 unbounded memory access",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6022,7 +6022,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6045,7 +6045,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = REJECT,
 		.errstr = "R1 unbounded memory access",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6070,7 +6070,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6094,7 +6094,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6118,7 +6118,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = REJECT,
 		.errstr = "R1 min value is negative",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6143,7 +6143,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6167,7 +6167,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6191,7 +6191,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = REJECT,
 		.errstr = "R1 min value is negative",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6210,7 +6210,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 8 },
+		.fixup_map_hash_16b = { 3, 8 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6230,7 +6230,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_update_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 10 },
+		.fixup_map_hash_16b = { 3, 10 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6250,8 +6250,8 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_update_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
-		.fixup_map3 = { 10 },
+		.fixup_map_hash_8b = { 3 },
+		.fixup_map_hash_16b = { 10 },
 		.result = REJECT,
 		.errstr = "invalid access to map value, value_size=8 off=0 size=16",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6272,7 +6272,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 9 },
+		.fixup_map_hash_16b = { 3, 9 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6292,7 +6292,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 9 },
+		.fixup_map_hash_16b = { 3, 9 },
 		.result = REJECT,
 		.errstr = "invalid access to map value, value_size=16 off=12 size=8",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6312,7 +6312,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 9 },
+		.fixup_map_hash_16b = { 3, 9 },
 		.result = REJECT,
 		.errstr = "invalid access to map value, value_size=16 off=-4 size=8",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6334,7 +6334,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 10 },
+		.fixup_map_hash_16b = { 3, 10 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6355,7 +6355,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 10 },
+		.fixup_map_hash_16b = { 3, 10 },
 		.result = REJECT,
 		.errstr = "invalid access to map value, value_size=16 off=12 size=8",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6376,7 +6376,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 10 },
+		.fixup_map_hash_16b = { 3, 10 },
 		.result = REJECT,
 		.errstr = "invalid access to map value, value_size=16 off=-4 size=8",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6399,7 +6399,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 11 },
+		.fixup_map_hash_16b = { 3, 11 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6419,7 +6419,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 10 },
+		.fixup_map_hash_16b = { 3, 10 },
 		.result = REJECT,
 		.errstr = "R2 unbounded memory access, make sure to bounds check any array access into a map",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6442,7 +6442,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 11 },
+		.fixup_map_hash_16b = { 3, 11 },
 		.result = REJECT,
 		.errstr = "invalid access to map value, value_size=16 off=9 size=8",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6464,7 +6464,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 42),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.result = ACCEPT,
 		.result_unpriv = REJECT,
@@ -6485,7 +6485,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 42),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.result = ACCEPT,
 		.result_unpriv = REJECT,
@@ -6502,7 +6502,7 @@ static struct bpf_test tests[] = {
 			BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R1 !read_ok",
 		.errstr = "R1 !read_ok",
 		.result = REJECT,
@@ -6536,7 +6536,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_7, -4, 24),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.result = ACCEPT,
 		.result_unpriv = REJECT,
@@ -6564,7 +6564,7 @@ static struct bpf_test tests[] = {
 			BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 4),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.result = ACCEPT,
 		.result_unpriv = REJECT,
@@ -6583,7 +6583,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R0 bitwise operator &= on pointer",
 		.result = REJECT,
 	},
@@ -6600,7 +6600,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R0 32-bit pointer arithmetic prohibited",
 		.result = REJECT,
 	},
@@ -6617,7 +6617,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R0 pointer arithmetic with /= operator",
 		.result = REJECT,
 	},
@@ -6634,7 +6634,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 pointer arithmetic prohibited",
 		.errstr = "invalid mem access 'inv'",
 		.result = REJECT,
@@ -6658,7 +6658,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R0 invalid mem access 'inv'",
 		.result = REJECT,
 	},
@@ -6681,7 +6681,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 42),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.result = ACCEPT,
 		.result_unpriv = REJECT,
@@ -6927,7 +6927,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6953,7 +6953,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "invalid access to map value, value_size=48 off=0 size=49",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6981,7 +6981,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -7008,7 +7008,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R1 min value is outside of the array range",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -7080,7 +7080,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_csum_diff),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -7105,7 +7105,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_csum_diff),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -7128,7 +7128,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_csum_diff),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -7209,7 +7209,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -7230,7 +7230,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -7250,7 +7250,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -7325,7 +7325,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R0 max value is outside of the array range",
 		.result = REJECT,
 		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -7355,7 +7355,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_REG(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R0 max value is outside of the array range",
 		.result = REJECT,
 		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -7708,7 +7708,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
@@ -7732,7 +7732,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
@@ -7758,7 +7758,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
@@ -7783,7 +7783,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
@@ -7807,7 +7807,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 	},
 	{
@@ -7831,7 +7831,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
@@ -7877,7 +7877,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 	},
 	{
@@ -7902,7 +7902,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
@@ -7928,7 +7928,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 	},
 	{
@@ -7953,7 +7953,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
@@ -7980,7 +7980,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
@@ -8006,7 +8006,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
@@ -8035,7 +8035,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
@@ -8065,7 +8065,7 @@ static struct bpf_test tests[] = {
 			BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, -3),
 			BPF_JMP_IMM(BPF_JA, 0, 0, -7),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.errstr = "R0 invalid mem access 'inv'",
 		.result = REJECT,
 	},
@@ -8093,7 +8093,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 		.result_unpriv = REJECT,
@@ -8120,7 +8120,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "R0 max value is outside of the array range",
 		.result = REJECT,
 	},
@@ -8145,7 +8145,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
 		.result = REJECT,
 	},
@@ -8171,7 +8171,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT
 	},
 	{
@@ -8196,7 +8196,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "map_value pointer and 4294967295",
 		.result = REJECT
 	},
@@ -8222,7 +8222,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "R0 min value is outside of the array range",
 		.result = REJECT
 	},
@@ -8246,7 +8246,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.errstr = "value_size=8 off=1073741825",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
@@ -8271,7 +8271,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.errstr = "value 1073741823",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
@@ -8307,7 +8307,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT
 	},
 	{
@@ -8346,7 +8346,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		/* not actually fully unbounded, but the bound is very high */
 		.errstr = "R0 unbounded memory access",
 		.result = REJECT
@@ -8389,7 +8389,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		/* not actually fully unbounded, but the bound is very high */
 		.errstr = "R0 unbounded memory access",
 		.result = REJECT
@@ -8418,7 +8418,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT
 	},
 	{
@@ -8445,7 +8445,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "R0 max value is outside of the array range",
 		.result = REJECT
 	},
@@ -8475,7 +8475,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "R0 unbounded memory access",
 		.result = REJECT
 	},
@@ -8495,7 +8495,7 @@ static struct bpf_test tests[] = {
 			BPF_JMP_A(0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "map_value pointer and 2147483646",
 		.result = REJECT
 	},
@@ -8517,7 +8517,7 @@ static struct bpf_test tests[] = {
 			BPF_JMP_A(0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "pointer offset 1073741822",
 		.result = REJECT
 	},
@@ -8538,7 +8538,7 @@ static struct bpf_test tests[] = {
 			BPF_JMP_A(0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "pointer offset -1073741822",
 		.result = REJECT
 	},
@@ -8560,7 +8560,7 @@ static struct bpf_test tests[] = {
 			BPF_JMP_A(0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "map_value pointer and 1000000000000",
 		.result = REJECT
 	},
@@ -8580,7 +8580,7 @@ static struct bpf_test tests[] = {
 			BPF_JMP_A(0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 		.retval = POINTER_VALUE,
 		.result_unpriv = REJECT,
@@ -8601,7 +8601,7 @@ static struct bpf_test tests[] = {
 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 		.retval = POINTER_VALUE,
 		.result_unpriv = REJECT,
@@ -8669,7 +8669,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 5 },
+		.fixup_map_hash_8b = { 5 },
 		.errstr = "variable stack read R2",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_LWT_IN,
@@ -8750,7 +8750,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.errstr = "R0 unbounded memory access",
 		.result_unpriv = REJECT,
@@ -10284,7 +10284,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-		.fixup_map1 = { 16 },
+		.fixup_map_hash_8b = { 16 },
 		.result = REJECT,
 		.errstr = "R0 min value is outside of the array range",
 	},
@@ -11235,7 +11235,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(), /* return 0 */
 		},
 		.prog_type = BPF_PROG_TYPE_XDP,
-		.fixup_map1 = { 23 },
+		.fixup_map_hash_8b = { 23 },
 		.result = ACCEPT,
 	},
 	{
@@ -11290,7 +11290,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(), /* return 1 */
 		},
 		.prog_type = BPF_PROG_TYPE_XDP,
-		.fixup_map1 = { 23 },
+		.fixup_map_hash_8b = { 23 },
 		.result = ACCEPT,
 	},
 	{
@@ -11345,7 +11345,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(), /* return 1 */
 		},
 		.prog_type = BPF_PROG_TYPE_XDP,
-		.fixup_map1 = { 23 },
+		.fixup_map_hash_8b = { 23 },
 		.result = REJECT,
 		.errstr = "invalid read from stack off -16+0 size 8",
 	},
@@ -11417,7 +11417,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-		.fixup_map1 = { 12, 22 },
+		.fixup_map_hash_8b = { 12, 22 },
 		.result = REJECT,
 		.errstr = "invalid access to map value, value_size=8 off=2 size=8",
 	},
@@ -11489,7 +11489,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-		.fixup_map1 = { 12, 22 },
+		.fixup_map_hash_8b = { 12, 22 },
 		.result = ACCEPT,
 	},
 	{
@@ -11560,7 +11560,7 @@ static struct bpf_test tests[] = {
 			BPF_JMP_IMM(BPF_JA, 0, 0, -8),
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-		.fixup_map1 = { 12, 22 },
+		.fixup_map_hash_8b = { 12, 22 },
 		.result = REJECT,
 		.errstr = "invalid access to map value, value_size=8 off=2 size=8",
 	},
@@ -11632,7 +11632,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-		.fixup_map1 = { 12, 22 },
+		.fixup_map_hash_8b = { 12, 22 },
 		.result = ACCEPT,
 	},
 	{
@@ -11703,7 +11703,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-		.fixup_map1 = { 12, 22 },
+		.fixup_map_hash_8b = { 12, 22 },
 		.result = REJECT,
 		.errstr = "R0 invalid mem access 'inv'",
 	},
@@ -12048,7 +12048,7 @@ static struct bpf_test tests[] = {
 			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 13 },
+		.fixup_map_hash_8b = { 13 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
@@ -12075,7 +12075,7 @@ static struct bpf_test tests[] = {
 				     BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 6 },
+		.fixup_map_hash_48b = { 6 },
 		.errstr = "invalid indirect read from stack off -8+0 size 8",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
@@ -12107,8 +12107,8 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-		.fixup_map2 = { 13 },
-		.fixup_map4 = { 16 },
+		.fixup_map_hash_48b = { 13 },
+		.fixup_map_array_48b = { 16 },
 		.result = ACCEPT,
 		.retval = 1,
 	},
@@ -12140,7 +12140,7 @@ static struct bpf_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.fixup_map_in_map = { 16 },
-		.fixup_map4 = { 13 },
+		.fixup_map_array_48b = { 13 },
 		.result = REJECT,
 		.errstr = "R0 invalid mem access 'map_ptr'",
 	},
@@ -12208,7 +12208,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_6, 0, 0xdead),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "R6 invalid mem access 'inv'",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -12232,7 +12232,7 @@ static struct bpf_test tests[] = {
 			BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -16),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "invalid read from stack off -16+0 size 8",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -12354,7 +12354,7 @@ static struct bpf_test tests[] = {
 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 3),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = REJECT,
 		.errstr = "misaligned value access off",
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
@@ -12464,7 +12464,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_get_stack),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 4 },
+		.fixup_map_hash_48b = { 4 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -13511,10 +13511,10 @@ static char bpf_vlog[UINT_MAX >> 8];
 static void do_test_fixup(struct bpf_test *test, enum bpf_map_type prog_type,
 			  struct bpf_insn *prog, int *map_fds)
 {
-	int *fixup_map1 = test->fixup_map1;
-	int *fixup_map2 = test->fixup_map2;
-	int *fixup_map3 = test->fixup_map3;
-	int *fixup_map4 = test->fixup_map4;
+	int *fixup_map_hash_8b = test->fixup_map_hash_8b;
+	int *fixup_map_hash_48b = test->fixup_map_hash_48b;
+	int *fixup_map_hash_16b = test->fixup_map_hash_16b;
+	int *fixup_map_array_48b = test->fixup_map_array_48b;
 	int *fixup_prog1 = test->fixup_prog1;
 	int *fixup_prog2 = test->fixup_prog2;
 	int *fixup_map_in_map = test->fixup_map_in_map;
@@ -13528,40 +13528,40 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_map_type prog_type,
 	 * for verifier and not do a runtime lookup, so the only thing
 	 * that really matters is value size in this case.
 	 */
-	if (*fixup_map1) {
+	if (*fixup_map_hash_8b) {
 		map_fds[0] = create_map(BPF_MAP_TYPE_HASH, sizeof(long long),
 					sizeof(long long), 1);
 		do {
-			prog[*fixup_map1].imm = map_fds[0];
-			fixup_map1++;
-		} while (*fixup_map1);
+			prog[*fixup_map_hash_8b].imm = map_fds[0];
+			fixup_map_hash_8b++;
+		} while (*fixup_map_hash_8b);
 	}
 
-	if (*fixup_map2) {
+	if (*fixup_map_hash_48b) {
 		map_fds[1] = create_map(BPF_MAP_TYPE_HASH, sizeof(long long),
 					sizeof(struct test_val), 1);
 		do {
-			prog[*fixup_map2].imm = map_fds[1];
-			fixup_map2++;
-		} while (*fixup_map2);
+			prog[*fixup_map_hash_48b].imm = map_fds[1];
+			fixup_map_hash_48b++;
+		} while (*fixup_map_hash_48b);
 	}
 
-	if (*fixup_map3) {
+	if (*fixup_map_hash_16b) {
 		map_fds[2] = create_map(BPF_MAP_TYPE_HASH, sizeof(long long),
 					sizeof(struct other_val), 1);
 		do {
-			prog[*fixup_map3].imm = map_fds[2];
-			fixup_map3++;
-		} while (*fixup_map3);
+			prog[*fixup_map_hash_16b].imm = map_fds[2];
+			fixup_map_hash_16b++;
+		} while (*fixup_map_hash_16b);
 	}
 
-	if (*fixup_map4) {
+	if (*fixup_map_array_48b) {
 		map_fds[3] = create_map(BPF_MAP_TYPE_ARRAY, sizeof(int),
 					sizeof(struct test_val), 1);
 		do {
-			prog[*fixup_map4].imm = map_fds[3];
-			fixup_map4++;
-		} while (*fixup_map4);
+			prog[*fixup_map_array_48b].imm = map_fds[3];
+			fixup_map_array_48b++;
+		} while (*fixup_map_array_48b);
 	}
 
 	if (*fixup_prog1) {
-- 
cgit 


From 7c85c448e7d74c4ddd759440a2141eab663567cf Mon Sep 17 00:00:00 2001
From: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Date: Tue, 9 Oct 2018 10:04:54 +0900
Subject: selftests/bpf: test_verifier, check bpf_map_lookup_elem access in bpf
 prog

map_lookup_elem isn't supported by certain map types like:
- BPF_MAP_TYPE_PROG_ARRAY
- BPF_MAP_TYPE_STACK_TRACE
- BPF_MAP_TYPE_XSKMAP
- BPF_MAP_TYPE_SOCKMAP/BPF_MAP_TYPE_SOCKHASH
Let's add verfier tests to check whether verifier prevents
bpf_map_lookup_elem call on above programs from bpf program.

Signed-off-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_verifier.c | 121 +++++++++++++++++++++++++++-
 1 file changed, 120 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 65ae44c85d27..cf4cd32b6772 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -48,7 +48,7 @@
 
 #define MAX_INSNS	BPF_MAXINSNS
 #define MAX_FIXUPS	8
-#define MAX_NR_MAPS	8
+#define MAX_NR_MAPS	13
 #define POINTER_VALUE	0xcafe4all
 #define TEST_DATA_LEN	64
 
@@ -65,6 +65,10 @@ struct bpf_test {
 	int fixup_map_hash_48b[MAX_FIXUPS];
 	int fixup_map_hash_16b[MAX_FIXUPS];
 	int fixup_map_array_48b[MAX_FIXUPS];
+	int fixup_map_sockmap[MAX_FIXUPS];
+	int fixup_map_sockhash[MAX_FIXUPS];
+	int fixup_map_xskmap[MAX_FIXUPS];
+	int fixup_map_stacktrace[MAX_FIXUPS];
 	int fixup_prog1[MAX_FIXUPS];
 	int fixup_prog2[MAX_FIXUPS];
 	int fixup_map_in_map[MAX_FIXUPS];
@@ -4541,6 +4545,85 @@ static struct bpf_test tests[] = {
 		.errstr = "invalid access to packet",
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
+	{
+		"prevent map lookup in sockmap",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_sockmap = { 3 },
+		.result = REJECT,
+		.errstr = "cannot pass map_type 15 into func bpf_map_lookup_elem",
+		.prog_type = BPF_PROG_TYPE_SOCK_OPS,
+	},
+	{
+		"prevent map lookup in sockhash",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_sockhash = { 3 },
+		.result = REJECT,
+		.errstr = "cannot pass map_type 18 into func bpf_map_lookup_elem",
+		.prog_type = BPF_PROG_TYPE_SOCK_OPS,
+	},
+	{
+		"prevent map lookup in xskmap",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_xskmap = { 3 },
+		.result = REJECT,
+		.errstr = "cannot pass map_type 17 into func bpf_map_lookup_elem",
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"prevent map lookup in stack trace",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_stacktrace = { 3 },
+		.result = REJECT,
+		.errstr = "cannot pass map_type 7 into func bpf_map_lookup_elem",
+		.prog_type = BPF_PROG_TYPE_PERF_EVENT,
+	},
+	{
+		"prevent map lookup in prog array",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_prog2 = { 3 },
+		.result = REJECT,
+		.errstr = "cannot pass map_type 3 into func bpf_map_lookup_elem",
+	},
 	{
 		"valid map access into an array with a constant",
 		.insns = {
@@ -13515,6 +13598,10 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_map_type prog_type,
 	int *fixup_map_hash_48b = test->fixup_map_hash_48b;
 	int *fixup_map_hash_16b = test->fixup_map_hash_16b;
 	int *fixup_map_array_48b = test->fixup_map_array_48b;
+	int *fixup_map_sockmap = test->fixup_map_sockmap;
+	int *fixup_map_sockhash = test->fixup_map_sockhash;
+	int *fixup_map_xskmap = test->fixup_map_xskmap;
+	int *fixup_map_stacktrace = test->fixup_map_stacktrace;
 	int *fixup_prog1 = test->fixup_prog1;
 	int *fixup_prog2 = test->fixup_prog2;
 	int *fixup_map_in_map = test->fixup_map_in_map;
@@ -13603,6 +13690,38 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_map_type prog_type,
 			fixup_percpu_cgroup_storage++;
 		} while (*fixup_percpu_cgroup_storage);
 	}
+	if (*fixup_map_sockmap) {
+		map_fds[9] = create_map(BPF_MAP_TYPE_SOCKMAP, sizeof(int),
+					sizeof(int), 1);
+		do {
+			prog[*fixup_map_sockmap].imm = map_fds[9];
+			fixup_map_sockmap++;
+		} while (*fixup_map_sockmap);
+	}
+	if (*fixup_map_sockhash) {
+		map_fds[10] = create_map(BPF_MAP_TYPE_SOCKHASH, sizeof(int),
+					sizeof(int), 1);
+		do {
+			prog[*fixup_map_sockhash].imm = map_fds[10];
+			fixup_map_sockhash++;
+		} while (*fixup_map_sockhash);
+	}
+	if (*fixup_map_xskmap) {
+		map_fds[11] = create_map(BPF_MAP_TYPE_XSKMAP, sizeof(int),
+					sizeof(int), 1);
+		do {
+			prog[*fixup_map_xskmap].imm = map_fds[11];
+			fixup_map_xskmap++;
+		} while (*fixup_map_xskmap);
+	}
+	if (*fixup_map_stacktrace) {
+		map_fds[12] = create_map(BPF_MAP_TYPE_STACK_TRACE, sizeof(u32),
+					 sizeof(u64), 1);
+		do {
+			prog[*fixup_map_stacktrace].imm = map_fds[12];
+			fixup_map_stacktrace++;
+		} while (fixup_map_stacktrace);
+	}
 }
 
 static void do_test_single(struct bpf_test *test, bool unpriv,
-- 
cgit 


From 4f775448f4d79e2db5791fcc3aa708373497d7e6 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Tue, 9 Oct 2018 12:04:48 +0200
Subject: bpf: make TC vlan bpf_helpers avail to selftests

The helper bpf_skb_vlan_push is needed by next patch, and the helper
bpf_skb_vlan_pop is added for completeness, regarding VLAN helpers.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/bpf_helpers.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 1d407b3494f9..fda8c162d0df 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -155,6 +155,10 @@ static struct bpf_sock *(*bpf_sk_lookup_udp)(void *ctx,
 	(void *) BPF_FUNC_sk_lookup_udp;
 static int (*bpf_sk_release)(struct bpf_sock *sk) =
 	(void *) BPF_FUNC_sk_release;
+static int (*bpf_skb_vlan_push)(void *ctx, __be16 vlan_proto, __u16 vlan_tci) =
+	(void *) BPF_FUNC_skb_vlan_push;
+static int (*bpf_skb_vlan_pop)(void *ctx) =
+	(void *) BPF_FUNC_skb_vlan_pop;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
-- 
cgit 


From 97396ff0bc2d31f8fcb29cbb57d2e0bbcb96d6c5 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Tue, 9 Oct 2018 12:04:53 +0200
Subject: selftests/bpf: add XDP selftests for modifying and popping VLAN
 headers

This XDP selftest also contain a small TC-bpf component. It provoke
the generic-XDP bug fixed in previous commit.

The selftest itself shows how to do VLAN manipulation from XDP and TC.
The test demonstrate how XDP ingress can remove a VLAN tag, and how TC
egress can add back a VLAN tag.

This use-case originates from a production need by ISP (kviknet.dk),
who gets DSL-lines terminated as VLAN Q-in-Q tagged packets, and want
to avoid having an net_device for every end-customer on the box doing
the L2 to L3 termination.
  The test-setup is done via a veth-pair and creating two network
namespaces (ns1 and ns2).  The 'ns1' simulate the ISP network that are
loading the BPF-progs stripping and adding VLAN IDs.  The 'ns2'
simulate the DSL-customer that are using VLAN tagged packets.

Running the script with --interactive, will simply not call the
cleanup function.  This gives the effect of creating a testlab, that
the users can inspect and play with.  The --verbose option will simply
request that the shell will print input lines as they are read, this
include comments, which in effect make the comments visible docs.

Reported-by: Yoel Caspersen <yoel@kviknet.dk>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/Makefile         |   6 +-
 tools/testing/selftests/bpf/test_xdp_vlan.c  | 292 +++++++++++++++++++++++++++
 tools/testing/selftests/bpf/test_xdp_vlan.sh | 195 ++++++++++++++++++
 3 files changed, 491 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/test_xdp_vlan.c
 create mode 100755 tools/testing/selftests/bpf/test_xdp_vlan.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 1381ab81099c..d24afe8b821d 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -36,7 +36,8 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \
 	test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
 	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
-	test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o test_sk_lookup_kern.o
+	test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o \
+	test_sk_lookup_kern.o test_xdp_vlan.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
@@ -49,7 +50,8 @@ TEST_PROGS := test_kmod.sh \
 	test_lwt_seg6local.sh \
 	test_lirc_mode2.sh \
 	test_skb_cgroup_id.sh \
-	test_flow_dissector.sh
+	test_flow_dissector.sh \
+	test_xdp_vlan.sh
 
 # Compile but not part of 'make run_tests'
 TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user \
diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.c b/tools/testing/selftests/bpf/test_xdp_vlan.c
new file mode 100644
index 000000000000..365a7d2d9f5c
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_vlan.c
@@ -0,0 +1,292 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *  Copyright(c) 2018 Jesper Dangaard Brouer.
+ *
+ * XDP/TC VLAN manipulation example
+ *
+ * GOTCHA: Remember to disable NIC hardware offloading of VLANs,
+ * else the VLAN tags are NOT inlined in the packet payload:
+ *
+ *  # ethtool -K ixgbe2 rxvlan off
+ *
+ * Verify setting:
+ *  # ethtool -k ixgbe2 | grep rx-vlan-offload
+ *  rx-vlan-offload: off
+ *
+ */
+#include <stddef.h>
+#include <stdbool.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/in.h>
+#include <linux/pkt_cls.h>
+
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+/* linux/if_vlan.h have not exposed this as UAPI, thus mirror some here
+ *
+ *	struct vlan_hdr - vlan header
+ *	@h_vlan_TCI: priority and VLAN ID
+ *	@h_vlan_encapsulated_proto: packet type ID or len
+ */
+struct _vlan_hdr {
+	__be16 h_vlan_TCI;
+	__be16 h_vlan_encapsulated_proto;
+};
+#define VLAN_PRIO_MASK		0xe000 /* Priority Code Point */
+#define VLAN_PRIO_SHIFT		13
+#define VLAN_CFI_MASK		0x1000 /* Canonical Format Indicator */
+#define VLAN_TAG_PRESENT	VLAN_CFI_MASK
+#define VLAN_VID_MASK		0x0fff /* VLAN Identifier */
+#define VLAN_N_VID		4096
+
+struct parse_pkt {
+	__u16 l3_proto;
+	__u16 l3_offset;
+	__u16 vlan_outer;
+	__u16 vlan_inner;
+	__u8  vlan_outer_offset;
+	__u8  vlan_inner_offset;
+};
+
+char _license[] SEC("license") = "GPL";
+
+static __always_inline
+bool parse_eth_frame(struct ethhdr *eth, void *data_end, struct parse_pkt *pkt)
+{
+	__u16 eth_type;
+	__u8 offset;
+
+	offset = sizeof(*eth);
+	/* Make sure packet is large enough for parsing eth + 2 VLAN headers */
+	if ((void *)eth + offset + (2*sizeof(struct _vlan_hdr)) > data_end)
+		return false;
+
+	eth_type = eth->h_proto;
+
+	/* Handle outer VLAN tag */
+	if (eth_type == bpf_htons(ETH_P_8021Q)
+	    || eth_type == bpf_htons(ETH_P_8021AD)) {
+		struct _vlan_hdr *vlan_hdr;
+
+		vlan_hdr = (void *)eth + offset;
+		pkt->vlan_outer_offset = offset;
+		pkt->vlan_outer = bpf_ntohs(vlan_hdr->h_vlan_TCI)
+				& VLAN_VID_MASK;
+		eth_type        = vlan_hdr->h_vlan_encapsulated_proto;
+		offset += sizeof(*vlan_hdr);
+	}
+
+	/* Handle inner (double) VLAN tag */
+	if (eth_type == bpf_htons(ETH_P_8021Q)
+	    || eth_type == bpf_htons(ETH_P_8021AD)) {
+		struct _vlan_hdr *vlan_hdr;
+
+		vlan_hdr = (void *)eth + offset;
+		pkt->vlan_inner_offset = offset;
+		pkt->vlan_inner = bpf_ntohs(vlan_hdr->h_vlan_TCI)
+				& VLAN_VID_MASK;
+		eth_type        = vlan_hdr->h_vlan_encapsulated_proto;
+		offset += sizeof(*vlan_hdr);
+	}
+
+	pkt->l3_proto = bpf_ntohs(eth_type); /* Convert to host-byte-order */
+	pkt->l3_offset = offset;
+
+	return true;
+}
+
+/* Hint, VLANs are choosen to hit network-byte-order issues */
+#define TESTVLAN 4011 /* 0xFAB */
+// #define TO_VLAN  4000 /* 0xFA0 (hint 0xOA0 = 160) */
+
+SEC("xdp_drop_vlan_4011")
+int  xdp_prognum0(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data     = (void *)(long)ctx->data;
+	struct parse_pkt pkt = { 0 };
+
+	if (!parse_eth_frame(data, data_end, &pkt))
+		return XDP_ABORTED;
+
+	/* Drop specific VLAN ID example */
+	if (pkt.vlan_outer == TESTVLAN)
+		return XDP_ABORTED;
+	/*
+	 * Using XDP_ABORTED makes it possible to record this event,
+	 * via tracepoint xdp:xdp_exception like:
+	 *  # perf record -a -e xdp:xdp_exception
+	 *  # perf script
+	 */
+	return XDP_PASS;
+}
+/*
+Commands to setup VLAN on Linux to test packets gets dropped:
+
+ export ROOTDEV=ixgbe2
+ export VLANID=4011
+ ip link add link $ROOTDEV name $ROOTDEV.$VLANID type vlan id $VLANID
+ ip link set dev  $ROOTDEV.$VLANID up
+
+ ip link set dev $ROOTDEV mtu 1508
+ ip addr add 100.64.40.11/24 dev $ROOTDEV.$VLANID
+
+Load prog with ip tool:
+
+ ip link set $ROOTDEV xdp off
+ ip link set $ROOTDEV xdp object xdp_vlan01_kern.o section xdp_drop_vlan_4011
+
+*/
+
+/* Changing VLAN to zero, have same practical effect as removing the VLAN. */
+#define TO_VLAN	0
+
+SEC("xdp_vlan_change")
+int  xdp_prognum1(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data     = (void *)(long)ctx->data;
+	struct parse_pkt pkt = { 0 };
+
+	if (!parse_eth_frame(data, data_end, &pkt))
+		return XDP_ABORTED;
+
+	/* Change specific VLAN ID */
+	if (pkt.vlan_outer == TESTVLAN) {
+		struct _vlan_hdr *vlan_hdr = data + pkt.vlan_outer_offset;
+
+		/* Modifying VLAN, preserve top 4 bits */
+		vlan_hdr->h_vlan_TCI =
+			bpf_htons((bpf_ntohs(vlan_hdr->h_vlan_TCI) & 0xf000)
+				  | TO_VLAN);
+	}
+
+	return XDP_PASS;
+}
+
+/*
+ * Show XDP+TC can cooperate, on creating a VLAN rewriter.
+ * 1. Create a XDP prog that can "pop"/remove a VLAN header.
+ * 2. Create a TC-bpf prog that egress can add a VLAN header.
+ */
+
+#ifndef ETH_ALEN /* Ethernet MAC address length */
+#define ETH_ALEN	6	/* bytes */
+#endif
+#define VLAN_HDR_SZ	4	/* bytes */
+
+SEC("xdp_vlan_remove_outer")
+int  xdp_prognum2(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data     = (void *)(long)ctx->data;
+	struct parse_pkt pkt = { 0 };
+	char *dest;
+
+	if (!parse_eth_frame(data, data_end, &pkt))
+		return XDP_ABORTED;
+
+	/* Skip packet if no outer VLAN was detected */
+	if (pkt.vlan_outer_offset == 0)
+		return XDP_PASS;
+
+	/* Moving Ethernet header, dest overlap with src, memmove handle this */
+	dest = data;
+	dest+= VLAN_HDR_SZ;
+	/*
+	 * Notice: Taking over vlan_hdr->h_vlan_encapsulated_proto, by
+	 * only moving two MAC addrs (12 bytes), not overwriting last 2 bytes
+	 */
+	__builtin_memmove(dest, data, ETH_ALEN * 2);
+	/* Note: LLVM built-in memmove inlining require size to be constant */
+
+	/* Move start of packet header seen by Linux kernel stack */
+	bpf_xdp_adjust_head(ctx, VLAN_HDR_SZ);
+
+	return XDP_PASS;
+}
+
+static __always_inline
+void shift_mac_4bytes_16bit(void *data)
+{
+	__u16 *p = data;
+
+	p[7] = p[5]; /* delete p[7] was vlan_hdr->h_vlan_TCI */
+	p[6] = p[4]; /* delete p[6] was ethhdr->h_proto */
+	p[5] = p[3];
+	p[4] = p[2];
+	p[3] = p[1];
+	p[2] = p[0];
+}
+
+static __always_inline
+void shift_mac_4bytes_32bit(void *data)
+{
+	__u32 *p = data;
+
+	/* Assuming VLAN hdr present. The 4 bytes in p[3] that gets
+	 * overwritten, is ethhdr->h_proto and vlan_hdr->h_vlan_TCI.
+	 * The vlan_hdr->h_vlan_encapsulated_proto take over role as
+	 * ethhdr->h_proto.
+	 */
+	p[3] = p[2];
+	p[2] = p[1];
+	p[1] = p[0];
+}
+
+SEC("xdp_vlan_remove_outer2")
+int  xdp_prognum3(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data     = (void *)(long)ctx->data;
+	struct ethhdr *orig_eth = data;
+	struct parse_pkt pkt = { 0 };
+
+	if (!parse_eth_frame(orig_eth, data_end, &pkt))
+		return XDP_ABORTED;
+
+	/* Skip packet if no outer VLAN was detected */
+	if (pkt.vlan_outer_offset == 0)
+		return XDP_PASS;
+
+	/* Simply shift down MAC addrs 4 bytes, overwrite h_proto + TCI */
+	shift_mac_4bytes_32bit(data);
+
+	/* Move start of packet header seen by Linux kernel stack */
+	bpf_xdp_adjust_head(ctx, VLAN_HDR_SZ);
+
+	return XDP_PASS;
+}
+
+/*=====================================
+ *  BELOW: TC-hook based ebpf programs
+ * ====================================
+ * The TC-clsact eBPF programs (currently) need to be attach via TC commands
+ */
+
+SEC("tc_vlan_push")
+int _tc_progA(struct __sk_buff *ctx)
+{
+	bpf_skb_vlan_push(ctx, bpf_htons(ETH_P_8021Q), TESTVLAN);
+
+	return TC_ACT_OK;
+}
+/*
+Commands to setup TC to use above bpf prog:
+
+export ROOTDEV=ixgbe2
+export FILE=xdp_vlan01_kern.o
+
+# Re-attach clsact to clear/flush existing role
+tc qdisc del dev $ROOTDEV clsact 2> /dev/null ;\
+tc qdisc add dev $ROOTDEV clsact
+
+# Attach BPF prog EGRESS
+tc filter add dev $ROOTDEV egress \
+  prio 1 handle 1 bpf da obj $FILE sec tc_vlan_push
+
+tc filter show dev $ROOTDEV egress
+*/
diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh
new file mode 100755
index 000000000000..51a3a31d1aac
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_vlan.sh
@@ -0,0 +1,195 @@
+#!/bin/bash
+
+TESTNAME=xdp_vlan
+
+usage() {
+  echo "Testing XDP + TC eBPF VLAN manipulations: $TESTNAME"
+  echo ""
+  echo "Usage: $0 [-vfh]"
+  echo "  -v | --verbose : Verbose"
+  echo "  --flush        : Flush before starting (e.g. after --interactive)"
+  echo "  --interactive  : Keep netns setup running after test-run"
+  echo ""
+}
+
+cleanup()
+{
+	local status=$?
+
+	if [ "$status" = "0" ]; then
+		echo "selftests: $TESTNAME [PASS]";
+	else
+		echo "selftests: $TESTNAME [FAILED]";
+	fi
+
+	if [ -n "$INTERACTIVE" ]; then
+		echo "Namespace setup still active explore with:"
+		echo " ip netns exec ns1 bash"
+		echo " ip netns exec ns2 bash"
+		exit $status
+	fi
+
+	set +e
+	ip link del veth1 2> /dev/null
+	ip netns del ns1 2> /dev/null
+	ip netns del ns2 2> /dev/null
+}
+
+# Using external program "getopt" to get --long-options
+OPTIONS=$(getopt -o hvfi: \
+    --long verbose,flush,help,interactive,debug -- "$@")
+if (( $? != 0 )); then
+    usage
+    echo "selftests: $TESTNAME [FAILED] Error calling getopt, unknown option?"
+    exit 2
+fi
+eval set -- "$OPTIONS"
+
+##  --- Parse command line arguments / parameters ---
+while true; do
+	case "$1" in
+	    -v | --verbose)
+		export VERBOSE=yes
+		shift
+		;;
+	    -i | --interactive | --debug )
+		INTERACTIVE=yes
+		shift
+		;;
+	    -f | --flush )
+		cleanup
+		shift
+		;;
+	    -- )
+		shift
+		break
+		;;
+	    -h | --help )
+		usage;
+		echo "selftests: $TESTNAME [SKIP] usage help info requested"
+		exit 0
+		;;
+	    * )
+		shift
+		break
+		;;
+	esac
+done
+
+if [ "$EUID" -ne 0 ]; then
+	echo "selftests: $TESTNAME [FAILED] need root privileges"
+	exit 1
+fi
+
+ip link set dev lo xdp off 2>/dev/null > /dev/null
+if [ $? -ne 0 ];then
+	echo "selftests: $TESTNAME [SKIP] need ip xdp support"
+	exit 0
+fi
+
+# Interactive mode likely require us to cleanup netns
+if [ -n "$INTERACTIVE" ]; then
+	ip link del veth1 2> /dev/null
+	ip netns del ns1 2> /dev/null
+	ip netns del ns2 2> /dev/null
+fi
+
+# Exit on failure
+set -e
+
+# Some shell-tools dependencies
+which ip > /dev/null
+which tc > /dev/null
+which ethtool > /dev/null
+
+# Make rest of shell verbose, showing comments as doc/info
+if [ -n "$VERBOSE" ]; then
+    set -v
+fi
+
+# Create two namespaces
+ip netns add ns1
+ip netns add ns2
+
+# Run cleanup if failing or on kill
+trap cleanup 0 2 3 6 9
+
+# Create veth pair
+ip link add veth1 type veth peer name veth2
+
+# Move veth1 and veth2 into the respective namespaces
+ip link set veth1 netns ns1
+ip link set veth2 netns ns2
+
+# NOTICE: XDP require VLAN header inside packet payload
+#  - Thus, disable VLAN offloading driver features
+#  - For veth REMEMBER TX side VLAN-offload
+#
+# Disable rx-vlan-offload (mostly needed on ns1)
+ip netns exec ns1 ethtool -K veth1 rxvlan off
+ip netns exec ns2 ethtool -K veth2 rxvlan off
+#
+# Disable tx-vlan-offload (mostly needed on ns2)
+ip netns exec ns2 ethtool -K veth2 txvlan off
+ip netns exec ns1 ethtool -K veth1 txvlan off
+
+export IPADDR1=100.64.41.1
+export IPADDR2=100.64.41.2
+
+# In ns1/veth1 add IP-addr on plain net_device
+ip netns exec ns1 ip addr add ${IPADDR1}/24 dev veth1
+ip netns exec ns1 ip link set veth1 up
+
+# In ns2/veth2 create VLAN device
+export VLAN=4011
+export DEVNS2=veth2
+ip netns exec ns2 ip link add link $DEVNS2 name $DEVNS2.$VLAN type vlan id $VLAN
+ip netns exec ns2 ip addr add ${IPADDR2}/24 dev $DEVNS2.$VLAN
+ip netns exec ns2 ip link set $DEVNS2 up
+ip netns exec ns2 ip link set $DEVNS2.$VLAN up
+
+# Bringup lo in netns (to avoids confusing people using --interactive)
+ip netns exec ns1 ip link set lo up
+ip netns exec ns2 ip link set lo up
+
+# At this point, the hosts cannot reach each-other,
+# because ns2 are using VLAN tags on the packets.
+
+ip netns exec ns2 sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Okay ping fails"'
+
+
+# Now we can use the test_xdp_vlan.c program to pop/push these VLAN tags
+# ----------------------------------------------------------------------
+# In ns1: ingress use XDP to remove VLAN tags
+export DEVNS1=veth1
+export FILE=test_xdp_vlan.o
+
+# First test: Remove VLAN by setting VLAN ID 0, using "xdp_vlan_change"
+export XDP_PROG=xdp_vlan_change
+ip netns exec ns1 ip link set $DEVNS1 xdp object $FILE section $XDP_PROG
+
+# In ns1: egress use TC to add back VLAN tag 4011
+#  (del cmd)
+#  tc qdisc del dev $DEVNS1 clsact 2> /dev/null
+#
+ip netns exec ns1 tc qdisc add dev $DEVNS1 clsact
+ip netns exec ns1 tc filter add dev $DEVNS1 egress \
+  prio 1 handle 1 bpf da obj $FILE sec tc_vlan_push
+
+# Now the namespaces can reach each-other, test with ping:
+ip netns exec ns2 ping -W 2 -c 3 $IPADDR1
+ip netns exec ns1 ping -W 2 -c 3 $IPADDR2
+
+# Second test: Replace xdp prog, that fully remove vlan header
+#
+# Catch kernel bug for generic-XDP, that does didn't allow us to
+# remove a VLAN header, because skb->protocol still contain VLAN
+# ETH_P_8021Q indication, and this cause overwriting of our changes.
+#
+export XDP_PROG=xdp_vlan_remove_outer2
+ip netns exec ns1 ip link set $DEVNS1 xdp off
+ip netns exec ns1 ip link set $DEVNS1 xdp object $FILE section $XDP_PROG
+
+# Now the namespaces should still be able reach each-other, test with ping:
+ip netns exec ns2 ping -W 2 -c 3 $IPADDR1
+ip netns exec ns1 ping -W 2 -c 3 $IPADDR2
-- 
cgit 


From 372809055f6c830ff978564e09f58bcb9e9b937c Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 8 Oct 2018 18:50:41 +0000
Subject: selftests: forwarding: Have lldpad_app_wait_set() wait for unknown,
 too

Immediately after mlxsw module is probed and lldpad started, added APP
entries are briefly in "unknown" state before becoming "pending". That's
the state that lldpad_app_wait_set() typically sees, and since there are
no pending entries at that time, it bails out. However the entries have
not been pushed to the kernel yet at that point, and thus the test case
fails.

Fix by waiting for both unknown and pending entries to disappear before
proceeding.

Fixes: d159261f3662 ("selftests: mlxsw: Add test for trust-DSCP")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 0e73698b2048..85d253546684 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -251,7 +251,7 @@ lldpad_app_wait_set()
 {
 	local dev=$1; shift
 
-	while lldptool -t -i $dev -V APP -c app | grep -q pending; do
+	while lldptool -t -i $dev -V APP -c app | grep -Eq "pending|unknown"; do
 		echo "$dev: waiting for lldpad to push pending APP updates"
 		sleep 5
 	done
-- 
cgit 


From 970152591d5552fb52ddbf50af8d26b61f02bf39 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 8 Oct 2018 18:50:42 +0000
Subject: selftests: mlxsw: qos_mc_aware: Make executable

This is a self-standing test and as such should be itself executable.

Fixes: b5638d46c90a ("selftests: mlxsw: Add a test for UC behavior under MC flood")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 mode change 100644 => 100755 tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
old mode 100644
new mode 100755
-- 
cgit 


From d3c72d7a20d8ebb0618d06fc49e83a4d74d96205 Mon Sep 17 00:00:00 2001
From: Anders Roxell <anders.roxell@linaro.org>
Date: Wed, 10 Oct 2018 11:21:23 +0200
Subject: selftests: bpf: add config fragment LWTUNNEL

When test_lwt_seg6local.sh was added commit c99a84eac026
("selftests/bpf: test for seg6local End.BPF action") config fragment
wasn't added, and without CONFIG_LWTUNNEL enabled we see this:
Error: CONFIG_LWTUNNEL is not enabled in this kernel.
selftests: test_lwt_seg6local [FAILED]

Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/config | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 3655508f95fd..dd49df5e2df4 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -19,3 +19,4 @@ CONFIG_CRYPTO_SHA256=m
 CONFIG_VXLAN=y
 CONFIG_GENEVE=y
 CONFIG_NET_CLS_FLOWER=m
+CONFIG_LWTUNNEL=y
-- 
cgit 


From ef4ab8447aa2639d7a80a50f23d9f27c5c0db276 Mon Sep 17 00:00:00 2001
From: Anders Roxell <anders.roxell@linaro.org>
Date: Wed, 10 Oct 2018 16:27:04 +0200
Subject: selftests: bpf: install script with_addr.sh

When test_flow_dissector.sh runs it complains that it can't find script
with_addr.sh:

./test_flow_dissector.sh: line 81: ./with_addr.sh: No such file or
directory

Rework so that with_addr.sh gets installed, add it to
TEST_PROGS_EXTENDED variable.

Fixes: 50b3ed57dee9 ("selftests/bpf: test bpf flow dissection")
Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/Makefile | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index d24afe8b821d..d99dd6fc3fbe 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -53,6 +53,8 @@ TEST_PROGS := test_kmod.sh \
 	test_flow_dissector.sh \
 	test_xdp_vlan.sh
 
+TEST_PROGS_EXTENDED := with_addr.sh
+
 # Compile but not part of 'make run_tests'
 TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user \
 	flow_dissector_load test_flow_dissector
-- 
cgit 


From 3c718e677c2b35b449992adc36ecce883c467e98 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 11 Oct 2018 10:54:52 +0200
Subject: selftests: rtnetlink.sh explicitly requires bash.

the script rtnetlink.sh requires a bash-only features (sleep with sub-second
precision). This may cause random test failure if the default shell is not
bash.
Address the above explicitly requiring bash as the script interpreter.

Fixes: 33b01b7b4f19 ("selftests: add rtnetlink test script")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rtnetlink.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 08c341b49760..e101af52d1d6 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 #
 # This test is for checking rtnetlink callpaths, and get as much coverage as possible.
 #
-- 
cgit 


From 12a2ea962c06efb30764c47b140d2ec9d3cd7cb0 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 11 Oct 2018 10:54:53 +0200
Subject: selftests: udpgso_bench.sh explicitly requires bash

The udpgso_bench.sh script requires several bash-only features. This
may cause random failures if the default shell is not bash.
Address the above explicitly requiring bash as the script interpreter

Fixes: 3a687bef148d ("selftests: udp gso benchmark")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/udpgso_bench.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh
index 850767befa47..99e537ab5ad9 100755
--- a/tools/testing/selftests/net/udpgso_bench.sh
+++ b/tools/testing/selftests/net/udpgso_bench.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 #
 # Run a series of udpgso benchmarks
-- 
cgit 


From 9dffa76c21268f6188b04b966089b5110a7447ef Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 11 Oct 2018 11:17:37 +0200
Subject: selftests: use posix-style redirection in ip_defrag.sh

The ip_defrag.sh script requires bash-style output redirection but
use the default shell. This may cause random failures if the default
shell is not bash.
Address the above using posix compliant output redirection.

Fixes: 02c7f38b7ace ("selftests/net: add ip_defrag selftest")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/ip_defrag.sh | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/ip_defrag.sh b/tools/testing/selftests/net/ip_defrag.sh
index 3a4042d918f0..f34672796044 100755
--- a/tools/testing/selftests/net/ip_defrag.sh
+++ b/tools/testing/selftests/net/ip_defrag.sh
@@ -11,10 +11,10 @@ readonly NETNS="ns-$(mktemp -u XXXXXX)"
 setup() {
 	ip netns add "${NETNS}"
 	ip -netns "${NETNS}" link set lo up
-	ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null
-	ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null
-	ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_high_thresh=9000000 &> /dev/null
-	ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_low_thresh=7000000 &> /dev/null
+	ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_high_thresh=9000000 >/dev/null 2>&1
+	ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_low_thresh=7000000 >/dev/null 2>&1
+	ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_high_thresh=9000000 >/dev/null 2>&1
+	ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_low_thresh=7000000 >/dev/null 2>&1
 }
 
 cleanup() {
-- 
cgit 


From e9dd904708c463ff57d019f4482c48d057fa4d7e Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Sat, 13 Oct 2018 02:46:02 +0200
Subject: bpf: add tls support for testing in test_sockmap

This adds a --ktls option to test_sockmap in order to enable the
combination of ktls and sockmap to run, which makes for another
batch of 648 test cases for both in combination.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_sockmap.c | 89 ++++++++++++++++++++++++++++++
 1 file changed, 89 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index ac7de38e5c63..10a5fa83c75a 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -71,6 +71,7 @@ int txmsg_start;
 int txmsg_end;
 int txmsg_ingress;
 int txmsg_skb;
+int ktls;
 
 static const struct option long_options[] = {
 	{"help",	no_argument,		NULL, 'h' },
@@ -92,6 +93,7 @@ static const struct option long_options[] = {
 	{"txmsg_end",	required_argument,	NULL, 'e'},
 	{"txmsg_ingress", no_argument,		&txmsg_ingress, 1 },
 	{"txmsg_skb", no_argument,		&txmsg_skb, 1 },
+	{"ktls", no_argument,			&ktls, 1 },
 	{0, 0, NULL, 0 }
 };
 
@@ -112,6 +114,76 @@ static void usage(char *argv[])
 	printf("\n");
 }
 
+#define TCP_ULP 31
+#define TLS_TX 1
+#define TLS_RX 2
+#include <linux/tls.h>
+
+char *sock_to_string(int s)
+{
+	if (s == c1)
+		return "client1";
+	else if (s == c2)
+		return "client2";
+	else if (s == s1)
+		return "server1";
+	else if (s == s2)
+		return "server2";
+	else if (s == p1)
+		return "peer1";
+	else if (s == p2)
+		return "peer2";
+	else
+		return "unknown";
+}
+
+static int sockmap_init_ktls(int verbose, int s)
+{
+	struct tls12_crypto_info_aes_gcm_128 tls_tx = {
+		.info = {
+			.version     = TLS_1_2_VERSION,
+			.cipher_type = TLS_CIPHER_AES_GCM_128,
+		},
+	};
+	struct tls12_crypto_info_aes_gcm_128 tls_rx = {
+		.info = {
+			.version     = TLS_1_2_VERSION,
+			.cipher_type = TLS_CIPHER_AES_GCM_128,
+		},
+	};
+	int so_buf = 6553500;
+	int err;
+
+	err = setsockopt(s, 6, TCP_ULP, "tls", sizeof("tls"));
+	if (err) {
+		fprintf(stderr, "setsockopt: TCP_ULP(%s) failed with error %i\n", sock_to_string(s), err);
+		return -EINVAL;
+	}
+	err = setsockopt(s, SOL_TLS, TLS_TX, (void *)&tls_tx, sizeof(tls_tx));
+	if (err) {
+		fprintf(stderr, "setsockopt: TLS_TX(%s) failed with error %i\n", sock_to_string(s), err);
+		return -EINVAL;
+	}
+	err = setsockopt(s, SOL_TLS, TLS_RX, (void *)&tls_rx, sizeof(tls_rx));
+	if (err) {
+		fprintf(stderr, "setsockopt: TLS_RX(%s) failed with error %i\n", sock_to_string(s), err);
+		return -EINVAL;
+	}
+	err = setsockopt(s, SOL_SOCKET, SO_SNDBUF, &so_buf, sizeof(so_buf));
+	if (err) {
+		fprintf(stderr, "setsockopt: (%s) failed sndbuf with error %i\n", sock_to_string(s), err);
+		return -EINVAL;
+	}
+	err = setsockopt(s, SOL_SOCKET, SO_RCVBUF, &so_buf, sizeof(so_buf));
+	if (err) {
+		fprintf(stderr, "setsockopt: (%s) failed rcvbuf with error %i\n", sock_to_string(s), err);
+		return -EINVAL;
+	}
+
+	if (verbose)
+		fprintf(stdout, "socket(%s) kTLS enabled\n", sock_to_string(s));
+	return 0;
+}
 static int sockmap_init_sockets(int verbose)
 {
 	int i, err, one = 1;
@@ -456,6 +528,21 @@ static int sendmsg_test(struct sockmap_options *opt)
 	else
 		rx_fd = p2;
 
+	if (ktls) {
+		/* Redirecting into non-TLS socket which sends into a TLS
+		 * socket is not a valid test. So in this case lets not
+		 * enable kTLS but still run the test.
+		 */
+		if (!txmsg_redir || (txmsg_redir && txmsg_ingress)) {
+			err = sockmap_init_ktls(opt->verbose, rx_fd);
+			if (err)
+				return err;
+		}
+		err = sockmap_init_ktls(opt->verbose, c1);
+		if (err)
+			return err;
+	}
+
 	rxpid = fork();
 	if (rxpid == 0) {
 		if (opt->drop_expected)
@@ -907,6 +994,8 @@ static void test_options(char *options)
 		strncat(options, "ingress,", OPTSTRING);
 	if (txmsg_skb)
 		strncat(options, "skb,", OPTSTRING);
+	if (ktls)
+		strncat(options, "ktls,", OPTSTRING);
 }
 
 static int __test_exec(int cgrp, int test, struct sockmap_options *opt)
-- 
cgit 


From 55bbc8ff4987d05b7d2f2d513caabd0a58fec021 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Fri, 12 Oct 2018 23:54:13 +0200
Subject: selftests: pmtu: Allow selection of single tests

As number of tests is growing, it's quite convenient to allow
single tests to be run.

Display usage when the script is run with any invalid argument,
keep existing semantics when no arguments are passed so that
automated runs won't break.

Instead of just looping on the list of requested tests, if any,
check first that they exist, and go through them in a nested
loop to keep the existing way to display test descriptions.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/pmtu.sh | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index b9cdb68df4c5..8278a24f5ba6 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -641,6 +641,20 @@ test_pmtu_vti6_link_change_mtu() {
 	return ${fail}
 }
 
+usage() {
+	echo
+	echo "$0 [TEST]..."
+	echo "If no TEST argument is given, all tests will be run."
+	echo
+	echo "Available tests${tests}"
+	exit 1
+}
+
+for arg do
+	# Check first that all requested tests are available before running any
+	command -v > /dev/null "test_${arg}" || { echo "=== Test ${arg} not found"; usage; }
+done
+
 trap cleanup EXIT
 
 exitcode=0
@@ -650,6 +664,13 @@ IFS="
 for t in ${tests}; do
 	[ $desc -eq 0 ] && name="${t}" && desc=1 && continue || desc=0
 
+	run_this=1
+	for arg do
+		[ "${arg}" = "${name}" ] && run_this=1 && break
+		run_this=0
+	done
+	[ $run_this -eq 0 ] && continue
+
 	(
 		unset IFS
 		eval test_${name}
-- 
cgit 


From bb059fb20447c869970ebd296010c1a822706c58 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Fri, 12 Oct 2018 23:54:14 +0200
Subject: selftests: pmtu: Add optional traffic captures for single tests

If --trace is passed as an option and tcpdump is available,
capture traffic for all relevant interfaces to per-test pcap
files named <test>_<interface>.pcap.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/pmtu.sh | 60 ++++++++++++++++++++++++++++++++-----
 1 file changed, 53 insertions(+), 7 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 8278a24f5ba6..a369d616b390 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -142,6 +142,7 @@ dummy6_mask="64"
 
 cleanup_done=1
 err_buf=
+tcpdump_pids=
 
 err() {
 	err_buf="${err_buf}${1}
@@ -284,7 +285,24 @@ setup() {
 	done
 }
 
+trace() {
+	[ $tracing -eq 0 ] && return
+
+	for arg do
+		[ "${ns_cmd}" = "" ] && ns_cmd="${arg}" && continue
+		${ns_cmd} tcpdump -s 0 -i "${arg}" -w "${name}_${arg}.pcap" 2> /dev/null &
+		tcpdump_pids="${tcpdump_pids} $!"
+		ns_cmd=
+	done
+	sleep 1
+}
+
 cleanup() {
+	for pid in ${tcpdump_pids}; do
+		kill ${pid}
+	done
+	tcpdump_pids=
+
 	[ ${cleanup_done} -eq 1 ] && return
 	for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
 		ip netns del ${n} 2> /dev/null
@@ -357,6 +375,10 @@ test_pmtu_ipvX() {
 	family=${1}
 
 	setup namespaces routing || return 2
+	trace "${ns_a}"  veth_A-R1    "${ns_r1}" veth_R1-A \
+	      "${ns_r1}" veth_R1-B    "${ns_b}"  veth_B-R1 \
+	      "${ns_a}"  veth_A-R2    "${ns_r2}" veth_R2-A \
+	      "${ns_r2}" veth_R2-B    "${ns_b}"  veth_B-R2
 
 	if [ ${family} -eq 4 ]; then
 		ping=ping
@@ -445,6 +467,8 @@ test_pmtu_ipv6_exception() {
 
 test_pmtu_vti4_exception() {
 	setup namespaces veth vti4 xfrm4 || return 2
+	trace "${ns_a}" veth_a    "${ns_b}" veth_b \
+	      "${ns_a}" vti4_a    "${ns_b}" vti4_b
 
 	veth_mtu=1500
 	vti_mtu=$((veth_mtu - 20))
@@ -473,6 +497,8 @@ test_pmtu_vti4_exception() {
 
 test_pmtu_vti6_exception() {
 	setup namespaces veth vti6 xfrm6 || return 2
+	trace "${ns_a}" veth_a    "${ns_b}" veth_b \
+	      "${ns_a}" vti6_a    "${ns_b}" vti6_b
 	fail=0
 
 	# Create route exception by exceeding link layer MTU
@@ -643,29 +669,49 @@ test_pmtu_vti6_link_change_mtu() {
 
 usage() {
 	echo
-	echo "$0 [TEST]..."
+	echo "$0 [OPTIONS] [TEST]..."
 	echo "If no TEST argument is given, all tests will be run."
 	echo
+	echo "Options"
+	echo "  --trace: capture traffic to TEST_INTERFACE.pcap"
+	echo
 	echo "Available tests${tests}"
 	exit 1
 }
 
+exitcode=0
+desc=0
+IFS="	
+"
+
+tracing=0
 for arg do
-	# Check first that all requested tests are available before running any
-	command -v > /dev/null "test_${arg}" || { echo "=== Test ${arg} not found"; usage; }
+	if [ "${arg}" != "${arg#--*}" ]; then
+		opt="${arg#--}"
+		if [ "${opt}" = "trace" ]; then
+			if which tcpdump > /dev/null 2>&1; then
+				tracing=1
+			else
+				echo "=== tcpdump not available, tracing disabled"
+			fi
+		else
+			usage
+		fi
+	else
+		# Check first that all requested tests are available before
+		# running any
+		command -v > /dev/null "test_${arg}" || { echo "=== Test ${arg} not found"; usage; }
+	fi
 done
 
 trap cleanup EXIT
 
-exitcode=0
-desc=0
-IFS="	
-"
 for t in ${tests}; do
 	[ $desc -eq 0 ] && name="${t}" && desc=1 && continue || desc=0
 
 	run_this=1
 	for arg do
+		[ "${arg}" != "${arg#--*}" ] && continue
 		[ "${arg}" = "${name}" ] && run_this=1 && break
 		run_this=0
 	done
-- 
cgit 


From 421f4292f46e871cdcf8bdc3e6fdfcefe2e81a9d Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 16 Oct 2018 15:59:36 +0200
Subject: bpf, tls: add tls header to tools infrastructure

Andrey reported a build error for the BPF kselftest suite when compiled on
a machine which does not have tls related header bits installed natively:

  test_sockmap.c:120:23: fatal error: linux/tls.h: No such file or directory
   #include <linux/tls.h>
                         ^
  compilation terminated.

Fix it by adding the header to the tools include infrastructure and add
definitions such as SOL_TLS that could potentially be missing.

Fixes: e9dd904708c4 ("bpf: add tls support for testing in test_sockmap")
Reported-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/uapi/linux/tls.h             | 78 ++++++++++++++++++++++++++++++
 tools/testing/selftests/bpf/test_sockmap.c | 13 +++--
 2 files changed, 86 insertions(+), 5 deletions(-)
 create mode 100644 tools/include/uapi/linux/tls.h

(limited to 'tools/testing')

diff --git a/tools/include/uapi/linux/tls.h b/tools/include/uapi/linux/tls.h
new file mode 100644
index 000000000000..ff02287495ac
--- /dev/null
+++ b/tools/include/uapi/linux/tls.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
+/*
+ * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _UAPI_LINUX_TLS_H
+#define _UAPI_LINUX_TLS_H
+
+#include <linux/types.h>
+
+/* TLS socket options */
+#define TLS_TX			1	/* Set transmit parameters */
+#define TLS_RX			2	/* Set receive parameters */
+
+/* Supported versions */
+#define TLS_VERSION_MINOR(ver)	((ver) & 0xFF)
+#define TLS_VERSION_MAJOR(ver)	(((ver) >> 8) & 0xFF)
+
+#define TLS_VERSION_NUMBER(id)	((((id##_VERSION_MAJOR) & 0xFF) << 8) |	\
+				 ((id##_VERSION_MINOR) & 0xFF))
+
+#define TLS_1_2_VERSION_MAJOR	0x3
+#define TLS_1_2_VERSION_MINOR	0x3
+#define TLS_1_2_VERSION		TLS_VERSION_NUMBER(TLS_1_2)
+
+/* Supported ciphers */
+#define TLS_CIPHER_AES_GCM_128				51
+#define TLS_CIPHER_AES_GCM_128_IV_SIZE			8
+#define TLS_CIPHER_AES_GCM_128_KEY_SIZE		16
+#define TLS_CIPHER_AES_GCM_128_SALT_SIZE		4
+#define TLS_CIPHER_AES_GCM_128_TAG_SIZE		16
+#define TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE		8
+
+#define TLS_SET_RECORD_TYPE	1
+#define TLS_GET_RECORD_TYPE	2
+
+struct tls_crypto_info {
+	__u16 version;
+	__u16 cipher_type;
+};
+
+struct tls12_crypto_info_aes_gcm_128 {
+	struct tls_crypto_info info;
+	unsigned char iv[TLS_CIPHER_AES_GCM_128_IV_SIZE];
+	unsigned char key[TLS_CIPHER_AES_GCM_128_KEY_SIZE];
+	unsigned char salt[TLS_CIPHER_AES_GCM_128_SALT_SIZE];
+	unsigned char rec_seq[TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE];
+};
+
+#endif /* _UAPI_LINUX_TLS_H */
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 10a5fa83c75a..7cb69ce6dfa2 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -28,6 +28,7 @@
 #include <linux/sock_diag.h>
 #include <linux/bpf.h>
 #include <linux/if_link.h>
+#include <linux/tls.h>
 #include <assert.h>
 #include <libgen.h>
 
@@ -43,6 +44,13 @@
 int running;
 static void running_handler(int a);
 
+#ifndef TCP_ULP
+# define TCP_ULP 31
+#endif
+#ifndef SOL_TLS
+# define SOL_TLS 282
+#endif
+
 /* randomly selected ports for testing on lo */
 #define S1_PORT 10000
 #define S2_PORT 10001
@@ -114,11 +122,6 @@ static void usage(char *argv[])
 	printf("\n");
 }
 
-#define TCP_ULP 31
-#define TLS_TX 1
-#define TLS_RX 2
-#include <linux/tls.h>
-
 char *sock_to_string(int s)
 {
 	if (s == c1)
-- 
cgit 


From 6c930268bcc4cef62194daf151097d2b94f67718 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:24 +0200
Subject: kvm: selftests: vcpu_setup: set cr4.osfxsr

Guest code may want to call functions that have variable arguments.
To do so, we either need to compile with -mno-sse or enable SSE in
the VCPUs. As it should be pretty safe to turn on the feature, and
-mno-sse would make linking test code with standard libraries
difficult, we choose the feature enabling.

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/lib/x86.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/lib/x86.c b/tools/testing/selftests/kvm/lib/x86.c
index a3122f1949a8..bb6c65ebfa77 100644
--- a/tools/testing/selftests/kvm/lib/x86.c
+++ b/tools/testing/selftests/kvm/lib/x86.c
@@ -626,7 +626,7 @@ void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot)
 	switch (vm->mode) {
 	case VM_MODE_FLAT48PG:
 		sregs.cr0 = X86_CR0_PE | X86_CR0_NE | X86_CR0_PG;
-		sregs.cr4 |= X86_CR4_PAE;
+		sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR;
 		sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
 
 		kvm_seg_set_unusable(&sregs.ldt);
-- 
cgit 


From 14c47b7530e2db1ab1d42ebbe99b2a58b8443ce7 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:25 +0200
Subject: kvm: selftests: introduce ucall

Rework the guest exit to userspace code to generalize the concept
into what it is, a "hypercall to userspace", and provide two
implementations of it: the PortIO version currently used, but only
useable by x86, and an MMIO version that other architectures (except
s390) can use.

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/Makefile               |   2 +-
 tools/testing/selftests/kvm/cr4_cpuid_sync_test.c  |  12 +-
 tools/testing/selftests/kvm/dirty_log_test.c       |   5 +-
 tools/testing/selftests/kvm/include/kvm_util.h     |  76 ++++++-----
 tools/testing/selftests/kvm/lib/kvm_util.c         |  15 +--
 .../testing/selftests/kvm/lib/kvm_util_internal.h  |   1 +
 tools/testing/selftests/kvm/lib/ucall.c            | 144 +++++++++++++++++++++
 tools/testing/selftests/kvm/platform_info_test.c   |  12 +-
 tools/testing/selftests/kvm/state_test.c           |  23 ++--
 tools/testing/selftests/kvm/vmx_tsc_adjust_test.c  |  17 ++-
 10 files changed, 222 insertions(+), 85 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/lib/ucall.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index ec32dad3c3f0..08426f036353 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -3,7 +3,7 @@ all:
 top_srcdir = ../../../../
 UNAME_M := $(shell uname -m)
 
-LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c
+LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/ucall.c lib/sparsebit.c
 LIBKVM_x86_64 = lib/x86.c lib/vmx.c
 
 TEST_GEN_PROGS_x86_64 = platform_info_test
diff --git a/tools/testing/selftests/kvm/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/cr4_cpuid_sync_test.c
index 11ec358bf969..fd4f419fe9ab 100644
--- a/tools/testing/selftests/kvm/cr4_cpuid_sync_test.c
+++ b/tools/testing/selftests/kvm/cr4_cpuid_sync_test.c
@@ -67,6 +67,7 @@ int main(int argc, char *argv[])
 	struct kvm_vm *vm;
 	struct kvm_sregs sregs;
 	struct kvm_cpuid_entry2 *entry;
+	struct ucall uc;
 	int rc;
 
 	entry = kvm_get_supported_cpuid_entry(1);
@@ -87,21 +88,20 @@ int main(int argc, char *argv[])
 		rc = _vcpu_run(vm, VCPU_ID);
 
 		if (run->exit_reason == KVM_EXIT_IO) {
-			switch (run->io.port) {
-			case GUEST_PORT_SYNC:
+			switch (get_ucall(vm, VCPU_ID, &uc)) {
+			case UCALL_SYNC:
 				/* emulate hypervisor clearing CR4.OSXSAVE */
 				vcpu_sregs_get(vm, VCPU_ID, &sregs);
 				sregs.cr4 &= ~X86_CR4_OSXSAVE;
 				vcpu_sregs_set(vm, VCPU_ID, &sregs);
 				break;
-			case GUEST_PORT_ABORT:
+			case UCALL_ABORT:
 				TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
 				break;
-			case GUEST_PORT_DONE:
+			case UCALL_DONE:
 				goto done;
 			default:
-				TEST_ASSERT(false, "Unknown port 0x%x.",
-					    run->io.port);
+				TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
 			}
 		}
 	}
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 0c2cdc105f96..7cf3e4ae6046 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -110,7 +110,7 @@ void *vcpu_worker(void *data)
 	uint64_t loops, *guest_array, pages_count = 0;
 	struct kvm_vm *vm = data;
 	struct kvm_run *run;
-	struct guest_args args;
+	struct ucall uc;
 
 	run = vcpu_state(vm, VCPU_ID);
 
@@ -124,9 +124,8 @@ void *vcpu_worker(void *data)
 	while (!READ_ONCE(host_quit)) {
 		/* Let the guest to dirty these random pages */
 		ret = _vcpu_run(vm, VCPU_ID);
-		guest_args_read(vm, VCPU_ID, &args);
 		if (run->exit_reason == KVM_EXIT_IO &&
-		    args.port == GUEST_PORT_SYNC) {
+		    get_ucall(vm, VCPU_ID, &uc) == UCALL_SYNC) {
 			pages_count += TEST_PAGES_PER_LOOP;
 			generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
 		} else {
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 3acf9a91704c..22667dd48a9c 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -152,43 +152,49 @@ allocate_kvm_dirty_log(struct kvm_userspace_memory_region *region);
 
 int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd);
 
-#define GUEST_PORT_SYNC         0x1000
-#define GUEST_PORT_ABORT        0x1001
-#define GUEST_PORT_DONE         0x1002
-
-static inline void __exit_to_l0(uint16_t port, uint64_t arg0, uint64_t arg1)
-{
-	__asm__ __volatile__("in %[port], %%al"
-			     :
-			     : [port]"d"(port), "D"(arg0), "S"(arg1)
-			     : "rax");
-}
-
-/*
- * Allows to pass three arguments to the host: port is 16bit wide,
- * arg0 & arg1 are 64bit wide
- */
-#define GUEST_SYNC_ARGS(_port, _arg0, _arg1) \
-	__exit_to_l0(_port, (uint64_t) (_arg0), (uint64_t) (_arg1))
-
-#define GUEST_ASSERT(_condition) do {				\
-		if (!(_condition))				\
-			GUEST_SYNC_ARGS(GUEST_PORT_ABORT,	\
-					"Failed guest assert: "	\
-					#_condition, __LINE__);	\
-	} while (0)
-
-#define GUEST_SYNC(stage)  GUEST_SYNC_ARGS(GUEST_PORT_SYNC, "hello", stage)
+#define sync_global_to_guest(vm, g) ({				\
+	typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g));	\
+	memcpy(_p, &(g), sizeof(g));				\
+})
+
+#define sync_global_from_guest(vm, g) ({			\
+	typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g));	\
+	memcpy(&(g), _p, sizeof(g));				\
+})
+
+/* ucall implementation types */
+typedef enum {
+	UCALL_PIO,
+	UCALL_MMIO,
+} ucall_type_t;
+
+/* Common ucalls */
+enum {
+	UCALL_NONE,
+	UCALL_SYNC,
+	UCALL_ABORT,
+	UCALL_DONE,
+};
 
-#define GUEST_DONE()  GUEST_SYNC_ARGS(GUEST_PORT_DONE, 0, 0)
+#define UCALL_MAX_ARGS 6
 
-struct guest_args {
-	uint64_t arg0;
-	uint64_t arg1;
-	uint16_t port;
-} __attribute__ ((packed));
+struct ucall {
+	uint64_t cmd;
+	uint64_t args[UCALL_MAX_ARGS];
+};
 
-void guest_args_read(struct kvm_vm *vm, uint32_t vcpu_id,
-		     struct guest_args *args);
+void ucall_init(struct kvm_vm *vm, ucall_type_t type, void *arg);
+void ucall_uninit(struct kvm_vm *vm);
+void ucall(uint64_t cmd, int nargs, ...);
+uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc);
+
+#define GUEST_SYNC(stage)	ucall(UCALL_SYNC, 2, "hello", stage)
+#define GUEST_DONE()		ucall(UCALL_DONE, 0)
+#define GUEST_ASSERT(_condition) do {			\
+	if (!(_condition))				\
+		ucall(UCALL_ABORT, 2,			\
+			"Failed guest assert: "		\
+			#_condition, __LINE__);		\
+} while (0)
 
 #endif /* SELFTEST_KVM_UTIL_H */
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 6fd8c089cafc..4bd31bf04f53 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -133,6 +133,7 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	case VM_MODE_FLAT48PG:
 		vm->page_size = 0x1000;
 		vm->page_shift = 12;
+		vm->va_bits = 48;
 
 		/* Limit to 48-bit canonical virtual addresses. */
 		vm->vpages_valid = sparsebit_alloc();
@@ -1669,17 +1670,3 @@ void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva)
 {
 	return addr_gpa2hva(vm, addr_gva2gpa(vm, gva));
 }
-
-void guest_args_read(struct kvm_vm *vm, uint32_t vcpu_id,
-		     struct guest_args *args)
-{
-	struct kvm_run *run = vcpu_state(vm, vcpu_id);
-	struct kvm_regs regs;
-
-	memset(&regs, 0, sizeof(regs));
-	vcpu_regs_get(vm, vcpu_id, &regs);
-
-	args->port = run->io.port;
-	args->arg0 = regs.rdi;
-	args->arg1 = regs.rsi;
-}
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index 542ed606b338..8fa7c9f7567a 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -47,6 +47,7 @@ struct kvm_vm {
 	int fd;
 	unsigned int page_size;
 	unsigned int page_shift;
+	unsigned int va_bits;
 	uint64_t max_gfn;
 	struct vcpu *vcpu_head;
 	struct userspace_mem_region *userspace_mem_region_head;
diff --git a/tools/testing/selftests/kvm/lib/ucall.c b/tools/testing/selftests/kvm/lib/ucall.c
new file mode 100644
index 000000000000..4777f9bb5194
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/ucall.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ucall support. A ucall is a "hypercall to userspace".
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+#include "kvm_util.h"
+#include "kvm_util_internal.h"
+
+#define UCALL_PIO_PORT ((uint16_t)0x1000)
+
+static ucall_type_t ucall_type;
+static vm_vaddr_t *ucall_exit_mmio_addr;
+
+static bool ucall_mmio_init(struct kvm_vm *vm, vm_paddr_t gpa)
+{
+	if (kvm_userspace_memory_region_find(vm, gpa, gpa + 1))
+		return false;
+
+	virt_pg_map(vm, gpa, gpa, 0);
+
+	ucall_exit_mmio_addr = (vm_vaddr_t *)gpa;
+	sync_global_to_guest(vm, ucall_exit_mmio_addr);
+
+	return true;
+}
+
+void ucall_init(struct kvm_vm *vm, ucall_type_t type, void *arg)
+{
+	ucall_type = type;
+	sync_global_to_guest(vm, ucall_type);
+
+	if (type == UCALL_PIO)
+		return;
+
+	if (type == UCALL_MMIO) {
+		vm_paddr_t gpa, start, end, step;
+		bool ret;
+
+		if (arg) {
+			gpa = (vm_paddr_t)arg;
+			ret = ucall_mmio_init(vm, gpa);
+			TEST_ASSERT(ret, "Can't set ucall mmio address to %lx", gpa);
+			return;
+		}
+
+		/*
+		 * Find an address within the allowed virtual address space,
+		 * that does _not_ have a KVM memory region associated with it.
+		 * Identity mapping an address like this allows the guest to
+		 * access it, but as KVM doesn't know what to do with it, it
+		 * will assume it's something userspace handles and exit with
+		 * KVM_EXIT_MMIO. Well, at least that's how it works for AArch64.
+		 * Here we start with a guess that the addresses around two
+		 * thirds of the VA space are unmapped and then work both down
+		 * and up from there in 1/6 VA space sized steps.
+		 */
+		start = 1ul << (vm->va_bits * 2 / 3);
+		end = 1ul << vm->va_bits;
+		step = 1ul << (vm->va_bits / 6);
+		for (gpa = start; gpa >= 0; gpa -= step) {
+			if (ucall_mmio_init(vm, gpa & ~(vm->page_size - 1)))
+				return;
+		}
+		for (gpa = start + step; gpa < end; gpa += step) {
+			if (ucall_mmio_init(vm, gpa & ~(vm->page_size - 1)))
+				return;
+		}
+		TEST_ASSERT(false, "Can't find a ucall mmio address");
+	}
+}
+
+void ucall_uninit(struct kvm_vm *vm)
+{
+	ucall_type = 0;
+	sync_global_to_guest(vm, ucall_type);
+	ucall_exit_mmio_addr = 0;
+	sync_global_to_guest(vm, ucall_exit_mmio_addr);
+}
+
+static void ucall_pio_exit(struct ucall *uc)
+{
+#ifdef __x86_64__
+	asm volatile("in %[port], %%al"
+		: : [port] "d" (UCALL_PIO_PORT), "D" (uc) : "rax");
+#endif
+}
+
+static void ucall_mmio_exit(struct ucall *uc)
+{
+	*ucall_exit_mmio_addr = (vm_vaddr_t)uc;
+}
+
+void ucall(uint64_t cmd, int nargs, ...)
+{
+	struct ucall uc = {
+		.cmd = cmd,
+	};
+	va_list va;
+	int i;
+
+	nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS;
+
+	va_start(va, nargs);
+	for (i = 0; i < nargs; ++i)
+		uc.args[i] = va_arg(va, uint64_t);
+	va_end(va);
+
+	switch (ucall_type) {
+	case UCALL_PIO:
+		ucall_pio_exit(&uc);
+		break;
+	case UCALL_MMIO:
+		ucall_mmio_exit(&uc);
+		break;
+	};
+}
+
+uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc)
+{
+	struct kvm_run *run = vcpu_state(vm, vcpu_id);
+
+	memset(uc, 0, sizeof(*uc));
+
+#ifdef __x86_64__
+	if (ucall_type == UCALL_PIO && run->exit_reason == KVM_EXIT_IO &&
+	    run->io.port == UCALL_PIO_PORT) {
+		struct kvm_regs regs;
+		vcpu_regs_get(vm, vcpu_id, &regs);
+		memcpy(uc, addr_gva2hva(vm, (vm_vaddr_t)regs.rdi), sizeof(*uc));
+		return uc->cmd;
+	}
+#endif
+	if (ucall_type == UCALL_MMIO && run->exit_reason == KVM_EXIT_MMIO &&
+	    run->mmio.phys_addr == (uint64_t)ucall_exit_mmio_addr) {
+		vm_vaddr_t gva;
+		TEST_ASSERT(run->mmio.is_write && run->mmio.len == 8,
+			    "Unexpected ucall exit mmio address access");
+		gva = *(vm_vaddr_t *)run->mmio.data;
+		memcpy(uc, addr_gva2hva(vm, gva), sizeof(*uc));
+	}
+
+	return uc->cmd;
+}
diff --git a/tools/testing/selftests/kvm/platform_info_test.c b/tools/testing/selftests/kvm/platform_info_test.c
index 3764e7121265..aa6a14331461 100644
--- a/tools/testing/selftests/kvm/platform_info_test.c
+++ b/tools/testing/selftests/kvm/platform_info_test.c
@@ -48,7 +48,7 @@ static void set_msr_platform_info_enabled(struct kvm_vm *vm, bool enable)
 static void test_msr_platform_info_enabled(struct kvm_vm *vm)
 {
 	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
-	struct guest_args args;
+	struct ucall uc;
 
 	set_msr_platform_info_enabled(vm, true);
 	vcpu_run(vm, VCPU_ID);
@@ -56,11 +56,11 @@ static void test_msr_platform_info_enabled(struct kvm_vm *vm)
 			"Exit_reason other than KVM_EXIT_IO: %u (%s),\n",
 			run->exit_reason,
 			exit_reason_str(run->exit_reason));
-	guest_args_read(vm, VCPU_ID, &args);
-	TEST_ASSERT(args.port == GUEST_PORT_SYNC,
-			"Received IO from port other than PORT_HOST_SYNC: %u\n",
-			run->io.port);
-	TEST_ASSERT((args.arg1 & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) ==
+	get_ucall(vm, VCPU_ID, &uc);
+	TEST_ASSERT(uc.cmd == UCALL_SYNC,
+			"Received ucall other than UCALL_SYNC: %u\n",
+			ucall);
+	TEST_ASSERT((uc.args[1] & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) ==
 		MSR_PLATFORM_INFO_MAX_TURBO_RATIO,
 		"Expected MSR_PLATFORM_INFO to have max turbo ratio mask: %i.",
 		MSR_PLATFORM_INFO_MAX_TURBO_RATIO);
diff --git a/tools/testing/selftests/kvm/state_test.c b/tools/testing/selftests/kvm/state_test.c
index 900e3e9dfb9f..cdf82735d6e7 100644
--- a/tools/testing/selftests/kvm/state_test.c
+++ b/tools/testing/selftests/kvm/state_test.c
@@ -127,6 +127,7 @@ int main(int argc, char *argv[])
 	struct kvm_vm *vm;
 	struct kvm_run *run;
 	struct kvm_x86_state *state;
+	struct ucall uc;
 	int stage;
 
 	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
@@ -155,23 +156,23 @@ int main(int argc, char *argv[])
 
 		memset(&regs1, 0, sizeof(regs1));
 		vcpu_regs_get(vm, VCPU_ID, &regs1);
-		switch (run->io.port) {
-		case GUEST_PORT_ABORT:
-			TEST_ASSERT(false, "%s at %s:%d", (const char *) regs1.rdi,
-				    __FILE__, regs1.rsi);
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_ABORT:
+			TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
+				    __FILE__, uc.args[1]);
 			/* NOT REACHED */
-		case GUEST_PORT_SYNC:
+		case UCALL_SYNC:
 			break;
-		case GUEST_PORT_DONE:
+		case UCALL_DONE:
 			goto done;
 		default:
-			TEST_ASSERT(false, "Unknown port 0x%x.", run->io.port);
+			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
 		}
 
-		/* PORT_SYNC is handled here.  */
-		TEST_ASSERT(!strcmp((const char *)regs1.rdi, "hello") &&
-			    regs1.rsi == stage, "Unexpected register values vmexit #%lx, got %lx",
-			    stage, (ulong) regs1.rsi);
+		/* UCALL_SYNC is handled here.  */
+		TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
+			    uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx",
+			    stage, (ulong)uc.args[1]);
 
 		state = vcpu_save_state(vm, VCPU_ID);
 		kvm_vm_release(vm);
diff --git a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
index 49bcc68b0235..8d487c78796a 100644
--- a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
+++ b/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
@@ -146,26 +146,25 @@ int main(int argc, char *argv[])
 
 	for (;;) {
 		volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
-		struct guest_args args;
+		struct ucall uc;
 
 		vcpu_run(vm, VCPU_ID);
-		guest_args_read(vm, VCPU_ID, &args);
 		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
 			    "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n",
 			    run->exit_reason,
 			    exit_reason_str(run->exit_reason));
 
-		switch (args.port) {
-		case GUEST_PORT_ABORT:
-			TEST_ASSERT(false, "%s", (const char *) args.arg0);
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_ABORT:
+			TEST_ASSERT(false, "%s", (const char *)uc.args[0]);
 			/* NOT REACHED */
-		case GUEST_PORT_SYNC:
-			report(args.arg1);
+		case UCALL_SYNC:
+			report(uc.args[1]);
 			break;
-		case GUEST_PORT_DONE:
+		case UCALL_DONE:
 			goto done;
 		default:
-			TEST_ASSERT(false, "Unknown port 0x%x.", args.port);
+			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
 		}
 	}
 
-- 
cgit 


From cc68765d418721ab854a03626c01e8eb82711922 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:26 +0200
Subject: kvm: selftests: move arch-specific files to arch-specific locations

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/.gitignore             |   13 +-
 tools/testing/selftests/kvm/Makefile               |   22 +-
 tools/testing/selftests/kvm/cr4_cpuid_sync_test.c  |  113 ---
 tools/testing/selftests/kvm/dirty_log_test.c       |  307 ------
 tools/testing/selftests/kvm/include/kvm_util.h     |    2 +-
 tools/testing/selftests/kvm/include/sparsebit.h    |    6 +-
 tools/testing/selftests/kvm/include/test_util.h    |    6 +-
 tools/testing/selftests/kvm/include/vmx.h          |  552 -----------
 tools/testing/selftests/kvm/include/x86.h          | 1047 --------------------
 .../selftests/kvm/include/x86_64/processor.h       | 1047 ++++++++++++++++++++
 tools/testing/selftests/kvm/include/x86_64/vmx.h   |  552 +++++++++++
 tools/testing/selftests/kvm/lib/assert.c           |    2 +-
 .../testing/selftests/kvm/lib/kvm_util_internal.h  |    8 +-
 tools/testing/selftests/kvm/lib/vmx.c              |  283 ------
 tools/testing/selftests/kvm/lib/x86.c              |  888 -----------------
 tools/testing/selftests/kvm/lib/x86_64/processor.c |  888 +++++++++++++++++
 tools/testing/selftests/kvm/lib/x86_64/vmx.c       |  283 ++++++
 tools/testing/selftests/kvm/platform_info_test.c   |  110 --
 tools/testing/selftests/kvm/set_sregs_test.c       |   54 -
 tools/testing/selftests/kvm/state_test.c           |  197 ----
 tools/testing/selftests/kvm/sync_regs_test.c       |  237 -----
 tools/testing/selftests/kvm/vmx_tsc_adjust_test.c  |  174 ----
 .../selftests/kvm/x86_64/cr4_cpuid_sync_test.c     |  113 +++
 .../testing/selftests/kvm/x86_64/dirty_log_test.c  |  307 ++++++
 .../selftests/kvm/x86_64/platform_info_test.c      |  110 ++
 .../testing/selftests/kvm/x86_64/set_sregs_test.c  |   54 +
 tools/testing/selftests/kvm/x86_64/state_test.c    |  197 ++++
 .../testing/selftests/kvm/x86_64/sync_regs_test.c  |  237 +++++
 .../selftests/kvm/x86_64/vmx_tsc_adjust_test.c     |  174 ++++
 29 files changed, 3992 insertions(+), 3991 deletions(-)
 delete mode 100644 tools/testing/selftests/kvm/cr4_cpuid_sync_test.c
 delete mode 100644 tools/testing/selftests/kvm/dirty_log_test.c
 delete mode 100644 tools/testing/selftests/kvm/include/vmx.h
 delete mode 100644 tools/testing/selftests/kvm/include/x86.h
 create mode 100644 tools/testing/selftests/kvm/include/x86_64/processor.h
 create mode 100644 tools/testing/selftests/kvm/include/x86_64/vmx.h
 delete mode 100644 tools/testing/selftests/kvm/lib/vmx.c
 delete mode 100644 tools/testing/selftests/kvm/lib/x86.c
 create mode 100644 tools/testing/selftests/kvm/lib/x86_64/processor.c
 create mode 100644 tools/testing/selftests/kvm/lib/x86_64/vmx.c
 delete mode 100644 tools/testing/selftests/kvm/platform_info_test.c
 delete mode 100644 tools/testing/selftests/kvm/set_sregs_test.c
 delete mode 100644 tools/testing/selftests/kvm/state_test.c
 delete mode 100644 tools/testing/selftests/kvm/sync_regs_test.c
 delete mode 100644 tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
 create mode 100644 tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
 create mode 100644 tools/testing/selftests/kvm/x86_64/dirty_log_test.c
 create mode 100644 tools/testing/selftests/kvm/x86_64/platform_info_test.c
 create mode 100644 tools/testing/selftests/kvm/x86_64/set_sregs_test.c
 create mode 100644 tools/testing/selftests/kvm/x86_64/state_test.c
 create mode 100644 tools/testing/selftests/kvm/x86_64/sync_regs_test.c
 create mode 100644 tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 5c34752e1cff..e0aa5411cf9b 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,6 +1,7 @@
-cr4_cpuid_sync_test
-platform_info_test
-set_sregs_test
-sync_regs_test
-vmx_tsc_adjust_test
-state_test
+/x86_64/cr4_cpuid_sync_test
+/x86_64/platform_info_test
+/x86_64/set_sregs_test
+/x86_64/sync_regs_test
+/x86_64/vmx_tsc_adjust_test
+/x86_64/state_test
+/x86_64/dirty_log_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 08426f036353..734a60da9776 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -1,26 +1,26 @@
 all:
 
-top_srcdir = ../../../../
+top_srcdir = ../../../..
 UNAME_M := $(shell uname -m)
 
 LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/ucall.c lib/sparsebit.c
-LIBKVM_x86_64 = lib/x86.c lib/vmx.c
+LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c
 
-TEST_GEN_PROGS_x86_64 = platform_info_test
-TEST_GEN_PROGS_x86_64 += set_sregs_test
-TEST_GEN_PROGS_x86_64 += sync_regs_test
-TEST_GEN_PROGS_x86_64 += vmx_tsc_adjust_test
-TEST_GEN_PROGS_x86_64 += cr4_cpuid_sync_test
-TEST_GEN_PROGS_x86_64 += state_test
-TEST_GEN_PROGS_x86_64 += dirty_log_test
+TEST_GEN_PROGS_x86_64 = x86_64/platform_info_test
+TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
+TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
+TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
+TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
+TEST_GEN_PROGS_x86_64 += x86_64/state_test
+TEST_GEN_PROGS_x86_64 += x86_64/dirty_log_test
 
 TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
 LIBKVM += $(LIBKVM_$(UNAME_M))
 
 INSTALL_HDR_PATH = $(top_srcdir)/usr
 LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
-LINUX_TOOL_INCLUDE = $(top_srcdir)tools/include
-CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -I..
+LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include
+CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I..
 LDFLAGS += -pthread
 
 # After inclusion, $(OUTPUT) is defined and
diff --git a/tools/testing/selftests/kvm/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/cr4_cpuid_sync_test.c
deleted file mode 100644
index fd4f419fe9ab..000000000000
--- a/tools/testing/selftests/kvm/cr4_cpuid_sync_test.c
+++ /dev/null
@@ -1,113 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * CR4 and CPUID sync test
- *
- * Copyright 2018, Red Hat, Inc. and/or its affiliates.
- *
- * Author:
- *   Wei Huang <wei@redhat.com>
- */
-
-#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 "x86.h"
-
-#define X86_FEATURE_XSAVE	(1<<26)
-#define X86_FEATURE_OSXSAVE	(1<<27)
-#define VCPU_ID			1
-
-static inline bool cr4_cpuid_is_sync(void)
-{
-	int func, subfunc;
-	uint32_t eax, ebx, ecx, edx;
-	uint64_t cr4;
-
-	func = 0x1;
-	subfunc = 0x0;
-	__asm__ __volatile__("cpuid"
-			     : "=a"(eax), "=b"(ebx), "=c"(ecx), "=d"(edx)
-			     : "a"(func), "c"(subfunc));
-
-	cr4 = get_cr4();
-
-	return (!!(ecx & X86_FEATURE_OSXSAVE)) == (!!(cr4 & X86_CR4_OSXSAVE));
-}
-
-static void guest_code(void)
-{
-	uint64_t cr4;
-
-	/* turn on CR4.OSXSAVE */
-	cr4 = get_cr4();
-	cr4 |= X86_CR4_OSXSAVE;
-	set_cr4(cr4);
-
-	/* verify CR4.OSXSAVE == CPUID.OSXSAVE */
-	GUEST_ASSERT(cr4_cpuid_is_sync());
-
-	/* notify hypervisor to change CR4 */
-	GUEST_SYNC(0);
-
-	/* check again */
-	GUEST_ASSERT(cr4_cpuid_is_sync());
-
-	GUEST_DONE();
-}
-
-int main(int argc, char *argv[])
-{
-	struct kvm_run *run;
-	struct kvm_vm *vm;
-	struct kvm_sregs sregs;
-	struct kvm_cpuid_entry2 *entry;
-	struct ucall uc;
-	int rc;
-
-	entry = kvm_get_supported_cpuid_entry(1);
-	if (!(entry->ecx & X86_FEATURE_XSAVE)) {
-		printf("XSAVE feature not supported, skipping test\n");
-		return 0;
-	}
-
-	/* Tell stdout not to buffer its content */
-	setbuf(stdout, NULL);
-
-	/* Create VM */
-	vm = vm_create_default(VCPU_ID, 0, guest_code);
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
-	run = vcpu_state(vm, VCPU_ID);
-
-	while (1) {
-		rc = _vcpu_run(vm, VCPU_ID);
-
-		if (run->exit_reason == KVM_EXIT_IO) {
-			switch (get_ucall(vm, VCPU_ID, &uc)) {
-			case UCALL_SYNC:
-				/* emulate hypervisor clearing CR4.OSXSAVE */
-				vcpu_sregs_get(vm, VCPU_ID, &sregs);
-				sregs.cr4 &= ~X86_CR4_OSXSAVE;
-				vcpu_sregs_set(vm, VCPU_ID, &sregs);
-				break;
-			case UCALL_ABORT:
-				TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
-				break;
-			case UCALL_DONE:
-				goto done;
-			default:
-				TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
-			}
-		}
-	}
-
-	kvm_vm_free(vm);
-
-done:
-	return 0;
-}
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
deleted file mode 100644
index 7cf3e4ae6046..000000000000
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ /dev/null
@@ -1,307 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * KVM dirty page logging test
- *
- * Copyright (C) 2018, Red Hat, Inc.
- */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <time.h>
-#include <pthread.h>
-#include <linux/bitmap.h>
-#include <linux/bitops.h>
-
-#include "test_util.h"
-#include "kvm_util.h"
-
-#define  DEBUG                 printf
-
-#define  VCPU_ID                        1
-/* The memory slot index to track dirty pages */
-#define  TEST_MEM_SLOT_INDEX            1
-/*
- * GPA offset of the testing memory slot. Must be bigger than the
- * default vm mem slot, which is DEFAULT_GUEST_PHY_PAGES.
- */
-#define  TEST_MEM_OFFSET                (1ULL << 30) /* 1G */
-/* Size of the testing memory slot */
-#define  TEST_MEM_PAGES                 (1ULL << 18) /* 1G for 4K pages */
-/* How many pages to dirty for each guest loop */
-#define  TEST_PAGES_PER_LOOP            1024
-/* How many host loops to run (one KVM_GET_DIRTY_LOG for each loop) */
-#define  TEST_HOST_LOOP_N               32
-/* Interval for each host loop (ms) */
-#define  TEST_HOST_LOOP_INTERVAL        10
-
-/*
- * Guest variables.  We use these variables to share data between host
- * and guest.  There are two copies of the variables, one in host memory
- * (which is unused) and one in guest memory.  When the host wants to
- * access these variables, it needs to call addr_gva2hva() to access the
- * guest copy.
- */
-uint64_t guest_random_array[TEST_PAGES_PER_LOOP];
-uint64_t guest_iteration;
-uint64_t guest_page_size;
-
-/*
- * Writes to the first byte of a random page within the testing memory
- * region continuously.
- */
-void guest_code(void)
-{
-	int i = 0;
-	uint64_t volatile *array = guest_random_array;
-	uint64_t volatile *guest_addr;
-
-	while (true) {
-		for (i = 0; i < TEST_PAGES_PER_LOOP; i++) {
-			/*
-			 * Write to the first 8 bytes of a random page
-			 * on the testing memory region.
-			 */
-			guest_addr = (uint64_t *)
-			    (TEST_MEM_OFFSET +
-			     (array[i] % TEST_MEM_PAGES) * guest_page_size);
-			*guest_addr = guest_iteration;
-		}
-		/* Tell the host that we need more random numbers */
-		GUEST_SYNC(1);
-	}
-}
-
-/*
- * Host variables.  These variables should only be used by the host
- * rather than the guest.
- */
-bool host_quit;
-
-/* Points to the test VM memory region on which we track dirty logs */
-void *host_test_mem;
-
-/* For statistics only */
-uint64_t host_dirty_count;
-uint64_t host_clear_count;
-uint64_t host_track_next_count;
-
-/*
- * We use this bitmap to track some pages that should have its dirty
- * bit set in the _next_ iteration.  For example, if we detected the
- * page value changed to current iteration but at the same time the
- * page bit is cleared in the latest bitmap, then the system must
- * report that write in the next get dirty log call.
- */
-unsigned long *host_bmap_track;
-
-void generate_random_array(uint64_t *guest_array, uint64_t size)
-{
-	uint64_t i;
-
-	for (i = 0; i < size; i++) {
-		guest_array[i] = random();
-	}
-}
-
-void *vcpu_worker(void *data)
-{
-	int ret;
-	uint64_t loops, *guest_array, pages_count = 0;
-	struct kvm_vm *vm = data;
-	struct kvm_run *run;
-	struct ucall uc;
-
-	run = vcpu_state(vm, VCPU_ID);
-
-	/* Retrieve the guest random array pointer and cache it */
-	guest_array = addr_gva2hva(vm, (vm_vaddr_t)guest_random_array);
-
-	DEBUG("VCPU starts\n");
-
-	generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
-
-	while (!READ_ONCE(host_quit)) {
-		/* Let the guest to dirty these random pages */
-		ret = _vcpu_run(vm, VCPU_ID);
-		if (run->exit_reason == KVM_EXIT_IO &&
-		    get_ucall(vm, VCPU_ID, &uc) == UCALL_SYNC) {
-			pages_count += TEST_PAGES_PER_LOOP;
-			generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
-		} else {
-			TEST_ASSERT(false,
-				    "Invalid guest sync status: "
-				    "exit_reason=%s\n",
-				    exit_reason_str(run->exit_reason));
-		}
-	}
-
-	DEBUG("VCPU exits, dirtied %"PRIu64" pages\n", pages_count);
-
-	return NULL;
-}
-
-void vm_dirty_log_verify(unsigned long *bmap, uint64_t iteration)
-{
-	uint64_t page;
-	uint64_t volatile *value_ptr;
-
-	for (page = 0; page < TEST_MEM_PAGES; page++) {
-		value_ptr = host_test_mem + page * getpagesize();
-
-		/* If this is a special page that we were tracking... */
-		if (test_and_clear_bit(page, host_bmap_track)) {
-			host_track_next_count++;
-			TEST_ASSERT(test_bit(page, bmap),
-				    "Page %"PRIu64" should have its dirty bit "
-				    "set in this iteration but it is missing",
-				    page);
-		}
-
-		if (test_bit(page, bmap)) {
-			host_dirty_count++;
-			/*
-			 * If the bit is set, the value written onto
-			 * the corresponding page should be either the
-			 * previous iteration number or the current one.
-			 */
-			TEST_ASSERT(*value_ptr == iteration ||
-				    *value_ptr == iteration - 1,
-				    "Set page %"PRIu64" value %"PRIu64
-				    " incorrect (iteration=%"PRIu64")",
-				    page, *value_ptr, iteration);
-		} else {
-			host_clear_count++;
-			/*
-			 * If cleared, the value written can be any
-			 * value smaller or equals to the iteration
-			 * number.  Note that the value can be exactly
-			 * (iteration-1) if that write can happen
-			 * like this:
-			 *
-			 * (1) increase loop count to "iteration-1"
-			 * (2) write to page P happens (with value
-			 *     "iteration-1")
-			 * (3) get dirty log for "iteration-1"; we'll
-			 *     see that page P bit is set (dirtied),
-			 *     and not set the bit in host_bmap_track
-			 * (4) increase loop count to "iteration"
-			 *     (which is current iteration)
-			 * (5) get dirty log for current iteration,
-			 *     we'll see that page P is cleared, with
-			 *     value "iteration-1".
-			 */
-			TEST_ASSERT(*value_ptr <= iteration,
-				    "Clear page %"PRIu64" value %"PRIu64
-				    " incorrect (iteration=%"PRIu64")",
-				    page, *value_ptr, iteration);
-			if (*value_ptr == iteration) {
-				/*
-				 * This page is _just_ modified; it
-				 * should report its dirtyness in the
-				 * next run
-				 */
-				set_bit(page, host_bmap_track);
-			}
-		}
-	}
-}
-
-void help(char *name)
-{
-	puts("");
-	printf("usage: %s [-i iterations] [-I interval] [-h]\n", name);
-	puts("");
-	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
-	       TEST_HOST_LOOP_N);
-	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
-	       TEST_HOST_LOOP_INTERVAL);
-	puts("");
-	exit(0);
-}
-
-int main(int argc, char *argv[])
-{
-	pthread_t vcpu_thread;
-	struct kvm_vm *vm;
-	uint64_t volatile *psize, *iteration;
-	unsigned long *bmap, iterations = TEST_HOST_LOOP_N,
-	    interval = TEST_HOST_LOOP_INTERVAL;
-	int opt;
-
-	while ((opt = getopt(argc, argv, "hi:I:")) != -1) {
-		switch (opt) {
-		case 'i':
-			iterations = strtol(optarg, NULL, 10);
-			break;
-		case 'I':
-			interval = strtol(optarg, NULL, 10);
-			break;
-		case 'h':
-		default:
-			help(argv[0]);
-			break;
-		}
-	}
-
-	TEST_ASSERT(iterations > 2, "Iteration must be bigger than zero\n");
-	TEST_ASSERT(interval > 0, "Interval must be bigger than zero");
-
-	DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
-	      iterations, interval);
-
-	srandom(time(0));
-
-	bmap = bitmap_alloc(TEST_MEM_PAGES);
-	host_bmap_track = bitmap_alloc(TEST_MEM_PAGES);
-
-	vm = vm_create_default(VCPU_ID, TEST_MEM_PAGES, guest_code);
-
-	/* Add an extra memory slot for testing dirty logging */
-	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
-				    TEST_MEM_OFFSET,
-				    TEST_MEM_SLOT_INDEX,
-				    TEST_MEM_PAGES,
-				    KVM_MEM_LOG_DIRTY_PAGES);
-	/* Cache the HVA pointer of the region */
-	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)TEST_MEM_OFFSET);
-
-	/* Do 1:1 mapping for the dirty track memory slot */
-	virt_map(vm, TEST_MEM_OFFSET, TEST_MEM_OFFSET,
-		 TEST_MEM_PAGES * getpagesize(), 0);
-
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
-
-	/* Tell the guest about the page size on the system */
-	psize = addr_gva2hva(vm, (vm_vaddr_t)&guest_page_size);
-	*psize = getpagesize();
-
-	/* Start the iterations */
-	iteration = addr_gva2hva(vm, (vm_vaddr_t)&guest_iteration);
-	*iteration = 1;
-
-	/* Start dirtying pages */
-	pthread_create(&vcpu_thread, NULL, vcpu_worker, vm);
-
-	while (*iteration < iterations) {
-		/* Give the vcpu thread some time to dirty some pages */
-		usleep(interval * 1000);
-		kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
-		vm_dirty_log_verify(bmap, *iteration);
-		(*iteration)++;
-	}
-
-	/* Tell the vcpu thread to quit */
-	host_quit = true;
-	pthread_join(vcpu_thread, NULL);
-
-	DEBUG("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), "
-	      "track_next (%"PRIu64")\n", host_dirty_count, host_clear_count,
-	      host_track_next_count);
-
-	free(bmap);
-	free(host_bmap_track);
-	kvm_vm_free(vm);
-
-	return 0;
-}
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 22667dd48a9c..7830c46f27d8 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -7,7 +7,7 @@
  *
  */
 #ifndef SELFTEST_KVM_UTIL_H
-#define SELFTEST_KVM_UTIL_H 1
+#define SELFTEST_KVM_UTIL_H
 
 #include "test_util.h"
 
diff --git a/tools/testing/selftests/kvm/include/sparsebit.h b/tools/testing/selftests/kvm/include/sparsebit.h
index 54cfeb6568d3..31e030915c1f 100644
--- a/tools/testing/selftests/kvm/include/sparsebit.h
+++ b/tools/testing/selftests/kvm/include/sparsebit.h
@@ -15,8 +15,8 @@
  * even in the case where most bits are set.
  */
 
-#ifndef _TEST_SPARSEBIT_H_
-#define _TEST_SPARSEBIT_H_
+#ifndef SELFTEST_KVM_SPARSEBIT_H
+#define SELFTEST_KVM_SPARSEBIT_H
 
 #include <stdbool.h>
 #include <stdint.h>
@@ -72,4 +72,4 @@ void sparsebit_validate_internal(struct sparsebit *sbit);
 }
 #endif
 
-#endif /* _TEST_SPARSEBIT_H_ */
+#endif /* SELFTEST_KVM_SPARSEBIT_H */
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index 73c3933436ec..c7dafe8bd02c 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -7,8 +7,8 @@
  *
  */
 
-#ifndef TEST_UTIL_H
-#define TEST_UTIL_H 1
+#ifndef SELFTEST_KVM_TEST_UTIL_H
+#define SELFTEST_KVM_TEST_UTIL_H
 
 #include <stdlib.h>
 #include <stdarg.h>
@@ -41,4 +41,4 @@ void test_assert(bool exp, const char *exp_str,
 		    #a, #b, #a, (unsigned long) __a, #b, (unsigned long) __b); \
 } while (0)
 
-#endif /* TEST_UTIL_H */
+#endif /* SELFTEST_KVM_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/vmx.h b/tools/testing/selftests/kvm/include/vmx.h
deleted file mode 100644
index b9ffe1024d3a..000000000000
--- a/tools/testing/selftests/kvm/include/vmx.h
+++ /dev/null
@@ -1,552 +0,0 @@
-/*
- * tools/testing/selftests/kvm/include/vmx.h
- *
- * Copyright (C) 2018, Google LLC.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- *
- */
-
-#ifndef SELFTEST_KVM_VMX_H
-#define SELFTEST_KVM_VMX_H
-
-#include <stdint.h>
-#include "x86.h"
-
-#define CPUID_VMX_BIT				5
-
-#define CPUID_VMX				(1 << 5)
-
-/*
- * Definitions of Primary Processor-Based VM-Execution Controls.
- */
-#define CPU_BASED_VIRTUAL_INTR_PENDING		0x00000004
-#define CPU_BASED_USE_TSC_OFFSETING		0x00000008
-#define CPU_BASED_HLT_EXITING			0x00000080
-#define CPU_BASED_INVLPG_EXITING		0x00000200
-#define CPU_BASED_MWAIT_EXITING			0x00000400
-#define CPU_BASED_RDPMC_EXITING			0x00000800
-#define CPU_BASED_RDTSC_EXITING			0x00001000
-#define CPU_BASED_CR3_LOAD_EXITING		0x00008000
-#define CPU_BASED_CR3_STORE_EXITING		0x00010000
-#define CPU_BASED_CR8_LOAD_EXITING		0x00080000
-#define CPU_BASED_CR8_STORE_EXITING		0x00100000
-#define CPU_BASED_TPR_SHADOW			0x00200000
-#define CPU_BASED_VIRTUAL_NMI_PENDING		0x00400000
-#define CPU_BASED_MOV_DR_EXITING		0x00800000
-#define CPU_BASED_UNCOND_IO_EXITING		0x01000000
-#define CPU_BASED_USE_IO_BITMAPS		0x02000000
-#define CPU_BASED_MONITOR_TRAP			0x08000000
-#define CPU_BASED_USE_MSR_BITMAPS		0x10000000
-#define CPU_BASED_MONITOR_EXITING		0x20000000
-#define CPU_BASED_PAUSE_EXITING			0x40000000
-#define CPU_BASED_ACTIVATE_SECONDARY_CONTROLS	0x80000000
-
-#define CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR	0x0401e172
-
-/*
- * Definitions of Secondary Processor-Based VM-Execution Controls.
- */
-#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
-#define SECONDARY_EXEC_ENABLE_EPT		0x00000002
-#define SECONDARY_EXEC_DESC			0x00000004
-#define SECONDARY_EXEC_RDTSCP			0x00000008
-#define SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE	0x00000010
-#define SECONDARY_EXEC_ENABLE_VPID		0x00000020
-#define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
-#define SECONDARY_EXEC_UNRESTRICTED_GUEST	0x00000080
-#define SECONDARY_EXEC_APIC_REGISTER_VIRT	0x00000100
-#define SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY	0x00000200
-#define SECONDARY_EXEC_PAUSE_LOOP_EXITING	0x00000400
-#define SECONDARY_EXEC_RDRAND_EXITING		0x00000800
-#define SECONDARY_EXEC_ENABLE_INVPCID		0x00001000
-#define SECONDARY_EXEC_ENABLE_VMFUNC		0x00002000
-#define SECONDARY_EXEC_SHADOW_VMCS		0x00004000
-#define SECONDARY_EXEC_RDSEED_EXITING		0x00010000
-#define SECONDARY_EXEC_ENABLE_PML		0x00020000
-#define SECONDARY_EPT_VE			0x00040000
-#define SECONDARY_ENABLE_XSAV_RESTORE		0x00100000
-#define SECONDARY_EXEC_TSC_SCALING		0x02000000
-
-#define PIN_BASED_EXT_INTR_MASK			0x00000001
-#define PIN_BASED_NMI_EXITING			0x00000008
-#define PIN_BASED_VIRTUAL_NMIS			0x00000020
-#define PIN_BASED_VMX_PREEMPTION_TIMER		0x00000040
-#define PIN_BASED_POSTED_INTR			0x00000080
-
-#define PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR	0x00000016
-
-#define VM_EXIT_SAVE_DEBUG_CONTROLS		0x00000004
-#define VM_EXIT_HOST_ADDR_SPACE_SIZE		0x00000200
-#define VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL	0x00001000
-#define VM_EXIT_ACK_INTR_ON_EXIT		0x00008000
-#define VM_EXIT_SAVE_IA32_PAT			0x00040000
-#define VM_EXIT_LOAD_IA32_PAT			0x00080000
-#define VM_EXIT_SAVE_IA32_EFER			0x00100000
-#define VM_EXIT_LOAD_IA32_EFER			0x00200000
-#define VM_EXIT_SAVE_VMX_PREEMPTION_TIMER	0x00400000
-
-#define VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR	0x00036dff
-
-#define VM_ENTRY_LOAD_DEBUG_CONTROLS		0x00000004
-#define VM_ENTRY_IA32E_MODE			0x00000200
-#define VM_ENTRY_SMM				0x00000400
-#define VM_ENTRY_DEACT_DUAL_MONITOR		0x00000800
-#define VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL	0x00002000
-#define VM_ENTRY_LOAD_IA32_PAT			0x00004000
-#define VM_ENTRY_LOAD_IA32_EFER			0x00008000
-
-#define VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR	0x000011ff
-
-#define VMX_MISC_PREEMPTION_TIMER_RATE_MASK	0x0000001f
-#define VMX_MISC_SAVE_EFER_LMA			0x00000020
-
-#define EXIT_REASON_FAILED_VMENTRY	0x80000000
-#define EXIT_REASON_EXCEPTION_NMI	0
-#define EXIT_REASON_EXTERNAL_INTERRUPT	1
-#define EXIT_REASON_TRIPLE_FAULT	2
-#define EXIT_REASON_PENDING_INTERRUPT	7
-#define EXIT_REASON_NMI_WINDOW		8
-#define EXIT_REASON_TASK_SWITCH		9
-#define EXIT_REASON_CPUID		10
-#define EXIT_REASON_HLT			12
-#define EXIT_REASON_INVD		13
-#define EXIT_REASON_INVLPG		14
-#define EXIT_REASON_RDPMC		15
-#define EXIT_REASON_RDTSC		16
-#define EXIT_REASON_VMCALL		18
-#define EXIT_REASON_VMCLEAR		19
-#define EXIT_REASON_VMLAUNCH		20
-#define EXIT_REASON_VMPTRLD		21
-#define EXIT_REASON_VMPTRST		22
-#define EXIT_REASON_VMREAD		23
-#define EXIT_REASON_VMRESUME		24
-#define EXIT_REASON_VMWRITE		25
-#define EXIT_REASON_VMOFF		26
-#define EXIT_REASON_VMON		27
-#define EXIT_REASON_CR_ACCESS		28
-#define EXIT_REASON_DR_ACCESS		29
-#define EXIT_REASON_IO_INSTRUCTION	30
-#define EXIT_REASON_MSR_READ		31
-#define EXIT_REASON_MSR_WRITE		32
-#define EXIT_REASON_INVALID_STATE	33
-#define EXIT_REASON_MWAIT_INSTRUCTION	36
-#define EXIT_REASON_MONITOR_INSTRUCTION 39
-#define EXIT_REASON_PAUSE_INSTRUCTION	40
-#define EXIT_REASON_MCE_DURING_VMENTRY	41
-#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
-#define EXIT_REASON_APIC_ACCESS		44
-#define EXIT_REASON_EOI_INDUCED		45
-#define EXIT_REASON_EPT_VIOLATION	48
-#define EXIT_REASON_EPT_MISCONFIG	49
-#define EXIT_REASON_INVEPT		50
-#define EXIT_REASON_RDTSCP		51
-#define EXIT_REASON_PREEMPTION_TIMER	52
-#define EXIT_REASON_INVVPID		53
-#define EXIT_REASON_WBINVD		54
-#define EXIT_REASON_XSETBV		55
-#define EXIT_REASON_APIC_WRITE		56
-#define EXIT_REASON_INVPCID		58
-#define EXIT_REASON_PML_FULL		62
-#define EXIT_REASON_XSAVES		63
-#define EXIT_REASON_XRSTORS		64
-#define LAST_EXIT_REASON		64
-
-enum vmcs_field {
-	VIRTUAL_PROCESSOR_ID		= 0x00000000,
-	POSTED_INTR_NV			= 0x00000002,
-	GUEST_ES_SELECTOR		= 0x00000800,
-	GUEST_CS_SELECTOR		= 0x00000802,
-	GUEST_SS_SELECTOR		= 0x00000804,
-	GUEST_DS_SELECTOR		= 0x00000806,
-	GUEST_FS_SELECTOR		= 0x00000808,
-	GUEST_GS_SELECTOR		= 0x0000080a,
-	GUEST_LDTR_SELECTOR		= 0x0000080c,
-	GUEST_TR_SELECTOR		= 0x0000080e,
-	GUEST_INTR_STATUS		= 0x00000810,
-	GUEST_PML_INDEX			= 0x00000812,
-	HOST_ES_SELECTOR		= 0x00000c00,
-	HOST_CS_SELECTOR		= 0x00000c02,
-	HOST_SS_SELECTOR		= 0x00000c04,
-	HOST_DS_SELECTOR		= 0x00000c06,
-	HOST_FS_SELECTOR		= 0x00000c08,
-	HOST_GS_SELECTOR		= 0x00000c0a,
-	HOST_TR_SELECTOR		= 0x00000c0c,
-	IO_BITMAP_A			= 0x00002000,
-	IO_BITMAP_A_HIGH		= 0x00002001,
-	IO_BITMAP_B			= 0x00002002,
-	IO_BITMAP_B_HIGH		= 0x00002003,
-	MSR_BITMAP			= 0x00002004,
-	MSR_BITMAP_HIGH			= 0x00002005,
-	VM_EXIT_MSR_STORE_ADDR		= 0x00002006,
-	VM_EXIT_MSR_STORE_ADDR_HIGH	= 0x00002007,
-	VM_EXIT_MSR_LOAD_ADDR		= 0x00002008,
-	VM_EXIT_MSR_LOAD_ADDR_HIGH	= 0x00002009,
-	VM_ENTRY_MSR_LOAD_ADDR		= 0x0000200a,
-	VM_ENTRY_MSR_LOAD_ADDR_HIGH	= 0x0000200b,
-	PML_ADDRESS			= 0x0000200e,
-	PML_ADDRESS_HIGH		= 0x0000200f,
-	TSC_OFFSET			= 0x00002010,
-	TSC_OFFSET_HIGH			= 0x00002011,
-	VIRTUAL_APIC_PAGE_ADDR		= 0x00002012,
-	VIRTUAL_APIC_PAGE_ADDR_HIGH	= 0x00002013,
-	APIC_ACCESS_ADDR		= 0x00002014,
-	APIC_ACCESS_ADDR_HIGH		= 0x00002015,
-	POSTED_INTR_DESC_ADDR		= 0x00002016,
-	POSTED_INTR_DESC_ADDR_HIGH	= 0x00002017,
-	EPT_POINTER			= 0x0000201a,
-	EPT_POINTER_HIGH		= 0x0000201b,
-	EOI_EXIT_BITMAP0		= 0x0000201c,
-	EOI_EXIT_BITMAP0_HIGH		= 0x0000201d,
-	EOI_EXIT_BITMAP1		= 0x0000201e,
-	EOI_EXIT_BITMAP1_HIGH		= 0x0000201f,
-	EOI_EXIT_BITMAP2		= 0x00002020,
-	EOI_EXIT_BITMAP2_HIGH		= 0x00002021,
-	EOI_EXIT_BITMAP3		= 0x00002022,
-	EOI_EXIT_BITMAP3_HIGH		= 0x00002023,
-	VMREAD_BITMAP			= 0x00002026,
-	VMREAD_BITMAP_HIGH		= 0x00002027,
-	VMWRITE_BITMAP			= 0x00002028,
-	VMWRITE_BITMAP_HIGH		= 0x00002029,
-	XSS_EXIT_BITMAP			= 0x0000202C,
-	XSS_EXIT_BITMAP_HIGH		= 0x0000202D,
-	TSC_MULTIPLIER			= 0x00002032,
-	TSC_MULTIPLIER_HIGH		= 0x00002033,
-	GUEST_PHYSICAL_ADDRESS		= 0x00002400,
-	GUEST_PHYSICAL_ADDRESS_HIGH	= 0x00002401,
-	VMCS_LINK_POINTER		= 0x00002800,
-	VMCS_LINK_POINTER_HIGH		= 0x00002801,
-	GUEST_IA32_DEBUGCTL		= 0x00002802,
-	GUEST_IA32_DEBUGCTL_HIGH	= 0x00002803,
-	GUEST_IA32_PAT			= 0x00002804,
-	GUEST_IA32_PAT_HIGH		= 0x00002805,
-	GUEST_IA32_EFER			= 0x00002806,
-	GUEST_IA32_EFER_HIGH		= 0x00002807,
-	GUEST_IA32_PERF_GLOBAL_CTRL	= 0x00002808,
-	GUEST_IA32_PERF_GLOBAL_CTRL_HIGH= 0x00002809,
-	GUEST_PDPTR0			= 0x0000280a,
-	GUEST_PDPTR0_HIGH		= 0x0000280b,
-	GUEST_PDPTR1			= 0x0000280c,
-	GUEST_PDPTR1_HIGH		= 0x0000280d,
-	GUEST_PDPTR2			= 0x0000280e,
-	GUEST_PDPTR2_HIGH		= 0x0000280f,
-	GUEST_PDPTR3			= 0x00002810,
-	GUEST_PDPTR3_HIGH		= 0x00002811,
-	GUEST_BNDCFGS			= 0x00002812,
-	GUEST_BNDCFGS_HIGH		= 0x00002813,
-	HOST_IA32_PAT			= 0x00002c00,
-	HOST_IA32_PAT_HIGH		= 0x00002c01,
-	HOST_IA32_EFER			= 0x00002c02,
-	HOST_IA32_EFER_HIGH		= 0x00002c03,
-	HOST_IA32_PERF_GLOBAL_CTRL	= 0x00002c04,
-	HOST_IA32_PERF_GLOBAL_CTRL_HIGH	= 0x00002c05,
-	PIN_BASED_VM_EXEC_CONTROL	= 0x00004000,
-	CPU_BASED_VM_EXEC_CONTROL	= 0x00004002,
-	EXCEPTION_BITMAP		= 0x00004004,
-	PAGE_FAULT_ERROR_CODE_MASK	= 0x00004006,
-	PAGE_FAULT_ERROR_CODE_MATCH	= 0x00004008,
-	CR3_TARGET_COUNT		= 0x0000400a,
-	VM_EXIT_CONTROLS		= 0x0000400c,
-	VM_EXIT_MSR_STORE_COUNT		= 0x0000400e,
-	VM_EXIT_MSR_LOAD_COUNT		= 0x00004010,
-	VM_ENTRY_CONTROLS		= 0x00004012,
-	VM_ENTRY_MSR_LOAD_COUNT		= 0x00004014,
-	VM_ENTRY_INTR_INFO_FIELD	= 0x00004016,
-	VM_ENTRY_EXCEPTION_ERROR_CODE	= 0x00004018,
-	VM_ENTRY_INSTRUCTION_LEN	= 0x0000401a,
-	TPR_THRESHOLD			= 0x0000401c,
-	SECONDARY_VM_EXEC_CONTROL	= 0x0000401e,
-	PLE_GAP				= 0x00004020,
-	PLE_WINDOW			= 0x00004022,
-	VM_INSTRUCTION_ERROR		= 0x00004400,
-	VM_EXIT_REASON			= 0x00004402,
-	VM_EXIT_INTR_INFO		= 0x00004404,
-	VM_EXIT_INTR_ERROR_CODE		= 0x00004406,
-	IDT_VECTORING_INFO_FIELD	= 0x00004408,
-	IDT_VECTORING_ERROR_CODE	= 0x0000440a,
-	VM_EXIT_INSTRUCTION_LEN		= 0x0000440c,
-	VMX_INSTRUCTION_INFO		= 0x0000440e,
-	GUEST_ES_LIMIT			= 0x00004800,
-	GUEST_CS_LIMIT			= 0x00004802,
-	GUEST_SS_LIMIT			= 0x00004804,
-	GUEST_DS_LIMIT			= 0x00004806,
-	GUEST_FS_LIMIT			= 0x00004808,
-	GUEST_GS_LIMIT			= 0x0000480a,
-	GUEST_LDTR_LIMIT		= 0x0000480c,
-	GUEST_TR_LIMIT			= 0x0000480e,
-	GUEST_GDTR_LIMIT		= 0x00004810,
-	GUEST_IDTR_LIMIT		= 0x00004812,
-	GUEST_ES_AR_BYTES		= 0x00004814,
-	GUEST_CS_AR_BYTES		= 0x00004816,
-	GUEST_SS_AR_BYTES		= 0x00004818,
-	GUEST_DS_AR_BYTES		= 0x0000481a,
-	GUEST_FS_AR_BYTES		= 0x0000481c,
-	GUEST_GS_AR_BYTES		= 0x0000481e,
-	GUEST_LDTR_AR_BYTES		= 0x00004820,
-	GUEST_TR_AR_BYTES		= 0x00004822,
-	GUEST_INTERRUPTIBILITY_INFO	= 0x00004824,
-	GUEST_ACTIVITY_STATE		= 0X00004826,
-	GUEST_SYSENTER_CS		= 0x0000482A,
-	VMX_PREEMPTION_TIMER_VALUE	= 0x0000482E,
-	HOST_IA32_SYSENTER_CS		= 0x00004c00,
-	CR0_GUEST_HOST_MASK		= 0x00006000,
-	CR4_GUEST_HOST_MASK		= 0x00006002,
-	CR0_READ_SHADOW			= 0x00006004,
-	CR4_READ_SHADOW			= 0x00006006,
-	CR3_TARGET_VALUE0		= 0x00006008,
-	CR3_TARGET_VALUE1		= 0x0000600a,
-	CR3_TARGET_VALUE2		= 0x0000600c,
-	CR3_TARGET_VALUE3		= 0x0000600e,
-	EXIT_QUALIFICATION		= 0x00006400,
-	GUEST_LINEAR_ADDRESS		= 0x0000640a,
-	GUEST_CR0			= 0x00006800,
-	GUEST_CR3			= 0x00006802,
-	GUEST_CR4			= 0x00006804,
-	GUEST_ES_BASE			= 0x00006806,
-	GUEST_CS_BASE			= 0x00006808,
-	GUEST_SS_BASE			= 0x0000680a,
-	GUEST_DS_BASE			= 0x0000680c,
-	GUEST_FS_BASE			= 0x0000680e,
-	GUEST_GS_BASE			= 0x00006810,
-	GUEST_LDTR_BASE			= 0x00006812,
-	GUEST_TR_BASE			= 0x00006814,
-	GUEST_GDTR_BASE			= 0x00006816,
-	GUEST_IDTR_BASE			= 0x00006818,
-	GUEST_DR7			= 0x0000681a,
-	GUEST_RSP			= 0x0000681c,
-	GUEST_RIP			= 0x0000681e,
-	GUEST_RFLAGS			= 0x00006820,
-	GUEST_PENDING_DBG_EXCEPTIONS	= 0x00006822,
-	GUEST_SYSENTER_ESP		= 0x00006824,
-	GUEST_SYSENTER_EIP		= 0x00006826,
-	HOST_CR0			= 0x00006c00,
-	HOST_CR3			= 0x00006c02,
-	HOST_CR4			= 0x00006c04,
-	HOST_FS_BASE			= 0x00006c06,
-	HOST_GS_BASE			= 0x00006c08,
-	HOST_TR_BASE			= 0x00006c0a,
-	HOST_GDTR_BASE			= 0x00006c0c,
-	HOST_IDTR_BASE			= 0x00006c0e,
-	HOST_IA32_SYSENTER_ESP		= 0x00006c10,
-	HOST_IA32_SYSENTER_EIP		= 0x00006c12,
-	HOST_RSP			= 0x00006c14,
-	HOST_RIP			= 0x00006c16,
-};
-
-struct vmx_msr_entry {
-	uint32_t index;
-	uint32_t reserved;
-	uint64_t value;
-} __attribute__ ((aligned(16)));
-
-static inline int vmxon(uint64_t phys)
-{
-	uint8_t ret;
-
-	__asm__ __volatile__ ("vmxon %[pa]; setna %[ret]"
-		: [ret]"=rm"(ret)
-		: [pa]"m"(phys)
-		: "cc", "memory");
-
-	return ret;
-}
-
-static inline void vmxoff(void)
-{
-	__asm__ __volatile__("vmxoff");
-}
-
-static inline int vmclear(uint64_t vmcs_pa)
-{
-	uint8_t ret;
-
-	__asm__ __volatile__ ("vmclear %[pa]; setna %[ret]"
-		: [ret]"=rm"(ret)
-		: [pa]"m"(vmcs_pa)
-		: "cc", "memory");
-
-	return ret;
-}
-
-static inline int vmptrld(uint64_t vmcs_pa)
-{
-	uint8_t ret;
-
-	__asm__ __volatile__ ("vmptrld %[pa]; setna %[ret]"
-		: [ret]"=rm"(ret)
-		: [pa]"m"(vmcs_pa)
-		: "cc", "memory");
-
-	return ret;
-}
-
-static inline int vmptrst(uint64_t *value)
-{
-	uint64_t tmp;
-	uint8_t ret;
-
-	__asm__ __volatile__("vmptrst %[value]; setna %[ret]"
-		: [value]"=m"(tmp), [ret]"=rm"(ret)
-		: : "cc", "memory");
-
-	*value = tmp;
-	return ret;
-}
-
-/*
- * A wrapper around vmptrst that ignores errors and returns zero if the
- * vmptrst instruction fails.
- */
-static inline uint64_t vmptrstz(void)
-{
-	uint64_t value = 0;
-	vmptrst(&value);
-	return value;
-}
-
-/*
- * No guest state (e.g. GPRs) is established by this vmlaunch.
- */
-static inline int vmlaunch(void)
-{
-	int ret;
-
-	__asm__ __volatile__("push %%rbp;"
-			     "push %%rcx;"
-			     "push %%rdx;"
-			     "push %%rsi;"
-			     "push %%rdi;"
-			     "push $0;"
-			     "vmwrite %%rsp, %[host_rsp];"
-			     "lea 1f(%%rip), %%rax;"
-			     "vmwrite %%rax, %[host_rip];"
-			     "vmlaunch;"
-			     "incq (%%rsp);"
-			     "1: pop %%rax;"
-			     "pop %%rdi;"
-			     "pop %%rsi;"
-			     "pop %%rdx;"
-			     "pop %%rcx;"
-			     "pop %%rbp;"
-			     : [ret]"=&a"(ret)
-			     : [host_rsp]"r"((uint64_t)HOST_RSP),
-			       [host_rip]"r"((uint64_t)HOST_RIP)
-			     : "memory", "cc", "rbx", "r8", "r9", "r10",
-			       "r11", "r12", "r13", "r14", "r15");
-	return ret;
-}
-
-/*
- * No guest state (e.g. GPRs) is established by this vmresume.
- */
-static inline int vmresume(void)
-{
-	int ret;
-
-	__asm__ __volatile__("push %%rbp;"
-			     "push %%rcx;"
-			     "push %%rdx;"
-			     "push %%rsi;"
-			     "push %%rdi;"
-			     "push $0;"
-			     "vmwrite %%rsp, %[host_rsp];"
-			     "lea 1f(%%rip), %%rax;"
-			     "vmwrite %%rax, %[host_rip];"
-			     "vmresume;"
-			     "incq (%%rsp);"
-			     "1: pop %%rax;"
-			     "pop %%rdi;"
-			     "pop %%rsi;"
-			     "pop %%rdx;"
-			     "pop %%rcx;"
-			     "pop %%rbp;"
-			     : [ret]"=&a"(ret)
-			     : [host_rsp]"r"((uint64_t)HOST_RSP),
-			       [host_rip]"r"((uint64_t)HOST_RIP)
-			     : "memory", "cc", "rbx", "r8", "r9", "r10",
-			       "r11", "r12", "r13", "r14", "r15");
-	return ret;
-}
-
-static inline void vmcall(void)
-{
-	/* Currently, L1 destroys our GPRs during vmexits.  */
-	__asm__ __volatile__("push %%rbp; vmcall; pop %%rbp" : : :
-			     "rax", "rbx", "rcx", "rdx",
-			     "rsi", "rdi", "r8", "r9", "r10", "r11", "r12",
-			     "r13", "r14", "r15");
-}
-
-static inline int vmread(uint64_t encoding, uint64_t *value)
-{
-	uint64_t tmp;
-	uint8_t ret;
-
-	__asm__ __volatile__("vmread %[encoding], %[value]; setna %[ret]"
-		: [value]"=rm"(tmp), [ret]"=rm"(ret)
-		: [encoding]"r"(encoding)
-		: "cc", "memory");
-
-	*value = tmp;
-	return ret;
-}
-
-/*
- * A wrapper around vmread that ignores errors and returns zero if the
- * vmread instruction fails.
- */
-static inline uint64_t vmreadz(uint64_t encoding)
-{
-	uint64_t value = 0;
-	vmread(encoding, &value);
-	return value;
-}
-
-static inline int vmwrite(uint64_t encoding, uint64_t value)
-{
-	uint8_t ret;
-
-	__asm__ __volatile__ ("vmwrite %[value], %[encoding]; setna %[ret]"
-		: [ret]"=rm"(ret)
-		: [value]"rm"(value), [encoding]"r"(encoding)
-		: "cc", "memory");
-
-	return ret;
-}
-
-static inline uint32_t vmcs_revision(void)
-{
-	return rdmsr(MSR_IA32_VMX_BASIC);
-}
-
-struct vmx_pages {
-	void *vmxon_hva;
-	uint64_t vmxon_gpa;
-	void *vmxon;
-
-	void *vmcs_hva;
-	uint64_t vmcs_gpa;
-	void *vmcs;
-
-	void *msr_hva;
-	uint64_t msr_gpa;
-	void *msr;
-
-	void *shadow_vmcs_hva;
-	uint64_t shadow_vmcs_gpa;
-	void *shadow_vmcs;
-
-	void *vmread_hva;
-	uint64_t vmread_gpa;
-	void *vmread;
-
-	void *vmwrite_hva;
-	uint64_t vmwrite_gpa;
-	void *vmwrite;
-};
-
-struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva);
-bool prepare_for_vmx_operation(struct vmx_pages *vmx);
-void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp);
-
-#endif /* !SELFTEST_KVM_VMX_H */
diff --git a/tools/testing/selftests/kvm/include/x86.h b/tools/testing/selftests/kvm/include/x86.h
deleted file mode 100644
index 42c3596815b8..000000000000
--- a/tools/testing/selftests/kvm/include/x86.h
+++ /dev/null
@@ -1,1047 +0,0 @@
-/*
- * tools/testing/selftests/kvm/include/x86.h
- *
- * Copyright (C) 2018, Google LLC.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- *
- */
-
-#ifndef SELFTEST_KVM_X86_H
-#define SELFTEST_KVM_X86_H
-
-#include <assert.h>
-#include <stdint.h>
-
-#define X86_EFLAGS_FIXED	 (1u << 1)
-
-#define X86_CR4_VME		(1ul << 0)
-#define X86_CR4_PVI		(1ul << 1)
-#define X86_CR4_TSD		(1ul << 2)
-#define X86_CR4_DE		(1ul << 3)
-#define X86_CR4_PSE		(1ul << 4)
-#define X86_CR4_PAE		(1ul << 5)
-#define X86_CR4_MCE		(1ul << 6)
-#define X86_CR4_PGE		(1ul << 7)
-#define X86_CR4_PCE		(1ul << 8)
-#define X86_CR4_OSFXSR		(1ul << 9)
-#define X86_CR4_OSXMMEXCPT	(1ul << 10)
-#define X86_CR4_UMIP		(1ul << 11)
-#define X86_CR4_VMXE		(1ul << 13)
-#define X86_CR4_SMXE		(1ul << 14)
-#define X86_CR4_FSGSBASE	(1ul << 16)
-#define X86_CR4_PCIDE		(1ul << 17)
-#define X86_CR4_OSXSAVE		(1ul << 18)
-#define X86_CR4_SMEP		(1ul << 20)
-#define X86_CR4_SMAP		(1ul << 21)
-#define X86_CR4_PKE		(1ul << 22)
-
-/* The enum values match the intruction encoding of each register */
-enum x86_register {
-	RAX = 0,
-	RCX,
-	RDX,
-	RBX,
-	RSP,
-	RBP,
-	RSI,
-	RDI,
-	R8,
-	R9,
-	R10,
-	R11,
-	R12,
-	R13,
-	R14,
-	R15,
-};
-
-struct desc64 {
-	uint16_t limit0;
-	uint16_t base0;
-	unsigned base1:8, s:1, type:4, dpl:2, p:1;
-	unsigned limit1:4, avl:1, l:1, db:1, g:1, base2:8;
-	uint32_t base3;
-	uint32_t zero1;
-} __attribute__((packed));
-
-struct desc_ptr {
-	uint16_t size;
-	uint64_t address;
-} __attribute__((packed));
-
-static inline uint64_t get_desc64_base(const struct desc64 *desc)
-{
-	return ((uint64_t)desc->base3 << 32) |
-		(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24));
-}
-
-static inline uint64_t rdtsc(void)
-{
-	uint32_t eax, edx;
-
-	/*
-	 * The lfence is to wait (on Intel CPUs) until all previous
-	 * instructions have been executed.
-	 */
-	__asm__ __volatile__("lfence; rdtsc" : "=a"(eax), "=d"(edx));
-	return ((uint64_t)edx) << 32 | eax;
-}
-
-static inline uint64_t rdtscp(uint32_t *aux)
-{
-	uint32_t eax, edx;
-
-	__asm__ __volatile__("rdtscp" : "=a"(eax), "=d"(edx), "=c"(*aux));
-	return ((uint64_t)edx) << 32 | eax;
-}
-
-static inline uint64_t rdmsr(uint32_t msr)
-{
-	uint32_t a, d;
-
-	__asm__ __volatile__("rdmsr" : "=a"(a), "=d"(d) : "c"(msr) : "memory");
-
-	return a | ((uint64_t) d << 32);
-}
-
-static inline void wrmsr(uint32_t msr, uint64_t value)
-{
-	uint32_t a = value;
-	uint32_t d = value >> 32;
-
-	__asm__ __volatile__("wrmsr" :: "a"(a), "d"(d), "c"(msr) : "memory");
-}
-
-
-static inline uint16_t inw(uint16_t port)
-{
-	uint16_t tmp;
-
-	__asm__ __volatile__("in %%dx, %%ax"
-		: /* output */ "=a" (tmp)
-		: /* input */ "d" (port));
-
-	return tmp;
-}
-
-static inline uint16_t get_es(void)
-{
-	uint16_t es;
-
-	__asm__ __volatile__("mov %%es, %[es]"
-			     : /* output */ [es]"=rm"(es));
-	return es;
-}
-
-static inline uint16_t get_cs(void)
-{
-	uint16_t cs;
-
-	__asm__ __volatile__("mov %%cs, %[cs]"
-			     : /* output */ [cs]"=rm"(cs));
-	return cs;
-}
-
-static inline uint16_t get_ss(void)
-{
-	uint16_t ss;
-
-	__asm__ __volatile__("mov %%ss, %[ss]"
-			     : /* output */ [ss]"=rm"(ss));
-	return ss;
-}
-
-static inline uint16_t get_ds(void)
-{
-	uint16_t ds;
-
-	__asm__ __volatile__("mov %%ds, %[ds]"
-			     : /* output */ [ds]"=rm"(ds));
-	return ds;
-}
-
-static inline uint16_t get_fs(void)
-{
-	uint16_t fs;
-
-	__asm__ __volatile__("mov %%fs, %[fs]"
-			     : /* output */ [fs]"=rm"(fs));
-	return fs;
-}
-
-static inline uint16_t get_gs(void)
-{
-	uint16_t gs;
-
-	__asm__ __volatile__("mov %%gs, %[gs]"
-			     : /* output */ [gs]"=rm"(gs));
-	return gs;
-}
-
-static inline uint16_t get_tr(void)
-{
-	uint16_t tr;
-
-	__asm__ __volatile__("str %[tr]"
-			     : /* output */ [tr]"=rm"(tr));
-	return tr;
-}
-
-static inline uint64_t get_cr0(void)
-{
-	uint64_t cr0;
-
-	__asm__ __volatile__("mov %%cr0, %[cr0]"
-			     : /* output */ [cr0]"=r"(cr0));
-	return cr0;
-}
-
-static inline uint64_t get_cr3(void)
-{
-	uint64_t cr3;
-
-	__asm__ __volatile__("mov %%cr3, %[cr3]"
-			     : /* output */ [cr3]"=r"(cr3));
-	return cr3;
-}
-
-static inline uint64_t get_cr4(void)
-{
-	uint64_t cr4;
-
-	__asm__ __volatile__("mov %%cr4, %[cr4]"
-			     : /* output */ [cr4]"=r"(cr4));
-	return cr4;
-}
-
-static inline void set_cr4(uint64_t val)
-{
-	__asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory");
-}
-
-static inline uint64_t get_gdt_base(void)
-{
-	struct desc_ptr gdt;
-	__asm__ __volatile__("sgdt %[gdt]"
-			     : /* output */ [gdt]"=m"(gdt));
-	return gdt.address;
-}
-
-static inline uint64_t get_idt_base(void)
-{
-	struct desc_ptr idt;
-	__asm__ __volatile__("sidt %[idt]"
-			     : /* output */ [idt]"=m"(idt));
-	return idt.address;
-}
-
-#define SET_XMM(__var, __xmm) \
-	asm volatile("movq %0, %%"#__xmm : : "r"(__var) : #__xmm)
-
-static inline void set_xmm(int n, unsigned long val)
-{
-	switch (n) {
-	case 0:
-		SET_XMM(val, xmm0);
-		break;
-	case 1:
-		SET_XMM(val, xmm1);
-		break;
-	case 2:
-		SET_XMM(val, xmm2);
-		break;
-	case 3:
-		SET_XMM(val, xmm3);
-		break;
-	case 4:
-		SET_XMM(val, xmm4);
-		break;
-	case 5:
-		SET_XMM(val, xmm5);
-		break;
-	case 6:
-		SET_XMM(val, xmm6);
-		break;
-	case 7:
-		SET_XMM(val, xmm7);
-		break;
-	}
-}
-
-typedef unsigned long v1di __attribute__ ((vector_size (8)));
-static inline unsigned long get_xmm(int n)
-{
-	assert(n >= 0 && n <= 7);
-
-	register v1di xmm0 __asm__("%xmm0");
-	register v1di xmm1 __asm__("%xmm1");
-	register v1di xmm2 __asm__("%xmm2");
-	register v1di xmm3 __asm__("%xmm3");
-	register v1di xmm4 __asm__("%xmm4");
-	register v1di xmm5 __asm__("%xmm5");
-	register v1di xmm6 __asm__("%xmm6");
-	register v1di xmm7 __asm__("%xmm7");
-	switch (n) {
-	case 0:
-		return (unsigned long)xmm0;
-	case 1:
-		return (unsigned long)xmm1;
-	case 2:
-		return (unsigned long)xmm2;
-	case 3:
-		return (unsigned long)xmm3;
-	case 4:
-		return (unsigned long)xmm4;
-	case 5:
-		return (unsigned long)xmm5;
-	case 6:
-		return (unsigned long)xmm6;
-	case 7:
-		return (unsigned long)xmm7;
-	}
-	return 0;
-}
-
-struct kvm_x86_state;
-struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid);
-void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *state);
-
-/*
- * Basic CPU control in CR0
- */
-#define X86_CR0_PE          (1UL<<0) /* Protection Enable */
-#define X86_CR0_MP          (1UL<<1) /* Monitor Coprocessor */
-#define X86_CR0_EM          (1UL<<2) /* Emulation */
-#define X86_CR0_TS          (1UL<<3) /* Task Switched */
-#define X86_CR0_ET          (1UL<<4) /* Extension Type */
-#define X86_CR0_NE          (1UL<<5) /* Numeric Error */
-#define X86_CR0_WP          (1UL<<16) /* Write Protect */
-#define X86_CR0_AM          (1UL<<18) /* Alignment Mask */
-#define X86_CR0_NW          (1UL<<29) /* Not Write-through */
-#define X86_CR0_CD          (1UL<<30) /* Cache Disable */
-#define X86_CR0_PG          (1UL<<31) /* Paging */
-
-/*
- * CPU model specific register (MSR) numbers.
- */
-
-/* x86-64 specific MSRs */
-#define MSR_EFER		0xc0000080 /* extended feature register */
-#define MSR_STAR		0xc0000081 /* legacy mode SYSCALL target */
-#define MSR_LSTAR		0xc0000082 /* long mode SYSCALL target */
-#define MSR_CSTAR		0xc0000083 /* compat mode SYSCALL target */
-#define MSR_SYSCALL_MASK	0xc0000084 /* EFLAGS mask for syscall */
-#define MSR_FS_BASE		0xc0000100 /* 64bit FS base */
-#define MSR_GS_BASE		0xc0000101 /* 64bit GS base */
-#define MSR_KERNEL_GS_BASE	0xc0000102 /* SwapGS GS shadow */
-#define MSR_TSC_AUX		0xc0000103 /* Auxiliary TSC */
-
-/* EFER bits: */
-#define EFER_SCE		(1<<0)  /* SYSCALL/SYSRET */
-#define EFER_LME		(1<<8)  /* Long mode enable */
-#define EFER_LMA		(1<<10) /* Long mode active (read-only) */
-#define EFER_NX			(1<<11) /* No execute enable */
-#define EFER_SVME		(1<<12) /* Enable virtualization */
-#define EFER_LMSLE		(1<<13) /* Long Mode Segment Limit Enable */
-#define EFER_FFXSR		(1<<14) /* Enable Fast FXSAVE/FXRSTOR */
-
-/* Intel MSRs. Some also available on other CPUs */
-
-#define MSR_PPIN_CTL			0x0000004e
-#define MSR_PPIN			0x0000004f
-
-#define MSR_IA32_PERFCTR0		0x000000c1
-#define MSR_IA32_PERFCTR1		0x000000c2
-#define MSR_FSB_FREQ			0x000000cd
-#define MSR_PLATFORM_INFO		0x000000ce
-#define MSR_PLATFORM_INFO_CPUID_FAULT_BIT	31
-#define MSR_PLATFORM_INFO_CPUID_FAULT		BIT_ULL(MSR_PLATFORM_INFO_CPUID_FAULT_BIT)
-
-#define MSR_PKG_CST_CONFIG_CONTROL	0x000000e2
-#define NHM_C3_AUTO_DEMOTE		(1UL << 25)
-#define NHM_C1_AUTO_DEMOTE		(1UL << 26)
-#define ATM_LNC_C6_AUTO_DEMOTE		(1UL << 25)
-#define SNB_C1_AUTO_UNDEMOTE		(1UL << 27)
-#define SNB_C3_AUTO_UNDEMOTE		(1UL << 28)
-
-#define MSR_MTRRcap			0x000000fe
-#define MSR_IA32_BBL_CR_CTL		0x00000119
-#define MSR_IA32_BBL_CR_CTL3		0x0000011e
-
-#define MSR_IA32_SYSENTER_CS		0x00000174
-#define MSR_IA32_SYSENTER_ESP		0x00000175
-#define MSR_IA32_SYSENTER_EIP		0x00000176
-
-#define MSR_IA32_MCG_CAP		0x00000179
-#define MSR_IA32_MCG_STATUS		0x0000017a
-#define MSR_IA32_MCG_CTL		0x0000017b
-#define MSR_IA32_MCG_EXT_CTL		0x000004d0
-
-#define MSR_OFFCORE_RSP_0		0x000001a6
-#define MSR_OFFCORE_RSP_1		0x000001a7
-#define MSR_TURBO_RATIO_LIMIT		0x000001ad
-#define MSR_TURBO_RATIO_LIMIT1		0x000001ae
-#define MSR_TURBO_RATIO_LIMIT2		0x000001af
-
-#define MSR_LBR_SELECT			0x000001c8
-#define MSR_LBR_TOS			0x000001c9
-#define MSR_LBR_NHM_FROM		0x00000680
-#define MSR_LBR_NHM_TO			0x000006c0
-#define MSR_LBR_CORE_FROM		0x00000040
-#define MSR_LBR_CORE_TO			0x00000060
-
-#define MSR_LBR_INFO_0			0x00000dc0 /* ... 0xddf for _31 */
-#define LBR_INFO_MISPRED		BIT_ULL(63)
-#define LBR_INFO_IN_TX			BIT_ULL(62)
-#define LBR_INFO_ABORT			BIT_ULL(61)
-#define LBR_INFO_CYCLES			0xffff
-
-#define MSR_IA32_PEBS_ENABLE		0x000003f1
-#define MSR_IA32_DS_AREA		0x00000600
-#define MSR_IA32_PERF_CAPABILITIES	0x00000345
-#define MSR_PEBS_LD_LAT_THRESHOLD	0x000003f6
-
-#define MSR_IA32_RTIT_CTL		0x00000570
-#define MSR_IA32_RTIT_STATUS		0x00000571
-#define MSR_IA32_RTIT_ADDR0_A		0x00000580
-#define MSR_IA32_RTIT_ADDR0_B		0x00000581
-#define MSR_IA32_RTIT_ADDR1_A		0x00000582
-#define MSR_IA32_RTIT_ADDR1_B		0x00000583
-#define MSR_IA32_RTIT_ADDR2_A		0x00000584
-#define MSR_IA32_RTIT_ADDR2_B		0x00000585
-#define MSR_IA32_RTIT_ADDR3_A		0x00000586
-#define MSR_IA32_RTIT_ADDR3_B		0x00000587
-#define MSR_IA32_RTIT_CR3_MATCH		0x00000572
-#define MSR_IA32_RTIT_OUTPUT_BASE	0x00000560
-#define MSR_IA32_RTIT_OUTPUT_MASK	0x00000561
-
-#define MSR_MTRRfix64K_00000		0x00000250
-#define MSR_MTRRfix16K_80000		0x00000258
-#define MSR_MTRRfix16K_A0000		0x00000259
-#define MSR_MTRRfix4K_C0000		0x00000268
-#define MSR_MTRRfix4K_C8000		0x00000269
-#define MSR_MTRRfix4K_D0000		0x0000026a
-#define MSR_MTRRfix4K_D8000		0x0000026b
-#define MSR_MTRRfix4K_E0000		0x0000026c
-#define MSR_MTRRfix4K_E8000		0x0000026d
-#define MSR_MTRRfix4K_F0000		0x0000026e
-#define MSR_MTRRfix4K_F8000		0x0000026f
-#define MSR_MTRRdefType			0x000002ff
-
-#define MSR_IA32_CR_PAT			0x00000277
-
-#define MSR_IA32_DEBUGCTLMSR		0x000001d9
-#define MSR_IA32_LASTBRANCHFROMIP	0x000001db
-#define MSR_IA32_LASTBRANCHTOIP		0x000001dc
-#define MSR_IA32_LASTINTFROMIP		0x000001dd
-#define MSR_IA32_LASTINTTOIP		0x000001de
-
-/* DEBUGCTLMSR bits (others vary by model): */
-#define DEBUGCTLMSR_LBR			(1UL <<  0) /* last branch recording */
-#define DEBUGCTLMSR_BTF_SHIFT		1
-#define DEBUGCTLMSR_BTF			(1UL <<  1) /* single-step on branches */
-#define DEBUGCTLMSR_TR			(1UL <<  6)
-#define DEBUGCTLMSR_BTS			(1UL <<  7)
-#define DEBUGCTLMSR_BTINT		(1UL <<  8)
-#define DEBUGCTLMSR_BTS_OFF_OS		(1UL <<  9)
-#define DEBUGCTLMSR_BTS_OFF_USR		(1UL << 10)
-#define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI	(1UL << 11)
-#define DEBUGCTLMSR_FREEZE_IN_SMM_BIT	14
-#define DEBUGCTLMSR_FREEZE_IN_SMM	(1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT)
-
-#define MSR_PEBS_FRONTEND		0x000003f7
-
-#define MSR_IA32_POWER_CTL		0x000001fc
-
-#define MSR_IA32_MC0_CTL		0x00000400
-#define MSR_IA32_MC0_STATUS		0x00000401
-#define MSR_IA32_MC0_ADDR		0x00000402
-#define MSR_IA32_MC0_MISC		0x00000403
-
-/* C-state Residency Counters */
-#define MSR_PKG_C3_RESIDENCY		0x000003f8
-#define MSR_PKG_C6_RESIDENCY		0x000003f9
-#define MSR_ATOM_PKG_C6_RESIDENCY	0x000003fa
-#define MSR_PKG_C7_RESIDENCY		0x000003fa
-#define MSR_CORE_C3_RESIDENCY		0x000003fc
-#define MSR_CORE_C6_RESIDENCY		0x000003fd
-#define MSR_CORE_C7_RESIDENCY		0x000003fe
-#define MSR_KNL_CORE_C6_RESIDENCY	0x000003ff
-#define MSR_PKG_C2_RESIDENCY		0x0000060d
-#define MSR_PKG_C8_RESIDENCY		0x00000630
-#define MSR_PKG_C9_RESIDENCY		0x00000631
-#define MSR_PKG_C10_RESIDENCY		0x00000632
-
-/* Interrupt Response Limit */
-#define MSR_PKGC3_IRTL			0x0000060a
-#define MSR_PKGC6_IRTL			0x0000060b
-#define MSR_PKGC7_IRTL			0x0000060c
-#define MSR_PKGC8_IRTL			0x00000633
-#define MSR_PKGC9_IRTL			0x00000634
-#define MSR_PKGC10_IRTL			0x00000635
-
-/* Run Time Average Power Limiting (RAPL) Interface */
-
-#define MSR_RAPL_POWER_UNIT		0x00000606
-
-#define MSR_PKG_POWER_LIMIT		0x00000610
-#define MSR_PKG_ENERGY_STATUS		0x00000611
-#define MSR_PKG_PERF_STATUS		0x00000613
-#define MSR_PKG_POWER_INFO		0x00000614
-
-#define MSR_DRAM_POWER_LIMIT		0x00000618
-#define MSR_DRAM_ENERGY_STATUS		0x00000619
-#define MSR_DRAM_PERF_STATUS		0x0000061b
-#define MSR_DRAM_POWER_INFO		0x0000061c
-
-#define MSR_PP0_POWER_LIMIT		0x00000638
-#define MSR_PP0_ENERGY_STATUS		0x00000639
-#define MSR_PP0_POLICY			0x0000063a
-#define MSR_PP0_PERF_STATUS		0x0000063b
-
-#define MSR_PP1_POWER_LIMIT		0x00000640
-#define MSR_PP1_ENERGY_STATUS		0x00000641
-#define MSR_PP1_POLICY			0x00000642
-
-/* Config TDP MSRs */
-#define MSR_CONFIG_TDP_NOMINAL		0x00000648
-#define MSR_CONFIG_TDP_LEVEL_1		0x00000649
-#define MSR_CONFIG_TDP_LEVEL_2		0x0000064A
-#define MSR_CONFIG_TDP_CONTROL		0x0000064B
-#define MSR_TURBO_ACTIVATION_RATIO	0x0000064C
-
-#define MSR_PLATFORM_ENERGY_STATUS	0x0000064D
-
-#define MSR_PKG_WEIGHTED_CORE_C0_RES	0x00000658
-#define MSR_PKG_ANY_CORE_C0_RES		0x00000659
-#define MSR_PKG_ANY_GFXE_C0_RES		0x0000065A
-#define MSR_PKG_BOTH_CORE_GFXE_C0_RES	0x0000065B
-
-#define MSR_CORE_C1_RES			0x00000660
-#define MSR_MODULE_C6_RES_MS		0x00000664
-
-#define MSR_CC6_DEMOTION_POLICY_CONFIG	0x00000668
-#define MSR_MC6_DEMOTION_POLICY_CONFIG	0x00000669
-
-#define MSR_ATOM_CORE_RATIOS		0x0000066a
-#define MSR_ATOM_CORE_VIDS		0x0000066b
-#define MSR_ATOM_CORE_TURBO_RATIOS	0x0000066c
-#define MSR_ATOM_CORE_TURBO_VIDS	0x0000066d
-
-
-#define MSR_CORE_PERF_LIMIT_REASONS	0x00000690
-#define MSR_GFX_PERF_LIMIT_REASONS	0x000006B0
-#define MSR_RING_PERF_LIMIT_REASONS	0x000006B1
-
-/* Hardware P state interface */
-#define MSR_PPERF			0x0000064e
-#define MSR_PERF_LIMIT_REASONS		0x0000064f
-#define MSR_PM_ENABLE			0x00000770
-#define MSR_HWP_CAPABILITIES		0x00000771
-#define MSR_HWP_REQUEST_PKG		0x00000772
-#define MSR_HWP_INTERRUPT		0x00000773
-#define MSR_HWP_REQUEST			0x00000774
-#define MSR_HWP_STATUS			0x00000777
-
-/* CPUID.6.EAX */
-#define HWP_BASE_BIT			(1<<7)
-#define HWP_NOTIFICATIONS_BIT		(1<<8)
-#define HWP_ACTIVITY_WINDOW_BIT		(1<<9)
-#define HWP_ENERGY_PERF_PREFERENCE_BIT	(1<<10)
-#define HWP_PACKAGE_LEVEL_REQUEST_BIT	(1<<11)
-
-/* IA32_HWP_CAPABILITIES */
-#define HWP_HIGHEST_PERF(x)		(((x) >> 0) & 0xff)
-#define HWP_GUARANTEED_PERF(x)		(((x) >> 8) & 0xff)
-#define HWP_MOSTEFFICIENT_PERF(x)	(((x) >> 16) & 0xff)
-#define HWP_LOWEST_PERF(x)		(((x) >> 24) & 0xff)
-
-/* IA32_HWP_REQUEST */
-#define HWP_MIN_PERF(x)			(x & 0xff)
-#define HWP_MAX_PERF(x)			((x & 0xff) << 8)
-#define HWP_DESIRED_PERF(x)		((x & 0xff) << 16)
-#define HWP_ENERGY_PERF_PREFERENCE(x)	(((unsigned long long) x & 0xff) << 24)
-#define HWP_EPP_PERFORMANCE		0x00
-#define HWP_EPP_BALANCE_PERFORMANCE	0x80
-#define HWP_EPP_BALANCE_POWERSAVE	0xC0
-#define HWP_EPP_POWERSAVE		0xFF
-#define HWP_ACTIVITY_WINDOW(x)		((unsigned long long)(x & 0xff3) << 32)
-#define HWP_PACKAGE_CONTROL(x)		((unsigned long long)(x & 0x1) << 42)
-
-/* IA32_HWP_STATUS */
-#define HWP_GUARANTEED_CHANGE(x)	(x & 0x1)
-#define HWP_EXCURSION_TO_MINIMUM(x)	(x & 0x4)
-
-/* IA32_HWP_INTERRUPT */
-#define HWP_CHANGE_TO_GUARANTEED_INT(x)	(x & 0x1)
-#define HWP_EXCURSION_TO_MINIMUM_INT(x)	(x & 0x2)
-
-#define MSR_AMD64_MC0_MASK		0xc0010044
-
-#define MSR_IA32_MCx_CTL(x)		(MSR_IA32_MC0_CTL + 4*(x))
-#define MSR_IA32_MCx_STATUS(x)		(MSR_IA32_MC0_STATUS + 4*(x))
-#define MSR_IA32_MCx_ADDR(x)		(MSR_IA32_MC0_ADDR + 4*(x))
-#define MSR_IA32_MCx_MISC(x)		(MSR_IA32_MC0_MISC + 4*(x))
-
-#define MSR_AMD64_MCx_MASK(x)		(MSR_AMD64_MC0_MASK + (x))
-
-/* These are consecutive and not in the normal 4er MCE bank block */
-#define MSR_IA32_MC0_CTL2		0x00000280
-#define MSR_IA32_MCx_CTL2(x)		(MSR_IA32_MC0_CTL2 + (x))
-
-#define MSR_P6_PERFCTR0			0x000000c1
-#define MSR_P6_PERFCTR1			0x000000c2
-#define MSR_P6_EVNTSEL0			0x00000186
-#define MSR_P6_EVNTSEL1			0x00000187
-
-#define MSR_KNC_PERFCTR0               0x00000020
-#define MSR_KNC_PERFCTR1               0x00000021
-#define MSR_KNC_EVNTSEL0               0x00000028
-#define MSR_KNC_EVNTSEL1               0x00000029
-
-/* Alternative perfctr range with full access. */
-#define MSR_IA32_PMC0			0x000004c1
-
-/* AMD64 MSRs. Not complete. See the architecture manual for a more
-   complete list. */
-
-#define MSR_AMD64_PATCH_LEVEL		0x0000008b
-#define MSR_AMD64_TSC_RATIO		0xc0000104
-#define MSR_AMD64_NB_CFG		0xc001001f
-#define MSR_AMD64_PATCH_LOADER		0xc0010020
-#define MSR_AMD64_OSVW_ID_LENGTH	0xc0010140
-#define MSR_AMD64_OSVW_STATUS		0xc0010141
-#define MSR_AMD64_LS_CFG		0xc0011020
-#define MSR_AMD64_DC_CFG		0xc0011022
-#define MSR_AMD64_BU_CFG2		0xc001102a
-#define MSR_AMD64_IBSFETCHCTL		0xc0011030
-#define MSR_AMD64_IBSFETCHLINAD		0xc0011031
-#define MSR_AMD64_IBSFETCHPHYSAD	0xc0011032
-#define MSR_AMD64_IBSFETCH_REG_COUNT	3
-#define MSR_AMD64_IBSFETCH_REG_MASK	((1UL<<MSR_AMD64_IBSFETCH_REG_COUNT)-1)
-#define MSR_AMD64_IBSOPCTL		0xc0011033
-#define MSR_AMD64_IBSOPRIP		0xc0011034
-#define MSR_AMD64_IBSOPDATA		0xc0011035
-#define MSR_AMD64_IBSOPDATA2		0xc0011036
-#define MSR_AMD64_IBSOPDATA3		0xc0011037
-#define MSR_AMD64_IBSDCLINAD		0xc0011038
-#define MSR_AMD64_IBSDCPHYSAD		0xc0011039
-#define MSR_AMD64_IBSOP_REG_COUNT	7
-#define MSR_AMD64_IBSOP_REG_MASK	((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1)
-#define MSR_AMD64_IBSCTL		0xc001103a
-#define MSR_AMD64_IBSBRTARGET		0xc001103b
-#define MSR_AMD64_IBSOPDATA4		0xc001103d
-#define MSR_AMD64_IBS_REG_COUNT_MAX	8 /* includes MSR_AMD64_IBSBRTARGET */
-#define MSR_AMD64_SEV			0xc0010131
-#define MSR_AMD64_SEV_ENABLED_BIT	0
-#define MSR_AMD64_SEV_ENABLED		BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
-
-/* Fam 17h MSRs */
-#define MSR_F17H_IRPERF			0xc00000e9
-
-/* Fam 16h MSRs */
-#define MSR_F16H_L2I_PERF_CTL		0xc0010230
-#define MSR_F16H_L2I_PERF_CTR		0xc0010231
-#define MSR_F16H_DR1_ADDR_MASK		0xc0011019
-#define MSR_F16H_DR2_ADDR_MASK		0xc001101a
-#define MSR_F16H_DR3_ADDR_MASK		0xc001101b
-#define MSR_F16H_DR0_ADDR_MASK		0xc0011027
-
-/* Fam 15h MSRs */
-#define MSR_F15H_PERF_CTL		0xc0010200
-#define MSR_F15H_PERF_CTR		0xc0010201
-#define MSR_F15H_NB_PERF_CTL		0xc0010240
-#define MSR_F15H_NB_PERF_CTR		0xc0010241
-#define MSR_F15H_PTSC			0xc0010280
-#define MSR_F15H_IC_CFG			0xc0011021
-
-/* Fam 10h MSRs */
-#define MSR_FAM10H_MMIO_CONF_BASE	0xc0010058
-#define FAM10H_MMIO_CONF_ENABLE		(1<<0)
-#define FAM10H_MMIO_CONF_BUSRANGE_MASK	0xf
-#define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2
-#define FAM10H_MMIO_CONF_BASE_MASK	0xfffffffULL
-#define FAM10H_MMIO_CONF_BASE_SHIFT	20
-#define MSR_FAM10H_NODE_ID		0xc001100c
-#define MSR_F10H_DECFG			0xc0011029
-#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT	1
-#define MSR_F10H_DECFG_LFENCE_SERIALIZE		BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT)
-
-/* K8 MSRs */
-#define MSR_K8_TOP_MEM1			0xc001001a
-#define MSR_K8_TOP_MEM2			0xc001001d
-#define MSR_K8_SYSCFG			0xc0010010
-#define MSR_K8_SYSCFG_MEM_ENCRYPT_BIT	23
-#define MSR_K8_SYSCFG_MEM_ENCRYPT	BIT_ULL(MSR_K8_SYSCFG_MEM_ENCRYPT_BIT)
-#define MSR_K8_INT_PENDING_MSG		0xc0010055
-/* C1E active bits in int pending message */
-#define K8_INTP_C1E_ACTIVE_MASK		0x18000000
-#define MSR_K8_TSEG_ADDR		0xc0010112
-#define MSR_K8_TSEG_MASK		0xc0010113
-#define K8_MTRRFIXRANGE_DRAM_ENABLE	0x00040000 /* MtrrFixDramEn bit    */
-#define K8_MTRRFIXRANGE_DRAM_MODIFY	0x00080000 /* MtrrFixDramModEn bit */
-#define K8_MTRR_RDMEM_WRMEM_MASK	0x18181818 /* Mask: RdMem|WrMem    */
-
-/* K7 MSRs */
-#define MSR_K7_EVNTSEL0			0xc0010000
-#define MSR_K7_PERFCTR0			0xc0010004
-#define MSR_K7_EVNTSEL1			0xc0010001
-#define MSR_K7_PERFCTR1			0xc0010005
-#define MSR_K7_EVNTSEL2			0xc0010002
-#define MSR_K7_PERFCTR2			0xc0010006
-#define MSR_K7_EVNTSEL3			0xc0010003
-#define MSR_K7_PERFCTR3			0xc0010007
-#define MSR_K7_CLK_CTL			0xc001001b
-#define MSR_K7_HWCR			0xc0010015
-#define MSR_K7_HWCR_SMMLOCK_BIT		0
-#define MSR_K7_HWCR_SMMLOCK		BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
-#define MSR_K7_FID_VID_CTL		0xc0010041
-#define MSR_K7_FID_VID_STATUS		0xc0010042
-
-/* K6 MSRs */
-#define MSR_K6_WHCR			0xc0000082
-#define MSR_K6_UWCCR			0xc0000085
-#define MSR_K6_EPMR			0xc0000086
-#define MSR_K6_PSOR			0xc0000087
-#define MSR_K6_PFIR			0xc0000088
-
-/* Centaur-Hauls/IDT defined MSRs. */
-#define MSR_IDT_FCR1			0x00000107
-#define MSR_IDT_FCR2			0x00000108
-#define MSR_IDT_FCR3			0x00000109
-#define MSR_IDT_FCR4			0x0000010a
-
-#define MSR_IDT_MCR0			0x00000110
-#define MSR_IDT_MCR1			0x00000111
-#define MSR_IDT_MCR2			0x00000112
-#define MSR_IDT_MCR3			0x00000113
-#define MSR_IDT_MCR4			0x00000114
-#define MSR_IDT_MCR5			0x00000115
-#define MSR_IDT_MCR6			0x00000116
-#define MSR_IDT_MCR7			0x00000117
-#define MSR_IDT_MCR_CTRL		0x00000120
-
-/* VIA Cyrix defined MSRs*/
-#define MSR_VIA_FCR			0x00001107
-#define MSR_VIA_LONGHAUL		0x0000110a
-#define MSR_VIA_RNG			0x0000110b
-#define MSR_VIA_BCR2			0x00001147
-
-/* Transmeta defined MSRs */
-#define MSR_TMTA_LONGRUN_CTRL		0x80868010
-#define MSR_TMTA_LONGRUN_FLAGS		0x80868011
-#define MSR_TMTA_LRTI_READOUT		0x80868018
-#define MSR_TMTA_LRTI_VOLT_MHZ		0x8086801a
-
-/* Intel defined MSRs. */
-#define MSR_IA32_P5_MC_ADDR		0x00000000
-#define MSR_IA32_P5_MC_TYPE		0x00000001
-#define MSR_IA32_TSC			0x00000010
-#define MSR_IA32_PLATFORM_ID		0x00000017
-#define MSR_IA32_EBL_CR_POWERON		0x0000002a
-#define MSR_EBC_FREQUENCY_ID		0x0000002c
-#define MSR_SMI_COUNT			0x00000034
-#define MSR_IA32_FEATURE_CONTROL        0x0000003a
-#define MSR_IA32_TSC_ADJUST             0x0000003b
-#define MSR_IA32_BNDCFGS		0x00000d90
-
-#define MSR_IA32_BNDCFGS_RSVD		0x00000ffc
-
-#define MSR_IA32_XSS			0x00000da0
-
-#define FEATURE_CONTROL_LOCKED				(1<<0)
-#define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX	(1<<1)
-#define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX	(1<<2)
-#define FEATURE_CONTROL_LMCE				(1<<20)
-
-#define MSR_IA32_APICBASE		0x0000001b
-#define MSR_IA32_APICBASE_BSP		(1<<8)
-#define MSR_IA32_APICBASE_ENABLE	(1<<11)
-#define MSR_IA32_APICBASE_BASE		(0xfffff<<12)
-
-#define MSR_IA32_TSCDEADLINE		0x000006e0
-
-#define MSR_IA32_UCODE_WRITE		0x00000079
-#define MSR_IA32_UCODE_REV		0x0000008b
-
-#define MSR_IA32_SMM_MONITOR_CTL	0x0000009b
-#define MSR_IA32_SMBASE			0x0000009e
-
-#define MSR_IA32_PERF_STATUS		0x00000198
-#define MSR_IA32_PERF_CTL		0x00000199
-#define INTEL_PERF_CTL_MASK		0xffff
-#define MSR_AMD_PSTATE_DEF_BASE		0xc0010064
-#define MSR_AMD_PERF_STATUS		0xc0010063
-#define MSR_AMD_PERF_CTL		0xc0010062
-
-#define MSR_IA32_MPERF			0x000000e7
-#define MSR_IA32_APERF			0x000000e8
-
-#define MSR_IA32_THERM_CONTROL		0x0000019a
-#define MSR_IA32_THERM_INTERRUPT	0x0000019b
-
-#define THERM_INT_HIGH_ENABLE		(1 << 0)
-#define THERM_INT_LOW_ENABLE		(1 << 1)
-#define THERM_INT_PLN_ENABLE		(1 << 24)
-
-#define MSR_IA32_THERM_STATUS		0x0000019c
-
-#define THERM_STATUS_PROCHOT		(1 << 0)
-#define THERM_STATUS_POWER_LIMIT	(1 << 10)
-
-#define MSR_THERM2_CTL			0x0000019d
-
-#define MSR_THERM2_CTL_TM_SELECT	(1ULL << 16)
-
-#define MSR_IA32_MISC_ENABLE		0x000001a0
-
-#define MSR_IA32_TEMPERATURE_TARGET	0x000001a2
-
-#define MSR_MISC_FEATURE_CONTROL	0x000001a4
-#define MSR_MISC_PWR_MGMT		0x000001aa
-
-#define MSR_IA32_ENERGY_PERF_BIAS	0x000001b0
-#define ENERGY_PERF_BIAS_PERFORMANCE		0
-#define ENERGY_PERF_BIAS_BALANCE_PERFORMANCE	4
-#define ENERGY_PERF_BIAS_NORMAL			6
-#define ENERGY_PERF_BIAS_BALANCE_POWERSAVE	8
-#define ENERGY_PERF_BIAS_POWERSAVE		15
-
-#define MSR_IA32_PACKAGE_THERM_STATUS		0x000001b1
-
-#define PACKAGE_THERM_STATUS_PROCHOT		(1 << 0)
-#define PACKAGE_THERM_STATUS_POWER_LIMIT	(1 << 10)
-
-#define MSR_IA32_PACKAGE_THERM_INTERRUPT	0x000001b2
-
-#define PACKAGE_THERM_INT_HIGH_ENABLE		(1 << 0)
-#define PACKAGE_THERM_INT_LOW_ENABLE		(1 << 1)
-#define PACKAGE_THERM_INT_PLN_ENABLE		(1 << 24)
-
-/* Thermal Thresholds Support */
-#define THERM_INT_THRESHOLD0_ENABLE    (1 << 15)
-#define THERM_SHIFT_THRESHOLD0        8
-#define THERM_MASK_THRESHOLD0          (0x7f << THERM_SHIFT_THRESHOLD0)
-#define THERM_INT_THRESHOLD1_ENABLE    (1 << 23)
-#define THERM_SHIFT_THRESHOLD1        16
-#define THERM_MASK_THRESHOLD1          (0x7f << THERM_SHIFT_THRESHOLD1)
-#define THERM_STATUS_THRESHOLD0        (1 << 6)
-#define THERM_LOG_THRESHOLD0           (1 << 7)
-#define THERM_STATUS_THRESHOLD1        (1 << 8)
-#define THERM_LOG_THRESHOLD1           (1 << 9)
-
-/* MISC_ENABLE bits: architectural */
-#define MSR_IA32_MISC_ENABLE_FAST_STRING_BIT		0
-#define MSR_IA32_MISC_ENABLE_FAST_STRING		(1ULL << MSR_IA32_MISC_ENABLE_FAST_STRING_BIT)
-#define MSR_IA32_MISC_ENABLE_TCC_BIT			1
-#define MSR_IA32_MISC_ENABLE_TCC			(1ULL << MSR_IA32_MISC_ENABLE_TCC_BIT)
-#define MSR_IA32_MISC_ENABLE_EMON_BIT			7
-#define MSR_IA32_MISC_ENABLE_EMON			(1ULL << MSR_IA32_MISC_ENABLE_EMON_BIT)
-#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT		11
-#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL		(1ULL << MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT)
-#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT		12
-#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL		(1ULL << MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT)
-#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT	16
-#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP		(1ULL << MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT)
-#define MSR_IA32_MISC_ENABLE_MWAIT_BIT			18
-#define MSR_IA32_MISC_ENABLE_MWAIT			(1ULL << MSR_IA32_MISC_ENABLE_MWAIT_BIT)
-#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT		22
-#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID		(1ULL << MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT)
-#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT		23
-#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT		34
-#define MSR_IA32_MISC_ENABLE_XD_DISABLE			(1ULL << MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT)
-
-/* MISC_ENABLE bits: model-specific, meaning may vary from core to core */
-#define MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT		2
-#define MSR_IA32_MISC_ENABLE_X87_COMPAT			(1ULL << MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT)
-#define MSR_IA32_MISC_ENABLE_TM1_BIT			3
-#define MSR_IA32_MISC_ENABLE_TM1			(1ULL << MSR_IA32_MISC_ENABLE_TM1_BIT)
-#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT	4
-#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT	6
-#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT		8
-#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK		(1ULL << MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT)
-#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT	9
-#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_FERR_BIT			10
-#define MSR_IA32_MISC_ENABLE_FERR			(1ULL << MSR_IA32_MISC_ENABLE_FERR_BIT)
-#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT		10
-#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX		(1ULL << MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT)
-#define MSR_IA32_MISC_ENABLE_TM2_BIT			13
-#define MSR_IA32_MISC_ENABLE_TM2			(1ULL << MSR_IA32_MISC_ENABLE_TM2_BIT)
-#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT	19
-#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT		20
-#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK		(1ULL << MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT)
-#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT		24
-#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT		(1ULL << MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT)
-#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT	37
-#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT		38
-#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT	39
-#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT)
-
-/* MISC_FEATURES_ENABLES non-architectural features */
-#define MSR_MISC_FEATURES_ENABLES	0x00000140
-
-#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT	0
-#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT		BIT_ULL(MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT)
-#define MSR_MISC_FEATURES_ENABLES_RING3MWAIT_BIT	1
-
-#define MSR_IA32_TSC_DEADLINE		0x000006E0
-
-/* P4/Xeon+ specific */
-#define MSR_IA32_MCG_EAX		0x00000180
-#define MSR_IA32_MCG_EBX		0x00000181
-#define MSR_IA32_MCG_ECX		0x00000182
-#define MSR_IA32_MCG_EDX		0x00000183
-#define MSR_IA32_MCG_ESI		0x00000184
-#define MSR_IA32_MCG_EDI		0x00000185
-#define MSR_IA32_MCG_EBP		0x00000186
-#define MSR_IA32_MCG_ESP		0x00000187
-#define MSR_IA32_MCG_EFLAGS		0x00000188
-#define MSR_IA32_MCG_EIP		0x00000189
-#define MSR_IA32_MCG_RESERVED		0x0000018a
-
-/* Pentium IV performance counter MSRs */
-#define MSR_P4_BPU_PERFCTR0		0x00000300
-#define MSR_P4_BPU_PERFCTR1		0x00000301
-#define MSR_P4_BPU_PERFCTR2		0x00000302
-#define MSR_P4_BPU_PERFCTR3		0x00000303
-#define MSR_P4_MS_PERFCTR0		0x00000304
-#define MSR_P4_MS_PERFCTR1		0x00000305
-#define MSR_P4_MS_PERFCTR2		0x00000306
-#define MSR_P4_MS_PERFCTR3		0x00000307
-#define MSR_P4_FLAME_PERFCTR0		0x00000308
-#define MSR_P4_FLAME_PERFCTR1		0x00000309
-#define MSR_P4_FLAME_PERFCTR2		0x0000030a
-#define MSR_P4_FLAME_PERFCTR3		0x0000030b
-#define MSR_P4_IQ_PERFCTR0		0x0000030c
-#define MSR_P4_IQ_PERFCTR1		0x0000030d
-#define MSR_P4_IQ_PERFCTR2		0x0000030e
-#define MSR_P4_IQ_PERFCTR3		0x0000030f
-#define MSR_P4_IQ_PERFCTR4		0x00000310
-#define MSR_P4_IQ_PERFCTR5		0x00000311
-#define MSR_P4_BPU_CCCR0		0x00000360
-#define MSR_P4_BPU_CCCR1		0x00000361
-#define MSR_P4_BPU_CCCR2		0x00000362
-#define MSR_P4_BPU_CCCR3		0x00000363
-#define MSR_P4_MS_CCCR0			0x00000364
-#define MSR_P4_MS_CCCR1			0x00000365
-#define MSR_P4_MS_CCCR2			0x00000366
-#define MSR_P4_MS_CCCR3			0x00000367
-#define MSR_P4_FLAME_CCCR0		0x00000368
-#define MSR_P4_FLAME_CCCR1		0x00000369
-#define MSR_P4_FLAME_CCCR2		0x0000036a
-#define MSR_P4_FLAME_CCCR3		0x0000036b
-#define MSR_P4_IQ_CCCR0			0x0000036c
-#define MSR_P4_IQ_CCCR1			0x0000036d
-#define MSR_P4_IQ_CCCR2			0x0000036e
-#define MSR_P4_IQ_CCCR3			0x0000036f
-#define MSR_P4_IQ_CCCR4			0x00000370
-#define MSR_P4_IQ_CCCR5			0x00000371
-#define MSR_P4_ALF_ESCR0		0x000003ca
-#define MSR_P4_ALF_ESCR1		0x000003cb
-#define MSR_P4_BPU_ESCR0		0x000003b2
-#define MSR_P4_BPU_ESCR1		0x000003b3
-#define MSR_P4_BSU_ESCR0		0x000003a0
-#define MSR_P4_BSU_ESCR1		0x000003a1
-#define MSR_P4_CRU_ESCR0		0x000003b8
-#define MSR_P4_CRU_ESCR1		0x000003b9
-#define MSR_P4_CRU_ESCR2		0x000003cc
-#define MSR_P4_CRU_ESCR3		0x000003cd
-#define MSR_P4_CRU_ESCR4		0x000003e0
-#define MSR_P4_CRU_ESCR5		0x000003e1
-#define MSR_P4_DAC_ESCR0		0x000003a8
-#define MSR_P4_DAC_ESCR1		0x000003a9
-#define MSR_P4_FIRM_ESCR0		0x000003a4
-#define MSR_P4_FIRM_ESCR1		0x000003a5
-#define MSR_P4_FLAME_ESCR0		0x000003a6
-#define MSR_P4_FLAME_ESCR1		0x000003a7
-#define MSR_P4_FSB_ESCR0		0x000003a2
-#define MSR_P4_FSB_ESCR1		0x000003a3
-#define MSR_P4_IQ_ESCR0			0x000003ba
-#define MSR_P4_IQ_ESCR1			0x000003bb
-#define MSR_P4_IS_ESCR0			0x000003b4
-#define MSR_P4_IS_ESCR1			0x000003b5
-#define MSR_P4_ITLB_ESCR0		0x000003b6
-#define MSR_P4_ITLB_ESCR1		0x000003b7
-#define MSR_P4_IX_ESCR0			0x000003c8
-#define MSR_P4_IX_ESCR1			0x000003c9
-#define MSR_P4_MOB_ESCR0		0x000003aa
-#define MSR_P4_MOB_ESCR1		0x000003ab
-#define MSR_P4_MS_ESCR0			0x000003c0
-#define MSR_P4_MS_ESCR1			0x000003c1
-#define MSR_P4_PMH_ESCR0		0x000003ac
-#define MSR_P4_PMH_ESCR1		0x000003ad
-#define MSR_P4_RAT_ESCR0		0x000003bc
-#define MSR_P4_RAT_ESCR1		0x000003bd
-#define MSR_P4_SAAT_ESCR0		0x000003ae
-#define MSR_P4_SAAT_ESCR1		0x000003af
-#define MSR_P4_SSU_ESCR0		0x000003be
-#define MSR_P4_SSU_ESCR1		0x000003bf /* guess: not in manual */
-
-#define MSR_P4_TBPU_ESCR0		0x000003c2
-#define MSR_P4_TBPU_ESCR1		0x000003c3
-#define MSR_P4_TC_ESCR0			0x000003c4
-#define MSR_P4_TC_ESCR1			0x000003c5
-#define MSR_P4_U2L_ESCR0		0x000003b0
-#define MSR_P4_U2L_ESCR1		0x000003b1
-
-#define MSR_P4_PEBS_MATRIX_VERT		0x000003f2
-
-/* Intel Core-based CPU performance counters */
-#define MSR_CORE_PERF_FIXED_CTR0	0x00000309
-#define MSR_CORE_PERF_FIXED_CTR1	0x0000030a
-#define MSR_CORE_PERF_FIXED_CTR2	0x0000030b
-#define MSR_CORE_PERF_FIXED_CTR_CTRL	0x0000038d
-#define MSR_CORE_PERF_GLOBAL_STATUS	0x0000038e
-#define MSR_CORE_PERF_GLOBAL_CTRL	0x0000038f
-#define MSR_CORE_PERF_GLOBAL_OVF_CTRL	0x00000390
-
-/* Geode defined MSRs */
-#define MSR_GEODE_BUSCONT_CONF0		0x00001900
-
-/* Intel VT MSRs */
-#define MSR_IA32_VMX_BASIC              0x00000480
-#define MSR_IA32_VMX_PINBASED_CTLS      0x00000481
-#define MSR_IA32_VMX_PROCBASED_CTLS     0x00000482
-#define MSR_IA32_VMX_EXIT_CTLS          0x00000483
-#define MSR_IA32_VMX_ENTRY_CTLS         0x00000484
-#define MSR_IA32_VMX_MISC               0x00000485
-#define MSR_IA32_VMX_CR0_FIXED0         0x00000486
-#define MSR_IA32_VMX_CR0_FIXED1         0x00000487
-#define MSR_IA32_VMX_CR4_FIXED0         0x00000488
-#define MSR_IA32_VMX_CR4_FIXED1         0x00000489
-#define MSR_IA32_VMX_VMCS_ENUM          0x0000048a
-#define MSR_IA32_VMX_PROCBASED_CTLS2    0x0000048b
-#define MSR_IA32_VMX_EPT_VPID_CAP       0x0000048c
-#define MSR_IA32_VMX_TRUE_PINBASED_CTLS  0x0000048d
-#define MSR_IA32_VMX_TRUE_PROCBASED_CTLS 0x0000048e
-#define MSR_IA32_VMX_TRUE_EXIT_CTLS      0x0000048f
-#define MSR_IA32_VMX_TRUE_ENTRY_CTLS     0x00000490
-#define MSR_IA32_VMX_VMFUNC             0x00000491
-
-/* VMX_BASIC bits and bitmasks */
-#define VMX_BASIC_VMCS_SIZE_SHIFT	32
-#define VMX_BASIC_TRUE_CTLS		(1ULL << 55)
-#define VMX_BASIC_64		0x0001000000000000LLU
-#define VMX_BASIC_MEM_TYPE_SHIFT	50
-#define VMX_BASIC_MEM_TYPE_MASK	0x003c000000000000LLU
-#define VMX_BASIC_MEM_TYPE_WB	6LLU
-#define VMX_BASIC_INOUT		0x0040000000000000LLU
-
-/* MSR_IA32_VMX_MISC bits */
-#define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29)
-#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE   0x1F
-/* AMD-V MSRs */
-
-#define MSR_VM_CR                       0xc0010114
-#define MSR_VM_IGNNE                    0xc0010115
-#define MSR_VM_HSAVE_PA                 0xc0010117
-
-#endif /* !SELFTEST_KVM_X86_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
new file mode 100644
index 000000000000..bb76e8db9b2b
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -0,0 +1,1047 @@
+/*
+ * tools/testing/selftests/kvm/include/x86_64/processor.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ */
+
+#ifndef SELFTEST_KVM_PROCESSOR_H
+#define SELFTEST_KVM_PROCESSOR_H
+
+#include <assert.h>
+#include <stdint.h>
+
+#define X86_EFLAGS_FIXED	 (1u << 1)
+
+#define X86_CR4_VME		(1ul << 0)
+#define X86_CR4_PVI		(1ul << 1)
+#define X86_CR4_TSD		(1ul << 2)
+#define X86_CR4_DE		(1ul << 3)
+#define X86_CR4_PSE		(1ul << 4)
+#define X86_CR4_PAE		(1ul << 5)
+#define X86_CR4_MCE		(1ul << 6)
+#define X86_CR4_PGE		(1ul << 7)
+#define X86_CR4_PCE		(1ul << 8)
+#define X86_CR4_OSFXSR		(1ul << 9)
+#define X86_CR4_OSXMMEXCPT	(1ul << 10)
+#define X86_CR4_UMIP		(1ul << 11)
+#define X86_CR4_VMXE		(1ul << 13)
+#define X86_CR4_SMXE		(1ul << 14)
+#define X86_CR4_FSGSBASE	(1ul << 16)
+#define X86_CR4_PCIDE		(1ul << 17)
+#define X86_CR4_OSXSAVE		(1ul << 18)
+#define X86_CR4_SMEP		(1ul << 20)
+#define X86_CR4_SMAP		(1ul << 21)
+#define X86_CR4_PKE		(1ul << 22)
+
+/* The enum values match the intruction encoding of each register */
+enum x86_register {
+	RAX = 0,
+	RCX,
+	RDX,
+	RBX,
+	RSP,
+	RBP,
+	RSI,
+	RDI,
+	R8,
+	R9,
+	R10,
+	R11,
+	R12,
+	R13,
+	R14,
+	R15,
+};
+
+struct desc64 {
+	uint16_t limit0;
+	uint16_t base0;
+	unsigned base1:8, s:1, type:4, dpl:2, p:1;
+	unsigned limit1:4, avl:1, l:1, db:1, g:1, base2:8;
+	uint32_t base3;
+	uint32_t zero1;
+} __attribute__((packed));
+
+struct desc_ptr {
+	uint16_t size;
+	uint64_t address;
+} __attribute__((packed));
+
+static inline uint64_t get_desc64_base(const struct desc64 *desc)
+{
+	return ((uint64_t)desc->base3 << 32) |
+		(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24));
+}
+
+static inline uint64_t rdtsc(void)
+{
+	uint32_t eax, edx;
+
+	/*
+	 * The lfence is to wait (on Intel CPUs) until all previous
+	 * instructions have been executed.
+	 */
+	__asm__ __volatile__("lfence; rdtsc" : "=a"(eax), "=d"(edx));
+	return ((uint64_t)edx) << 32 | eax;
+}
+
+static inline uint64_t rdtscp(uint32_t *aux)
+{
+	uint32_t eax, edx;
+
+	__asm__ __volatile__("rdtscp" : "=a"(eax), "=d"(edx), "=c"(*aux));
+	return ((uint64_t)edx) << 32 | eax;
+}
+
+static inline uint64_t rdmsr(uint32_t msr)
+{
+	uint32_t a, d;
+
+	__asm__ __volatile__("rdmsr" : "=a"(a), "=d"(d) : "c"(msr) : "memory");
+
+	return a | ((uint64_t) d << 32);
+}
+
+static inline void wrmsr(uint32_t msr, uint64_t value)
+{
+	uint32_t a = value;
+	uint32_t d = value >> 32;
+
+	__asm__ __volatile__("wrmsr" :: "a"(a), "d"(d), "c"(msr) : "memory");
+}
+
+
+static inline uint16_t inw(uint16_t port)
+{
+	uint16_t tmp;
+
+	__asm__ __volatile__("in %%dx, %%ax"
+		: /* output */ "=a" (tmp)
+		: /* input */ "d" (port));
+
+	return tmp;
+}
+
+static inline uint16_t get_es(void)
+{
+	uint16_t es;
+
+	__asm__ __volatile__("mov %%es, %[es]"
+			     : /* output */ [es]"=rm"(es));
+	return es;
+}
+
+static inline uint16_t get_cs(void)
+{
+	uint16_t cs;
+
+	__asm__ __volatile__("mov %%cs, %[cs]"
+			     : /* output */ [cs]"=rm"(cs));
+	return cs;
+}
+
+static inline uint16_t get_ss(void)
+{
+	uint16_t ss;
+
+	__asm__ __volatile__("mov %%ss, %[ss]"
+			     : /* output */ [ss]"=rm"(ss));
+	return ss;
+}
+
+static inline uint16_t get_ds(void)
+{
+	uint16_t ds;
+
+	__asm__ __volatile__("mov %%ds, %[ds]"
+			     : /* output */ [ds]"=rm"(ds));
+	return ds;
+}
+
+static inline uint16_t get_fs(void)
+{
+	uint16_t fs;
+
+	__asm__ __volatile__("mov %%fs, %[fs]"
+			     : /* output */ [fs]"=rm"(fs));
+	return fs;
+}
+
+static inline uint16_t get_gs(void)
+{
+	uint16_t gs;
+
+	__asm__ __volatile__("mov %%gs, %[gs]"
+			     : /* output */ [gs]"=rm"(gs));
+	return gs;
+}
+
+static inline uint16_t get_tr(void)
+{
+	uint16_t tr;
+
+	__asm__ __volatile__("str %[tr]"
+			     : /* output */ [tr]"=rm"(tr));
+	return tr;
+}
+
+static inline uint64_t get_cr0(void)
+{
+	uint64_t cr0;
+
+	__asm__ __volatile__("mov %%cr0, %[cr0]"
+			     : /* output */ [cr0]"=r"(cr0));
+	return cr0;
+}
+
+static inline uint64_t get_cr3(void)
+{
+	uint64_t cr3;
+
+	__asm__ __volatile__("mov %%cr3, %[cr3]"
+			     : /* output */ [cr3]"=r"(cr3));
+	return cr3;
+}
+
+static inline uint64_t get_cr4(void)
+{
+	uint64_t cr4;
+
+	__asm__ __volatile__("mov %%cr4, %[cr4]"
+			     : /* output */ [cr4]"=r"(cr4));
+	return cr4;
+}
+
+static inline void set_cr4(uint64_t val)
+{
+	__asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory");
+}
+
+static inline uint64_t get_gdt_base(void)
+{
+	struct desc_ptr gdt;
+	__asm__ __volatile__("sgdt %[gdt]"
+			     : /* output */ [gdt]"=m"(gdt));
+	return gdt.address;
+}
+
+static inline uint64_t get_idt_base(void)
+{
+	struct desc_ptr idt;
+	__asm__ __volatile__("sidt %[idt]"
+			     : /* output */ [idt]"=m"(idt));
+	return idt.address;
+}
+
+#define SET_XMM(__var, __xmm) \
+	asm volatile("movq %0, %%"#__xmm : : "r"(__var) : #__xmm)
+
+static inline void set_xmm(int n, unsigned long val)
+{
+	switch (n) {
+	case 0:
+		SET_XMM(val, xmm0);
+		break;
+	case 1:
+		SET_XMM(val, xmm1);
+		break;
+	case 2:
+		SET_XMM(val, xmm2);
+		break;
+	case 3:
+		SET_XMM(val, xmm3);
+		break;
+	case 4:
+		SET_XMM(val, xmm4);
+		break;
+	case 5:
+		SET_XMM(val, xmm5);
+		break;
+	case 6:
+		SET_XMM(val, xmm6);
+		break;
+	case 7:
+		SET_XMM(val, xmm7);
+		break;
+	}
+}
+
+typedef unsigned long v1di __attribute__ ((vector_size (8)));
+static inline unsigned long get_xmm(int n)
+{
+	assert(n >= 0 && n <= 7);
+
+	register v1di xmm0 __asm__("%xmm0");
+	register v1di xmm1 __asm__("%xmm1");
+	register v1di xmm2 __asm__("%xmm2");
+	register v1di xmm3 __asm__("%xmm3");
+	register v1di xmm4 __asm__("%xmm4");
+	register v1di xmm5 __asm__("%xmm5");
+	register v1di xmm6 __asm__("%xmm6");
+	register v1di xmm7 __asm__("%xmm7");
+	switch (n) {
+	case 0:
+		return (unsigned long)xmm0;
+	case 1:
+		return (unsigned long)xmm1;
+	case 2:
+		return (unsigned long)xmm2;
+	case 3:
+		return (unsigned long)xmm3;
+	case 4:
+		return (unsigned long)xmm4;
+	case 5:
+		return (unsigned long)xmm5;
+	case 6:
+		return (unsigned long)xmm6;
+	case 7:
+		return (unsigned long)xmm7;
+	}
+	return 0;
+}
+
+struct kvm_x86_state;
+struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *state);
+
+/*
+ * Basic CPU control in CR0
+ */
+#define X86_CR0_PE          (1UL<<0) /* Protection Enable */
+#define X86_CR0_MP          (1UL<<1) /* Monitor Coprocessor */
+#define X86_CR0_EM          (1UL<<2) /* Emulation */
+#define X86_CR0_TS          (1UL<<3) /* Task Switched */
+#define X86_CR0_ET          (1UL<<4) /* Extension Type */
+#define X86_CR0_NE          (1UL<<5) /* Numeric Error */
+#define X86_CR0_WP          (1UL<<16) /* Write Protect */
+#define X86_CR0_AM          (1UL<<18) /* Alignment Mask */
+#define X86_CR0_NW          (1UL<<29) /* Not Write-through */
+#define X86_CR0_CD          (1UL<<30) /* Cache Disable */
+#define X86_CR0_PG          (1UL<<31) /* Paging */
+
+/*
+ * CPU model specific register (MSR) numbers.
+ */
+
+/* x86-64 specific MSRs */
+#define MSR_EFER		0xc0000080 /* extended feature register */
+#define MSR_STAR		0xc0000081 /* legacy mode SYSCALL target */
+#define MSR_LSTAR		0xc0000082 /* long mode SYSCALL target */
+#define MSR_CSTAR		0xc0000083 /* compat mode SYSCALL target */
+#define MSR_SYSCALL_MASK	0xc0000084 /* EFLAGS mask for syscall */
+#define MSR_FS_BASE		0xc0000100 /* 64bit FS base */
+#define MSR_GS_BASE		0xc0000101 /* 64bit GS base */
+#define MSR_KERNEL_GS_BASE	0xc0000102 /* SwapGS GS shadow */
+#define MSR_TSC_AUX		0xc0000103 /* Auxiliary TSC */
+
+/* EFER bits: */
+#define EFER_SCE		(1<<0)  /* SYSCALL/SYSRET */
+#define EFER_LME		(1<<8)  /* Long mode enable */
+#define EFER_LMA		(1<<10) /* Long mode active (read-only) */
+#define EFER_NX			(1<<11) /* No execute enable */
+#define EFER_SVME		(1<<12) /* Enable virtualization */
+#define EFER_LMSLE		(1<<13) /* Long Mode Segment Limit Enable */
+#define EFER_FFXSR		(1<<14) /* Enable Fast FXSAVE/FXRSTOR */
+
+/* Intel MSRs. Some also available on other CPUs */
+
+#define MSR_PPIN_CTL			0x0000004e
+#define MSR_PPIN			0x0000004f
+
+#define MSR_IA32_PERFCTR0		0x000000c1
+#define MSR_IA32_PERFCTR1		0x000000c2
+#define MSR_FSB_FREQ			0x000000cd
+#define MSR_PLATFORM_INFO		0x000000ce
+#define MSR_PLATFORM_INFO_CPUID_FAULT_BIT	31
+#define MSR_PLATFORM_INFO_CPUID_FAULT		BIT_ULL(MSR_PLATFORM_INFO_CPUID_FAULT_BIT)
+
+#define MSR_PKG_CST_CONFIG_CONTROL	0x000000e2
+#define NHM_C3_AUTO_DEMOTE		(1UL << 25)
+#define NHM_C1_AUTO_DEMOTE		(1UL << 26)
+#define ATM_LNC_C6_AUTO_DEMOTE		(1UL << 25)
+#define SNB_C1_AUTO_UNDEMOTE		(1UL << 27)
+#define SNB_C3_AUTO_UNDEMOTE		(1UL << 28)
+
+#define MSR_MTRRcap			0x000000fe
+#define MSR_IA32_BBL_CR_CTL		0x00000119
+#define MSR_IA32_BBL_CR_CTL3		0x0000011e
+
+#define MSR_IA32_SYSENTER_CS		0x00000174
+#define MSR_IA32_SYSENTER_ESP		0x00000175
+#define MSR_IA32_SYSENTER_EIP		0x00000176
+
+#define MSR_IA32_MCG_CAP		0x00000179
+#define MSR_IA32_MCG_STATUS		0x0000017a
+#define MSR_IA32_MCG_CTL		0x0000017b
+#define MSR_IA32_MCG_EXT_CTL		0x000004d0
+
+#define MSR_OFFCORE_RSP_0		0x000001a6
+#define MSR_OFFCORE_RSP_1		0x000001a7
+#define MSR_TURBO_RATIO_LIMIT		0x000001ad
+#define MSR_TURBO_RATIO_LIMIT1		0x000001ae
+#define MSR_TURBO_RATIO_LIMIT2		0x000001af
+
+#define MSR_LBR_SELECT			0x000001c8
+#define MSR_LBR_TOS			0x000001c9
+#define MSR_LBR_NHM_FROM		0x00000680
+#define MSR_LBR_NHM_TO			0x000006c0
+#define MSR_LBR_CORE_FROM		0x00000040
+#define MSR_LBR_CORE_TO			0x00000060
+
+#define MSR_LBR_INFO_0			0x00000dc0 /* ... 0xddf for _31 */
+#define LBR_INFO_MISPRED		BIT_ULL(63)
+#define LBR_INFO_IN_TX			BIT_ULL(62)
+#define LBR_INFO_ABORT			BIT_ULL(61)
+#define LBR_INFO_CYCLES			0xffff
+
+#define MSR_IA32_PEBS_ENABLE		0x000003f1
+#define MSR_IA32_DS_AREA		0x00000600
+#define MSR_IA32_PERF_CAPABILITIES	0x00000345
+#define MSR_PEBS_LD_LAT_THRESHOLD	0x000003f6
+
+#define MSR_IA32_RTIT_CTL		0x00000570
+#define MSR_IA32_RTIT_STATUS		0x00000571
+#define MSR_IA32_RTIT_ADDR0_A		0x00000580
+#define MSR_IA32_RTIT_ADDR0_B		0x00000581
+#define MSR_IA32_RTIT_ADDR1_A		0x00000582
+#define MSR_IA32_RTIT_ADDR1_B		0x00000583
+#define MSR_IA32_RTIT_ADDR2_A		0x00000584
+#define MSR_IA32_RTIT_ADDR2_B		0x00000585
+#define MSR_IA32_RTIT_ADDR3_A		0x00000586
+#define MSR_IA32_RTIT_ADDR3_B		0x00000587
+#define MSR_IA32_RTIT_CR3_MATCH		0x00000572
+#define MSR_IA32_RTIT_OUTPUT_BASE	0x00000560
+#define MSR_IA32_RTIT_OUTPUT_MASK	0x00000561
+
+#define MSR_MTRRfix64K_00000		0x00000250
+#define MSR_MTRRfix16K_80000		0x00000258
+#define MSR_MTRRfix16K_A0000		0x00000259
+#define MSR_MTRRfix4K_C0000		0x00000268
+#define MSR_MTRRfix4K_C8000		0x00000269
+#define MSR_MTRRfix4K_D0000		0x0000026a
+#define MSR_MTRRfix4K_D8000		0x0000026b
+#define MSR_MTRRfix4K_E0000		0x0000026c
+#define MSR_MTRRfix4K_E8000		0x0000026d
+#define MSR_MTRRfix4K_F0000		0x0000026e
+#define MSR_MTRRfix4K_F8000		0x0000026f
+#define MSR_MTRRdefType			0x000002ff
+
+#define MSR_IA32_CR_PAT			0x00000277
+
+#define MSR_IA32_DEBUGCTLMSR		0x000001d9
+#define MSR_IA32_LASTBRANCHFROMIP	0x000001db
+#define MSR_IA32_LASTBRANCHTOIP		0x000001dc
+#define MSR_IA32_LASTINTFROMIP		0x000001dd
+#define MSR_IA32_LASTINTTOIP		0x000001de
+
+/* DEBUGCTLMSR bits (others vary by model): */
+#define DEBUGCTLMSR_LBR			(1UL <<  0) /* last branch recording */
+#define DEBUGCTLMSR_BTF_SHIFT		1
+#define DEBUGCTLMSR_BTF			(1UL <<  1) /* single-step on branches */
+#define DEBUGCTLMSR_TR			(1UL <<  6)
+#define DEBUGCTLMSR_BTS			(1UL <<  7)
+#define DEBUGCTLMSR_BTINT		(1UL <<  8)
+#define DEBUGCTLMSR_BTS_OFF_OS		(1UL <<  9)
+#define DEBUGCTLMSR_BTS_OFF_USR		(1UL << 10)
+#define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI	(1UL << 11)
+#define DEBUGCTLMSR_FREEZE_IN_SMM_BIT	14
+#define DEBUGCTLMSR_FREEZE_IN_SMM	(1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT)
+
+#define MSR_PEBS_FRONTEND		0x000003f7
+
+#define MSR_IA32_POWER_CTL		0x000001fc
+
+#define MSR_IA32_MC0_CTL		0x00000400
+#define MSR_IA32_MC0_STATUS		0x00000401
+#define MSR_IA32_MC0_ADDR		0x00000402
+#define MSR_IA32_MC0_MISC		0x00000403
+
+/* C-state Residency Counters */
+#define MSR_PKG_C3_RESIDENCY		0x000003f8
+#define MSR_PKG_C6_RESIDENCY		0x000003f9
+#define MSR_ATOM_PKG_C6_RESIDENCY	0x000003fa
+#define MSR_PKG_C7_RESIDENCY		0x000003fa
+#define MSR_CORE_C3_RESIDENCY		0x000003fc
+#define MSR_CORE_C6_RESIDENCY		0x000003fd
+#define MSR_CORE_C7_RESIDENCY		0x000003fe
+#define MSR_KNL_CORE_C6_RESIDENCY	0x000003ff
+#define MSR_PKG_C2_RESIDENCY		0x0000060d
+#define MSR_PKG_C8_RESIDENCY		0x00000630
+#define MSR_PKG_C9_RESIDENCY		0x00000631
+#define MSR_PKG_C10_RESIDENCY		0x00000632
+
+/* Interrupt Response Limit */
+#define MSR_PKGC3_IRTL			0x0000060a
+#define MSR_PKGC6_IRTL			0x0000060b
+#define MSR_PKGC7_IRTL			0x0000060c
+#define MSR_PKGC8_IRTL			0x00000633
+#define MSR_PKGC9_IRTL			0x00000634
+#define MSR_PKGC10_IRTL			0x00000635
+
+/* Run Time Average Power Limiting (RAPL) Interface */
+
+#define MSR_RAPL_POWER_UNIT		0x00000606
+
+#define MSR_PKG_POWER_LIMIT		0x00000610
+#define MSR_PKG_ENERGY_STATUS		0x00000611
+#define MSR_PKG_PERF_STATUS		0x00000613
+#define MSR_PKG_POWER_INFO		0x00000614
+
+#define MSR_DRAM_POWER_LIMIT		0x00000618
+#define MSR_DRAM_ENERGY_STATUS		0x00000619
+#define MSR_DRAM_PERF_STATUS		0x0000061b
+#define MSR_DRAM_POWER_INFO		0x0000061c
+
+#define MSR_PP0_POWER_LIMIT		0x00000638
+#define MSR_PP0_ENERGY_STATUS		0x00000639
+#define MSR_PP0_POLICY			0x0000063a
+#define MSR_PP0_PERF_STATUS		0x0000063b
+
+#define MSR_PP1_POWER_LIMIT		0x00000640
+#define MSR_PP1_ENERGY_STATUS		0x00000641
+#define MSR_PP1_POLICY			0x00000642
+
+/* Config TDP MSRs */
+#define MSR_CONFIG_TDP_NOMINAL		0x00000648
+#define MSR_CONFIG_TDP_LEVEL_1		0x00000649
+#define MSR_CONFIG_TDP_LEVEL_2		0x0000064A
+#define MSR_CONFIG_TDP_CONTROL		0x0000064B
+#define MSR_TURBO_ACTIVATION_RATIO	0x0000064C
+
+#define MSR_PLATFORM_ENERGY_STATUS	0x0000064D
+
+#define MSR_PKG_WEIGHTED_CORE_C0_RES	0x00000658
+#define MSR_PKG_ANY_CORE_C0_RES		0x00000659
+#define MSR_PKG_ANY_GFXE_C0_RES		0x0000065A
+#define MSR_PKG_BOTH_CORE_GFXE_C0_RES	0x0000065B
+
+#define MSR_CORE_C1_RES			0x00000660
+#define MSR_MODULE_C6_RES_MS		0x00000664
+
+#define MSR_CC6_DEMOTION_POLICY_CONFIG	0x00000668
+#define MSR_MC6_DEMOTION_POLICY_CONFIG	0x00000669
+
+#define MSR_ATOM_CORE_RATIOS		0x0000066a
+#define MSR_ATOM_CORE_VIDS		0x0000066b
+#define MSR_ATOM_CORE_TURBO_RATIOS	0x0000066c
+#define MSR_ATOM_CORE_TURBO_VIDS	0x0000066d
+
+
+#define MSR_CORE_PERF_LIMIT_REASONS	0x00000690
+#define MSR_GFX_PERF_LIMIT_REASONS	0x000006B0
+#define MSR_RING_PERF_LIMIT_REASONS	0x000006B1
+
+/* Hardware P state interface */
+#define MSR_PPERF			0x0000064e
+#define MSR_PERF_LIMIT_REASONS		0x0000064f
+#define MSR_PM_ENABLE			0x00000770
+#define MSR_HWP_CAPABILITIES		0x00000771
+#define MSR_HWP_REQUEST_PKG		0x00000772
+#define MSR_HWP_INTERRUPT		0x00000773
+#define MSR_HWP_REQUEST			0x00000774
+#define MSR_HWP_STATUS			0x00000777
+
+/* CPUID.6.EAX */
+#define HWP_BASE_BIT			(1<<7)
+#define HWP_NOTIFICATIONS_BIT		(1<<8)
+#define HWP_ACTIVITY_WINDOW_BIT		(1<<9)
+#define HWP_ENERGY_PERF_PREFERENCE_BIT	(1<<10)
+#define HWP_PACKAGE_LEVEL_REQUEST_BIT	(1<<11)
+
+/* IA32_HWP_CAPABILITIES */
+#define HWP_HIGHEST_PERF(x)		(((x) >> 0) & 0xff)
+#define HWP_GUARANTEED_PERF(x)		(((x) >> 8) & 0xff)
+#define HWP_MOSTEFFICIENT_PERF(x)	(((x) >> 16) & 0xff)
+#define HWP_LOWEST_PERF(x)		(((x) >> 24) & 0xff)
+
+/* IA32_HWP_REQUEST */
+#define HWP_MIN_PERF(x)			(x & 0xff)
+#define HWP_MAX_PERF(x)			((x & 0xff) << 8)
+#define HWP_DESIRED_PERF(x)		((x & 0xff) << 16)
+#define HWP_ENERGY_PERF_PREFERENCE(x)	(((unsigned long long) x & 0xff) << 24)
+#define HWP_EPP_PERFORMANCE		0x00
+#define HWP_EPP_BALANCE_PERFORMANCE	0x80
+#define HWP_EPP_BALANCE_POWERSAVE	0xC0
+#define HWP_EPP_POWERSAVE		0xFF
+#define HWP_ACTIVITY_WINDOW(x)		((unsigned long long)(x & 0xff3) << 32)
+#define HWP_PACKAGE_CONTROL(x)		((unsigned long long)(x & 0x1) << 42)
+
+/* IA32_HWP_STATUS */
+#define HWP_GUARANTEED_CHANGE(x)	(x & 0x1)
+#define HWP_EXCURSION_TO_MINIMUM(x)	(x & 0x4)
+
+/* IA32_HWP_INTERRUPT */
+#define HWP_CHANGE_TO_GUARANTEED_INT(x)	(x & 0x1)
+#define HWP_EXCURSION_TO_MINIMUM_INT(x)	(x & 0x2)
+
+#define MSR_AMD64_MC0_MASK		0xc0010044
+
+#define MSR_IA32_MCx_CTL(x)		(MSR_IA32_MC0_CTL + 4*(x))
+#define MSR_IA32_MCx_STATUS(x)		(MSR_IA32_MC0_STATUS + 4*(x))
+#define MSR_IA32_MCx_ADDR(x)		(MSR_IA32_MC0_ADDR + 4*(x))
+#define MSR_IA32_MCx_MISC(x)		(MSR_IA32_MC0_MISC + 4*(x))
+
+#define MSR_AMD64_MCx_MASK(x)		(MSR_AMD64_MC0_MASK + (x))
+
+/* These are consecutive and not in the normal 4er MCE bank block */
+#define MSR_IA32_MC0_CTL2		0x00000280
+#define MSR_IA32_MCx_CTL2(x)		(MSR_IA32_MC0_CTL2 + (x))
+
+#define MSR_P6_PERFCTR0			0x000000c1
+#define MSR_P6_PERFCTR1			0x000000c2
+#define MSR_P6_EVNTSEL0			0x00000186
+#define MSR_P6_EVNTSEL1			0x00000187
+
+#define MSR_KNC_PERFCTR0               0x00000020
+#define MSR_KNC_PERFCTR1               0x00000021
+#define MSR_KNC_EVNTSEL0               0x00000028
+#define MSR_KNC_EVNTSEL1               0x00000029
+
+/* Alternative perfctr range with full access. */
+#define MSR_IA32_PMC0			0x000004c1
+
+/* AMD64 MSRs. Not complete. See the architecture manual for a more
+   complete list. */
+
+#define MSR_AMD64_PATCH_LEVEL		0x0000008b
+#define MSR_AMD64_TSC_RATIO		0xc0000104
+#define MSR_AMD64_NB_CFG		0xc001001f
+#define MSR_AMD64_PATCH_LOADER		0xc0010020
+#define MSR_AMD64_OSVW_ID_LENGTH	0xc0010140
+#define MSR_AMD64_OSVW_STATUS		0xc0010141
+#define MSR_AMD64_LS_CFG		0xc0011020
+#define MSR_AMD64_DC_CFG		0xc0011022
+#define MSR_AMD64_BU_CFG2		0xc001102a
+#define MSR_AMD64_IBSFETCHCTL		0xc0011030
+#define MSR_AMD64_IBSFETCHLINAD		0xc0011031
+#define MSR_AMD64_IBSFETCHPHYSAD	0xc0011032
+#define MSR_AMD64_IBSFETCH_REG_COUNT	3
+#define MSR_AMD64_IBSFETCH_REG_MASK	((1UL<<MSR_AMD64_IBSFETCH_REG_COUNT)-1)
+#define MSR_AMD64_IBSOPCTL		0xc0011033
+#define MSR_AMD64_IBSOPRIP		0xc0011034
+#define MSR_AMD64_IBSOPDATA		0xc0011035
+#define MSR_AMD64_IBSOPDATA2		0xc0011036
+#define MSR_AMD64_IBSOPDATA3		0xc0011037
+#define MSR_AMD64_IBSDCLINAD		0xc0011038
+#define MSR_AMD64_IBSDCPHYSAD		0xc0011039
+#define MSR_AMD64_IBSOP_REG_COUNT	7
+#define MSR_AMD64_IBSOP_REG_MASK	((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1)
+#define MSR_AMD64_IBSCTL		0xc001103a
+#define MSR_AMD64_IBSBRTARGET		0xc001103b
+#define MSR_AMD64_IBSOPDATA4		0xc001103d
+#define MSR_AMD64_IBS_REG_COUNT_MAX	8 /* includes MSR_AMD64_IBSBRTARGET */
+#define MSR_AMD64_SEV			0xc0010131
+#define MSR_AMD64_SEV_ENABLED_BIT	0
+#define MSR_AMD64_SEV_ENABLED		BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
+
+/* Fam 17h MSRs */
+#define MSR_F17H_IRPERF			0xc00000e9
+
+/* Fam 16h MSRs */
+#define MSR_F16H_L2I_PERF_CTL		0xc0010230
+#define MSR_F16H_L2I_PERF_CTR		0xc0010231
+#define MSR_F16H_DR1_ADDR_MASK		0xc0011019
+#define MSR_F16H_DR2_ADDR_MASK		0xc001101a
+#define MSR_F16H_DR3_ADDR_MASK		0xc001101b
+#define MSR_F16H_DR0_ADDR_MASK		0xc0011027
+
+/* Fam 15h MSRs */
+#define MSR_F15H_PERF_CTL		0xc0010200
+#define MSR_F15H_PERF_CTR		0xc0010201
+#define MSR_F15H_NB_PERF_CTL		0xc0010240
+#define MSR_F15H_NB_PERF_CTR		0xc0010241
+#define MSR_F15H_PTSC			0xc0010280
+#define MSR_F15H_IC_CFG			0xc0011021
+
+/* Fam 10h MSRs */
+#define MSR_FAM10H_MMIO_CONF_BASE	0xc0010058
+#define FAM10H_MMIO_CONF_ENABLE		(1<<0)
+#define FAM10H_MMIO_CONF_BUSRANGE_MASK	0xf
+#define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2
+#define FAM10H_MMIO_CONF_BASE_MASK	0xfffffffULL
+#define FAM10H_MMIO_CONF_BASE_SHIFT	20
+#define MSR_FAM10H_NODE_ID		0xc001100c
+#define MSR_F10H_DECFG			0xc0011029
+#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT	1
+#define MSR_F10H_DECFG_LFENCE_SERIALIZE		BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT)
+
+/* K8 MSRs */
+#define MSR_K8_TOP_MEM1			0xc001001a
+#define MSR_K8_TOP_MEM2			0xc001001d
+#define MSR_K8_SYSCFG			0xc0010010
+#define MSR_K8_SYSCFG_MEM_ENCRYPT_BIT	23
+#define MSR_K8_SYSCFG_MEM_ENCRYPT	BIT_ULL(MSR_K8_SYSCFG_MEM_ENCRYPT_BIT)
+#define MSR_K8_INT_PENDING_MSG		0xc0010055
+/* C1E active bits in int pending message */
+#define K8_INTP_C1E_ACTIVE_MASK		0x18000000
+#define MSR_K8_TSEG_ADDR		0xc0010112
+#define MSR_K8_TSEG_MASK		0xc0010113
+#define K8_MTRRFIXRANGE_DRAM_ENABLE	0x00040000 /* MtrrFixDramEn bit    */
+#define K8_MTRRFIXRANGE_DRAM_MODIFY	0x00080000 /* MtrrFixDramModEn bit */
+#define K8_MTRR_RDMEM_WRMEM_MASK	0x18181818 /* Mask: RdMem|WrMem    */
+
+/* K7 MSRs */
+#define MSR_K7_EVNTSEL0			0xc0010000
+#define MSR_K7_PERFCTR0			0xc0010004
+#define MSR_K7_EVNTSEL1			0xc0010001
+#define MSR_K7_PERFCTR1			0xc0010005
+#define MSR_K7_EVNTSEL2			0xc0010002
+#define MSR_K7_PERFCTR2			0xc0010006
+#define MSR_K7_EVNTSEL3			0xc0010003
+#define MSR_K7_PERFCTR3			0xc0010007
+#define MSR_K7_CLK_CTL			0xc001001b
+#define MSR_K7_HWCR			0xc0010015
+#define MSR_K7_HWCR_SMMLOCK_BIT		0
+#define MSR_K7_HWCR_SMMLOCK		BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
+#define MSR_K7_FID_VID_CTL		0xc0010041
+#define MSR_K7_FID_VID_STATUS		0xc0010042
+
+/* K6 MSRs */
+#define MSR_K6_WHCR			0xc0000082
+#define MSR_K6_UWCCR			0xc0000085
+#define MSR_K6_EPMR			0xc0000086
+#define MSR_K6_PSOR			0xc0000087
+#define MSR_K6_PFIR			0xc0000088
+
+/* Centaur-Hauls/IDT defined MSRs. */
+#define MSR_IDT_FCR1			0x00000107
+#define MSR_IDT_FCR2			0x00000108
+#define MSR_IDT_FCR3			0x00000109
+#define MSR_IDT_FCR4			0x0000010a
+
+#define MSR_IDT_MCR0			0x00000110
+#define MSR_IDT_MCR1			0x00000111
+#define MSR_IDT_MCR2			0x00000112
+#define MSR_IDT_MCR3			0x00000113
+#define MSR_IDT_MCR4			0x00000114
+#define MSR_IDT_MCR5			0x00000115
+#define MSR_IDT_MCR6			0x00000116
+#define MSR_IDT_MCR7			0x00000117
+#define MSR_IDT_MCR_CTRL		0x00000120
+
+/* VIA Cyrix defined MSRs*/
+#define MSR_VIA_FCR			0x00001107
+#define MSR_VIA_LONGHAUL		0x0000110a
+#define MSR_VIA_RNG			0x0000110b
+#define MSR_VIA_BCR2			0x00001147
+
+/* Transmeta defined MSRs */
+#define MSR_TMTA_LONGRUN_CTRL		0x80868010
+#define MSR_TMTA_LONGRUN_FLAGS		0x80868011
+#define MSR_TMTA_LRTI_READOUT		0x80868018
+#define MSR_TMTA_LRTI_VOLT_MHZ		0x8086801a
+
+/* Intel defined MSRs. */
+#define MSR_IA32_P5_MC_ADDR		0x00000000
+#define MSR_IA32_P5_MC_TYPE		0x00000001
+#define MSR_IA32_TSC			0x00000010
+#define MSR_IA32_PLATFORM_ID		0x00000017
+#define MSR_IA32_EBL_CR_POWERON		0x0000002a
+#define MSR_EBC_FREQUENCY_ID		0x0000002c
+#define MSR_SMI_COUNT			0x00000034
+#define MSR_IA32_FEATURE_CONTROL        0x0000003a
+#define MSR_IA32_TSC_ADJUST             0x0000003b
+#define MSR_IA32_BNDCFGS		0x00000d90
+
+#define MSR_IA32_BNDCFGS_RSVD		0x00000ffc
+
+#define MSR_IA32_XSS			0x00000da0
+
+#define FEATURE_CONTROL_LOCKED				(1<<0)
+#define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX	(1<<1)
+#define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX	(1<<2)
+#define FEATURE_CONTROL_LMCE				(1<<20)
+
+#define MSR_IA32_APICBASE		0x0000001b
+#define MSR_IA32_APICBASE_BSP		(1<<8)
+#define MSR_IA32_APICBASE_ENABLE	(1<<11)
+#define MSR_IA32_APICBASE_BASE		(0xfffff<<12)
+
+#define MSR_IA32_TSCDEADLINE		0x000006e0
+
+#define MSR_IA32_UCODE_WRITE		0x00000079
+#define MSR_IA32_UCODE_REV		0x0000008b
+
+#define MSR_IA32_SMM_MONITOR_CTL	0x0000009b
+#define MSR_IA32_SMBASE			0x0000009e
+
+#define MSR_IA32_PERF_STATUS		0x00000198
+#define MSR_IA32_PERF_CTL		0x00000199
+#define INTEL_PERF_CTL_MASK		0xffff
+#define MSR_AMD_PSTATE_DEF_BASE		0xc0010064
+#define MSR_AMD_PERF_STATUS		0xc0010063
+#define MSR_AMD_PERF_CTL		0xc0010062
+
+#define MSR_IA32_MPERF			0x000000e7
+#define MSR_IA32_APERF			0x000000e8
+
+#define MSR_IA32_THERM_CONTROL		0x0000019a
+#define MSR_IA32_THERM_INTERRUPT	0x0000019b
+
+#define THERM_INT_HIGH_ENABLE		(1 << 0)
+#define THERM_INT_LOW_ENABLE		(1 << 1)
+#define THERM_INT_PLN_ENABLE		(1 << 24)
+
+#define MSR_IA32_THERM_STATUS		0x0000019c
+
+#define THERM_STATUS_PROCHOT		(1 << 0)
+#define THERM_STATUS_POWER_LIMIT	(1 << 10)
+
+#define MSR_THERM2_CTL			0x0000019d
+
+#define MSR_THERM2_CTL_TM_SELECT	(1ULL << 16)
+
+#define MSR_IA32_MISC_ENABLE		0x000001a0
+
+#define MSR_IA32_TEMPERATURE_TARGET	0x000001a2
+
+#define MSR_MISC_FEATURE_CONTROL	0x000001a4
+#define MSR_MISC_PWR_MGMT		0x000001aa
+
+#define MSR_IA32_ENERGY_PERF_BIAS	0x000001b0
+#define ENERGY_PERF_BIAS_PERFORMANCE		0
+#define ENERGY_PERF_BIAS_BALANCE_PERFORMANCE	4
+#define ENERGY_PERF_BIAS_NORMAL			6
+#define ENERGY_PERF_BIAS_BALANCE_POWERSAVE	8
+#define ENERGY_PERF_BIAS_POWERSAVE		15
+
+#define MSR_IA32_PACKAGE_THERM_STATUS		0x000001b1
+
+#define PACKAGE_THERM_STATUS_PROCHOT		(1 << 0)
+#define PACKAGE_THERM_STATUS_POWER_LIMIT	(1 << 10)
+
+#define MSR_IA32_PACKAGE_THERM_INTERRUPT	0x000001b2
+
+#define PACKAGE_THERM_INT_HIGH_ENABLE		(1 << 0)
+#define PACKAGE_THERM_INT_LOW_ENABLE		(1 << 1)
+#define PACKAGE_THERM_INT_PLN_ENABLE		(1 << 24)
+
+/* Thermal Thresholds Support */
+#define THERM_INT_THRESHOLD0_ENABLE    (1 << 15)
+#define THERM_SHIFT_THRESHOLD0        8
+#define THERM_MASK_THRESHOLD0          (0x7f << THERM_SHIFT_THRESHOLD0)
+#define THERM_INT_THRESHOLD1_ENABLE    (1 << 23)
+#define THERM_SHIFT_THRESHOLD1        16
+#define THERM_MASK_THRESHOLD1          (0x7f << THERM_SHIFT_THRESHOLD1)
+#define THERM_STATUS_THRESHOLD0        (1 << 6)
+#define THERM_LOG_THRESHOLD0           (1 << 7)
+#define THERM_STATUS_THRESHOLD1        (1 << 8)
+#define THERM_LOG_THRESHOLD1           (1 << 9)
+
+/* MISC_ENABLE bits: architectural */
+#define MSR_IA32_MISC_ENABLE_FAST_STRING_BIT		0
+#define MSR_IA32_MISC_ENABLE_FAST_STRING		(1ULL << MSR_IA32_MISC_ENABLE_FAST_STRING_BIT)
+#define MSR_IA32_MISC_ENABLE_TCC_BIT			1
+#define MSR_IA32_MISC_ENABLE_TCC			(1ULL << MSR_IA32_MISC_ENABLE_TCC_BIT)
+#define MSR_IA32_MISC_ENABLE_EMON_BIT			7
+#define MSR_IA32_MISC_ENABLE_EMON			(1ULL << MSR_IA32_MISC_ENABLE_EMON_BIT)
+#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT		11
+#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL		(1ULL << MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT)
+#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT		12
+#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL		(1ULL << MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT)
+#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT	16
+#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP		(1ULL << MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT)
+#define MSR_IA32_MISC_ENABLE_MWAIT_BIT			18
+#define MSR_IA32_MISC_ENABLE_MWAIT			(1ULL << MSR_IA32_MISC_ENABLE_MWAIT_BIT)
+#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT		22
+#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID		(1ULL << MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT)
+#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT		23
+#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT		34
+#define MSR_IA32_MISC_ENABLE_XD_DISABLE			(1ULL << MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT)
+
+/* MISC_ENABLE bits: model-specific, meaning may vary from core to core */
+#define MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT		2
+#define MSR_IA32_MISC_ENABLE_X87_COMPAT			(1ULL << MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT)
+#define MSR_IA32_MISC_ENABLE_TM1_BIT			3
+#define MSR_IA32_MISC_ENABLE_TM1			(1ULL << MSR_IA32_MISC_ENABLE_TM1_BIT)
+#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT	4
+#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT	6
+#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT		8
+#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK		(1ULL << MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT)
+#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT	9
+#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_FERR_BIT			10
+#define MSR_IA32_MISC_ENABLE_FERR			(1ULL << MSR_IA32_MISC_ENABLE_FERR_BIT)
+#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT		10
+#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX		(1ULL << MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT)
+#define MSR_IA32_MISC_ENABLE_TM2_BIT			13
+#define MSR_IA32_MISC_ENABLE_TM2			(1ULL << MSR_IA32_MISC_ENABLE_TM2_BIT)
+#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT	19
+#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT		20
+#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK		(1ULL << MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT)
+#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT		24
+#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT		(1ULL << MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT)
+#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT	37
+#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT		38
+#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT	39
+#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT)
+
+/* MISC_FEATURES_ENABLES non-architectural features */
+#define MSR_MISC_FEATURES_ENABLES	0x00000140
+
+#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT	0
+#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT		BIT_ULL(MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT)
+#define MSR_MISC_FEATURES_ENABLES_RING3MWAIT_BIT	1
+
+#define MSR_IA32_TSC_DEADLINE		0x000006E0
+
+/* P4/Xeon+ specific */
+#define MSR_IA32_MCG_EAX		0x00000180
+#define MSR_IA32_MCG_EBX		0x00000181
+#define MSR_IA32_MCG_ECX		0x00000182
+#define MSR_IA32_MCG_EDX		0x00000183
+#define MSR_IA32_MCG_ESI		0x00000184
+#define MSR_IA32_MCG_EDI		0x00000185
+#define MSR_IA32_MCG_EBP		0x00000186
+#define MSR_IA32_MCG_ESP		0x00000187
+#define MSR_IA32_MCG_EFLAGS		0x00000188
+#define MSR_IA32_MCG_EIP		0x00000189
+#define MSR_IA32_MCG_RESERVED		0x0000018a
+
+/* Pentium IV performance counter MSRs */
+#define MSR_P4_BPU_PERFCTR0		0x00000300
+#define MSR_P4_BPU_PERFCTR1		0x00000301
+#define MSR_P4_BPU_PERFCTR2		0x00000302
+#define MSR_P4_BPU_PERFCTR3		0x00000303
+#define MSR_P4_MS_PERFCTR0		0x00000304
+#define MSR_P4_MS_PERFCTR1		0x00000305
+#define MSR_P4_MS_PERFCTR2		0x00000306
+#define MSR_P4_MS_PERFCTR3		0x00000307
+#define MSR_P4_FLAME_PERFCTR0		0x00000308
+#define MSR_P4_FLAME_PERFCTR1		0x00000309
+#define MSR_P4_FLAME_PERFCTR2		0x0000030a
+#define MSR_P4_FLAME_PERFCTR3		0x0000030b
+#define MSR_P4_IQ_PERFCTR0		0x0000030c
+#define MSR_P4_IQ_PERFCTR1		0x0000030d
+#define MSR_P4_IQ_PERFCTR2		0x0000030e
+#define MSR_P4_IQ_PERFCTR3		0x0000030f
+#define MSR_P4_IQ_PERFCTR4		0x00000310
+#define MSR_P4_IQ_PERFCTR5		0x00000311
+#define MSR_P4_BPU_CCCR0		0x00000360
+#define MSR_P4_BPU_CCCR1		0x00000361
+#define MSR_P4_BPU_CCCR2		0x00000362
+#define MSR_P4_BPU_CCCR3		0x00000363
+#define MSR_P4_MS_CCCR0			0x00000364
+#define MSR_P4_MS_CCCR1			0x00000365
+#define MSR_P4_MS_CCCR2			0x00000366
+#define MSR_P4_MS_CCCR3			0x00000367
+#define MSR_P4_FLAME_CCCR0		0x00000368
+#define MSR_P4_FLAME_CCCR1		0x00000369
+#define MSR_P4_FLAME_CCCR2		0x0000036a
+#define MSR_P4_FLAME_CCCR3		0x0000036b
+#define MSR_P4_IQ_CCCR0			0x0000036c
+#define MSR_P4_IQ_CCCR1			0x0000036d
+#define MSR_P4_IQ_CCCR2			0x0000036e
+#define MSR_P4_IQ_CCCR3			0x0000036f
+#define MSR_P4_IQ_CCCR4			0x00000370
+#define MSR_P4_IQ_CCCR5			0x00000371
+#define MSR_P4_ALF_ESCR0		0x000003ca
+#define MSR_P4_ALF_ESCR1		0x000003cb
+#define MSR_P4_BPU_ESCR0		0x000003b2
+#define MSR_P4_BPU_ESCR1		0x000003b3
+#define MSR_P4_BSU_ESCR0		0x000003a0
+#define MSR_P4_BSU_ESCR1		0x000003a1
+#define MSR_P4_CRU_ESCR0		0x000003b8
+#define MSR_P4_CRU_ESCR1		0x000003b9
+#define MSR_P4_CRU_ESCR2		0x000003cc
+#define MSR_P4_CRU_ESCR3		0x000003cd
+#define MSR_P4_CRU_ESCR4		0x000003e0
+#define MSR_P4_CRU_ESCR5		0x000003e1
+#define MSR_P4_DAC_ESCR0		0x000003a8
+#define MSR_P4_DAC_ESCR1		0x000003a9
+#define MSR_P4_FIRM_ESCR0		0x000003a4
+#define MSR_P4_FIRM_ESCR1		0x000003a5
+#define MSR_P4_FLAME_ESCR0		0x000003a6
+#define MSR_P4_FLAME_ESCR1		0x000003a7
+#define MSR_P4_FSB_ESCR0		0x000003a2
+#define MSR_P4_FSB_ESCR1		0x000003a3
+#define MSR_P4_IQ_ESCR0			0x000003ba
+#define MSR_P4_IQ_ESCR1			0x000003bb
+#define MSR_P4_IS_ESCR0			0x000003b4
+#define MSR_P4_IS_ESCR1			0x000003b5
+#define MSR_P4_ITLB_ESCR0		0x000003b6
+#define MSR_P4_ITLB_ESCR1		0x000003b7
+#define MSR_P4_IX_ESCR0			0x000003c8
+#define MSR_P4_IX_ESCR1			0x000003c9
+#define MSR_P4_MOB_ESCR0		0x000003aa
+#define MSR_P4_MOB_ESCR1		0x000003ab
+#define MSR_P4_MS_ESCR0			0x000003c0
+#define MSR_P4_MS_ESCR1			0x000003c1
+#define MSR_P4_PMH_ESCR0		0x000003ac
+#define MSR_P4_PMH_ESCR1		0x000003ad
+#define MSR_P4_RAT_ESCR0		0x000003bc
+#define MSR_P4_RAT_ESCR1		0x000003bd
+#define MSR_P4_SAAT_ESCR0		0x000003ae
+#define MSR_P4_SAAT_ESCR1		0x000003af
+#define MSR_P4_SSU_ESCR0		0x000003be
+#define MSR_P4_SSU_ESCR1		0x000003bf /* guess: not in manual */
+
+#define MSR_P4_TBPU_ESCR0		0x000003c2
+#define MSR_P4_TBPU_ESCR1		0x000003c3
+#define MSR_P4_TC_ESCR0			0x000003c4
+#define MSR_P4_TC_ESCR1			0x000003c5
+#define MSR_P4_U2L_ESCR0		0x000003b0
+#define MSR_P4_U2L_ESCR1		0x000003b1
+
+#define MSR_P4_PEBS_MATRIX_VERT		0x000003f2
+
+/* Intel Core-based CPU performance counters */
+#define MSR_CORE_PERF_FIXED_CTR0	0x00000309
+#define MSR_CORE_PERF_FIXED_CTR1	0x0000030a
+#define MSR_CORE_PERF_FIXED_CTR2	0x0000030b
+#define MSR_CORE_PERF_FIXED_CTR_CTRL	0x0000038d
+#define MSR_CORE_PERF_GLOBAL_STATUS	0x0000038e
+#define MSR_CORE_PERF_GLOBAL_CTRL	0x0000038f
+#define MSR_CORE_PERF_GLOBAL_OVF_CTRL	0x00000390
+
+/* Geode defined MSRs */
+#define MSR_GEODE_BUSCONT_CONF0		0x00001900
+
+/* Intel VT MSRs */
+#define MSR_IA32_VMX_BASIC              0x00000480
+#define MSR_IA32_VMX_PINBASED_CTLS      0x00000481
+#define MSR_IA32_VMX_PROCBASED_CTLS     0x00000482
+#define MSR_IA32_VMX_EXIT_CTLS          0x00000483
+#define MSR_IA32_VMX_ENTRY_CTLS         0x00000484
+#define MSR_IA32_VMX_MISC               0x00000485
+#define MSR_IA32_VMX_CR0_FIXED0         0x00000486
+#define MSR_IA32_VMX_CR0_FIXED1         0x00000487
+#define MSR_IA32_VMX_CR4_FIXED0         0x00000488
+#define MSR_IA32_VMX_CR4_FIXED1         0x00000489
+#define MSR_IA32_VMX_VMCS_ENUM          0x0000048a
+#define MSR_IA32_VMX_PROCBASED_CTLS2    0x0000048b
+#define MSR_IA32_VMX_EPT_VPID_CAP       0x0000048c
+#define MSR_IA32_VMX_TRUE_PINBASED_CTLS  0x0000048d
+#define MSR_IA32_VMX_TRUE_PROCBASED_CTLS 0x0000048e
+#define MSR_IA32_VMX_TRUE_EXIT_CTLS      0x0000048f
+#define MSR_IA32_VMX_TRUE_ENTRY_CTLS     0x00000490
+#define MSR_IA32_VMX_VMFUNC             0x00000491
+
+/* VMX_BASIC bits and bitmasks */
+#define VMX_BASIC_VMCS_SIZE_SHIFT	32
+#define VMX_BASIC_TRUE_CTLS		(1ULL << 55)
+#define VMX_BASIC_64		0x0001000000000000LLU
+#define VMX_BASIC_MEM_TYPE_SHIFT	50
+#define VMX_BASIC_MEM_TYPE_MASK	0x003c000000000000LLU
+#define VMX_BASIC_MEM_TYPE_WB	6LLU
+#define VMX_BASIC_INOUT		0x0040000000000000LLU
+
+/* MSR_IA32_VMX_MISC bits */
+#define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29)
+#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE   0x1F
+/* AMD-V MSRs */
+
+#define MSR_VM_CR                       0xc0010114
+#define MSR_VM_IGNNE                    0xc0010115
+#define MSR_VM_HSAVE_PA                 0xc0010117
+
+#endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
new file mode 100644
index 000000000000..12ebd836f7ef
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -0,0 +1,552 @@
+/*
+ * tools/testing/selftests/kvm/include/x86_64/vmx.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ */
+
+#ifndef SELFTEST_KVM_VMX_H
+#define SELFTEST_KVM_VMX_H
+
+#include <stdint.h>
+#include "processor.h"
+
+#define CPUID_VMX_BIT				5
+
+#define CPUID_VMX				(1 << 5)
+
+/*
+ * Definitions of Primary Processor-Based VM-Execution Controls.
+ */
+#define CPU_BASED_VIRTUAL_INTR_PENDING		0x00000004
+#define CPU_BASED_USE_TSC_OFFSETING		0x00000008
+#define CPU_BASED_HLT_EXITING			0x00000080
+#define CPU_BASED_INVLPG_EXITING		0x00000200
+#define CPU_BASED_MWAIT_EXITING			0x00000400
+#define CPU_BASED_RDPMC_EXITING			0x00000800
+#define CPU_BASED_RDTSC_EXITING			0x00001000
+#define CPU_BASED_CR3_LOAD_EXITING		0x00008000
+#define CPU_BASED_CR3_STORE_EXITING		0x00010000
+#define CPU_BASED_CR8_LOAD_EXITING		0x00080000
+#define CPU_BASED_CR8_STORE_EXITING		0x00100000
+#define CPU_BASED_TPR_SHADOW			0x00200000
+#define CPU_BASED_VIRTUAL_NMI_PENDING		0x00400000
+#define CPU_BASED_MOV_DR_EXITING		0x00800000
+#define CPU_BASED_UNCOND_IO_EXITING		0x01000000
+#define CPU_BASED_USE_IO_BITMAPS		0x02000000
+#define CPU_BASED_MONITOR_TRAP			0x08000000
+#define CPU_BASED_USE_MSR_BITMAPS		0x10000000
+#define CPU_BASED_MONITOR_EXITING		0x20000000
+#define CPU_BASED_PAUSE_EXITING			0x40000000
+#define CPU_BASED_ACTIVATE_SECONDARY_CONTROLS	0x80000000
+
+#define CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR	0x0401e172
+
+/*
+ * Definitions of Secondary Processor-Based VM-Execution Controls.
+ */
+#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
+#define SECONDARY_EXEC_ENABLE_EPT		0x00000002
+#define SECONDARY_EXEC_DESC			0x00000004
+#define SECONDARY_EXEC_RDTSCP			0x00000008
+#define SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE	0x00000010
+#define SECONDARY_EXEC_ENABLE_VPID		0x00000020
+#define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
+#define SECONDARY_EXEC_UNRESTRICTED_GUEST	0x00000080
+#define SECONDARY_EXEC_APIC_REGISTER_VIRT	0x00000100
+#define SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY	0x00000200
+#define SECONDARY_EXEC_PAUSE_LOOP_EXITING	0x00000400
+#define SECONDARY_EXEC_RDRAND_EXITING		0x00000800
+#define SECONDARY_EXEC_ENABLE_INVPCID		0x00001000
+#define SECONDARY_EXEC_ENABLE_VMFUNC		0x00002000
+#define SECONDARY_EXEC_SHADOW_VMCS		0x00004000
+#define SECONDARY_EXEC_RDSEED_EXITING		0x00010000
+#define SECONDARY_EXEC_ENABLE_PML		0x00020000
+#define SECONDARY_EPT_VE			0x00040000
+#define SECONDARY_ENABLE_XSAV_RESTORE		0x00100000
+#define SECONDARY_EXEC_TSC_SCALING		0x02000000
+
+#define PIN_BASED_EXT_INTR_MASK			0x00000001
+#define PIN_BASED_NMI_EXITING			0x00000008
+#define PIN_BASED_VIRTUAL_NMIS			0x00000020
+#define PIN_BASED_VMX_PREEMPTION_TIMER		0x00000040
+#define PIN_BASED_POSTED_INTR			0x00000080
+
+#define PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR	0x00000016
+
+#define VM_EXIT_SAVE_DEBUG_CONTROLS		0x00000004
+#define VM_EXIT_HOST_ADDR_SPACE_SIZE		0x00000200
+#define VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL	0x00001000
+#define VM_EXIT_ACK_INTR_ON_EXIT		0x00008000
+#define VM_EXIT_SAVE_IA32_PAT			0x00040000
+#define VM_EXIT_LOAD_IA32_PAT			0x00080000
+#define VM_EXIT_SAVE_IA32_EFER			0x00100000
+#define VM_EXIT_LOAD_IA32_EFER			0x00200000
+#define VM_EXIT_SAVE_VMX_PREEMPTION_TIMER	0x00400000
+
+#define VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR	0x00036dff
+
+#define VM_ENTRY_LOAD_DEBUG_CONTROLS		0x00000004
+#define VM_ENTRY_IA32E_MODE			0x00000200
+#define VM_ENTRY_SMM				0x00000400
+#define VM_ENTRY_DEACT_DUAL_MONITOR		0x00000800
+#define VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL	0x00002000
+#define VM_ENTRY_LOAD_IA32_PAT			0x00004000
+#define VM_ENTRY_LOAD_IA32_EFER			0x00008000
+
+#define VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR	0x000011ff
+
+#define VMX_MISC_PREEMPTION_TIMER_RATE_MASK	0x0000001f
+#define VMX_MISC_SAVE_EFER_LMA			0x00000020
+
+#define EXIT_REASON_FAILED_VMENTRY	0x80000000
+#define EXIT_REASON_EXCEPTION_NMI	0
+#define EXIT_REASON_EXTERNAL_INTERRUPT	1
+#define EXIT_REASON_TRIPLE_FAULT	2
+#define EXIT_REASON_PENDING_INTERRUPT	7
+#define EXIT_REASON_NMI_WINDOW		8
+#define EXIT_REASON_TASK_SWITCH		9
+#define EXIT_REASON_CPUID		10
+#define EXIT_REASON_HLT			12
+#define EXIT_REASON_INVD		13
+#define EXIT_REASON_INVLPG		14
+#define EXIT_REASON_RDPMC		15
+#define EXIT_REASON_RDTSC		16
+#define EXIT_REASON_VMCALL		18
+#define EXIT_REASON_VMCLEAR		19
+#define EXIT_REASON_VMLAUNCH		20
+#define EXIT_REASON_VMPTRLD		21
+#define EXIT_REASON_VMPTRST		22
+#define EXIT_REASON_VMREAD		23
+#define EXIT_REASON_VMRESUME		24
+#define EXIT_REASON_VMWRITE		25
+#define EXIT_REASON_VMOFF		26
+#define EXIT_REASON_VMON		27
+#define EXIT_REASON_CR_ACCESS		28
+#define EXIT_REASON_DR_ACCESS		29
+#define EXIT_REASON_IO_INSTRUCTION	30
+#define EXIT_REASON_MSR_READ		31
+#define EXIT_REASON_MSR_WRITE		32
+#define EXIT_REASON_INVALID_STATE	33
+#define EXIT_REASON_MWAIT_INSTRUCTION	36
+#define EXIT_REASON_MONITOR_INSTRUCTION 39
+#define EXIT_REASON_PAUSE_INSTRUCTION	40
+#define EXIT_REASON_MCE_DURING_VMENTRY	41
+#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
+#define EXIT_REASON_APIC_ACCESS		44
+#define EXIT_REASON_EOI_INDUCED		45
+#define EXIT_REASON_EPT_VIOLATION	48
+#define EXIT_REASON_EPT_MISCONFIG	49
+#define EXIT_REASON_INVEPT		50
+#define EXIT_REASON_RDTSCP		51
+#define EXIT_REASON_PREEMPTION_TIMER	52
+#define EXIT_REASON_INVVPID		53
+#define EXIT_REASON_WBINVD		54
+#define EXIT_REASON_XSETBV		55
+#define EXIT_REASON_APIC_WRITE		56
+#define EXIT_REASON_INVPCID		58
+#define EXIT_REASON_PML_FULL		62
+#define EXIT_REASON_XSAVES		63
+#define EXIT_REASON_XRSTORS		64
+#define LAST_EXIT_REASON		64
+
+enum vmcs_field {
+	VIRTUAL_PROCESSOR_ID		= 0x00000000,
+	POSTED_INTR_NV			= 0x00000002,
+	GUEST_ES_SELECTOR		= 0x00000800,
+	GUEST_CS_SELECTOR		= 0x00000802,
+	GUEST_SS_SELECTOR		= 0x00000804,
+	GUEST_DS_SELECTOR		= 0x00000806,
+	GUEST_FS_SELECTOR		= 0x00000808,
+	GUEST_GS_SELECTOR		= 0x0000080a,
+	GUEST_LDTR_SELECTOR		= 0x0000080c,
+	GUEST_TR_SELECTOR		= 0x0000080e,
+	GUEST_INTR_STATUS		= 0x00000810,
+	GUEST_PML_INDEX			= 0x00000812,
+	HOST_ES_SELECTOR		= 0x00000c00,
+	HOST_CS_SELECTOR		= 0x00000c02,
+	HOST_SS_SELECTOR		= 0x00000c04,
+	HOST_DS_SELECTOR		= 0x00000c06,
+	HOST_FS_SELECTOR		= 0x00000c08,
+	HOST_GS_SELECTOR		= 0x00000c0a,
+	HOST_TR_SELECTOR		= 0x00000c0c,
+	IO_BITMAP_A			= 0x00002000,
+	IO_BITMAP_A_HIGH		= 0x00002001,
+	IO_BITMAP_B			= 0x00002002,
+	IO_BITMAP_B_HIGH		= 0x00002003,
+	MSR_BITMAP			= 0x00002004,
+	MSR_BITMAP_HIGH			= 0x00002005,
+	VM_EXIT_MSR_STORE_ADDR		= 0x00002006,
+	VM_EXIT_MSR_STORE_ADDR_HIGH	= 0x00002007,
+	VM_EXIT_MSR_LOAD_ADDR		= 0x00002008,
+	VM_EXIT_MSR_LOAD_ADDR_HIGH	= 0x00002009,
+	VM_ENTRY_MSR_LOAD_ADDR		= 0x0000200a,
+	VM_ENTRY_MSR_LOAD_ADDR_HIGH	= 0x0000200b,
+	PML_ADDRESS			= 0x0000200e,
+	PML_ADDRESS_HIGH		= 0x0000200f,
+	TSC_OFFSET			= 0x00002010,
+	TSC_OFFSET_HIGH			= 0x00002011,
+	VIRTUAL_APIC_PAGE_ADDR		= 0x00002012,
+	VIRTUAL_APIC_PAGE_ADDR_HIGH	= 0x00002013,
+	APIC_ACCESS_ADDR		= 0x00002014,
+	APIC_ACCESS_ADDR_HIGH		= 0x00002015,
+	POSTED_INTR_DESC_ADDR		= 0x00002016,
+	POSTED_INTR_DESC_ADDR_HIGH	= 0x00002017,
+	EPT_POINTER			= 0x0000201a,
+	EPT_POINTER_HIGH		= 0x0000201b,
+	EOI_EXIT_BITMAP0		= 0x0000201c,
+	EOI_EXIT_BITMAP0_HIGH		= 0x0000201d,
+	EOI_EXIT_BITMAP1		= 0x0000201e,
+	EOI_EXIT_BITMAP1_HIGH		= 0x0000201f,
+	EOI_EXIT_BITMAP2		= 0x00002020,
+	EOI_EXIT_BITMAP2_HIGH		= 0x00002021,
+	EOI_EXIT_BITMAP3		= 0x00002022,
+	EOI_EXIT_BITMAP3_HIGH		= 0x00002023,
+	VMREAD_BITMAP			= 0x00002026,
+	VMREAD_BITMAP_HIGH		= 0x00002027,
+	VMWRITE_BITMAP			= 0x00002028,
+	VMWRITE_BITMAP_HIGH		= 0x00002029,
+	XSS_EXIT_BITMAP			= 0x0000202C,
+	XSS_EXIT_BITMAP_HIGH		= 0x0000202D,
+	TSC_MULTIPLIER			= 0x00002032,
+	TSC_MULTIPLIER_HIGH		= 0x00002033,
+	GUEST_PHYSICAL_ADDRESS		= 0x00002400,
+	GUEST_PHYSICAL_ADDRESS_HIGH	= 0x00002401,
+	VMCS_LINK_POINTER		= 0x00002800,
+	VMCS_LINK_POINTER_HIGH		= 0x00002801,
+	GUEST_IA32_DEBUGCTL		= 0x00002802,
+	GUEST_IA32_DEBUGCTL_HIGH	= 0x00002803,
+	GUEST_IA32_PAT			= 0x00002804,
+	GUEST_IA32_PAT_HIGH		= 0x00002805,
+	GUEST_IA32_EFER			= 0x00002806,
+	GUEST_IA32_EFER_HIGH		= 0x00002807,
+	GUEST_IA32_PERF_GLOBAL_CTRL	= 0x00002808,
+	GUEST_IA32_PERF_GLOBAL_CTRL_HIGH= 0x00002809,
+	GUEST_PDPTR0			= 0x0000280a,
+	GUEST_PDPTR0_HIGH		= 0x0000280b,
+	GUEST_PDPTR1			= 0x0000280c,
+	GUEST_PDPTR1_HIGH		= 0x0000280d,
+	GUEST_PDPTR2			= 0x0000280e,
+	GUEST_PDPTR2_HIGH		= 0x0000280f,
+	GUEST_PDPTR3			= 0x00002810,
+	GUEST_PDPTR3_HIGH		= 0x00002811,
+	GUEST_BNDCFGS			= 0x00002812,
+	GUEST_BNDCFGS_HIGH		= 0x00002813,
+	HOST_IA32_PAT			= 0x00002c00,
+	HOST_IA32_PAT_HIGH		= 0x00002c01,
+	HOST_IA32_EFER			= 0x00002c02,
+	HOST_IA32_EFER_HIGH		= 0x00002c03,
+	HOST_IA32_PERF_GLOBAL_CTRL	= 0x00002c04,
+	HOST_IA32_PERF_GLOBAL_CTRL_HIGH	= 0x00002c05,
+	PIN_BASED_VM_EXEC_CONTROL	= 0x00004000,
+	CPU_BASED_VM_EXEC_CONTROL	= 0x00004002,
+	EXCEPTION_BITMAP		= 0x00004004,
+	PAGE_FAULT_ERROR_CODE_MASK	= 0x00004006,
+	PAGE_FAULT_ERROR_CODE_MATCH	= 0x00004008,
+	CR3_TARGET_COUNT		= 0x0000400a,
+	VM_EXIT_CONTROLS		= 0x0000400c,
+	VM_EXIT_MSR_STORE_COUNT		= 0x0000400e,
+	VM_EXIT_MSR_LOAD_COUNT		= 0x00004010,
+	VM_ENTRY_CONTROLS		= 0x00004012,
+	VM_ENTRY_MSR_LOAD_COUNT		= 0x00004014,
+	VM_ENTRY_INTR_INFO_FIELD	= 0x00004016,
+	VM_ENTRY_EXCEPTION_ERROR_CODE	= 0x00004018,
+	VM_ENTRY_INSTRUCTION_LEN	= 0x0000401a,
+	TPR_THRESHOLD			= 0x0000401c,
+	SECONDARY_VM_EXEC_CONTROL	= 0x0000401e,
+	PLE_GAP				= 0x00004020,
+	PLE_WINDOW			= 0x00004022,
+	VM_INSTRUCTION_ERROR		= 0x00004400,
+	VM_EXIT_REASON			= 0x00004402,
+	VM_EXIT_INTR_INFO		= 0x00004404,
+	VM_EXIT_INTR_ERROR_CODE		= 0x00004406,
+	IDT_VECTORING_INFO_FIELD	= 0x00004408,
+	IDT_VECTORING_ERROR_CODE	= 0x0000440a,
+	VM_EXIT_INSTRUCTION_LEN		= 0x0000440c,
+	VMX_INSTRUCTION_INFO		= 0x0000440e,
+	GUEST_ES_LIMIT			= 0x00004800,
+	GUEST_CS_LIMIT			= 0x00004802,
+	GUEST_SS_LIMIT			= 0x00004804,
+	GUEST_DS_LIMIT			= 0x00004806,
+	GUEST_FS_LIMIT			= 0x00004808,
+	GUEST_GS_LIMIT			= 0x0000480a,
+	GUEST_LDTR_LIMIT		= 0x0000480c,
+	GUEST_TR_LIMIT			= 0x0000480e,
+	GUEST_GDTR_LIMIT		= 0x00004810,
+	GUEST_IDTR_LIMIT		= 0x00004812,
+	GUEST_ES_AR_BYTES		= 0x00004814,
+	GUEST_CS_AR_BYTES		= 0x00004816,
+	GUEST_SS_AR_BYTES		= 0x00004818,
+	GUEST_DS_AR_BYTES		= 0x0000481a,
+	GUEST_FS_AR_BYTES		= 0x0000481c,
+	GUEST_GS_AR_BYTES		= 0x0000481e,
+	GUEST_LDTR_AR_BYTES		= 0x00004820,
+	GUEST_TR_AR_BYTES		= 0x00004822,
+	GUEST_INTERRUPTIBILITY_INFO	= 0x00004824,
+	GUEST_ACTIVITY_STATE		= 0X00004826,
+	GUEST_SYSENTER_CS		= 0x0000482A,
+	VMX_PREEMPTION_TIMER_VALUE	= 0x0000482E,
+	HOST_IA32_SYSENTER_CS		= 0x00004c00,
+	CR0_GUEST_HOST_MASK		= 0x00006000,
+	CR4_GUEST_HOST_MASK		= 0x00006002,
+	CR0_READ_SHADOW			= 0x00006004,
+	CR4_READ_SHADOW			= 0x00006006,
+	CR3_TARGET_VALUE0		= 0x00006008,
+	CR3_TARGET_VALUE1		= 0x0000600a,
+	CR3_TARGET_VALUE2		= 0x0000600c,
+	CR3_TARGET_VALUE3		= 0x0000600e,
+	EXIT_QUALIFICATION		= 0x00006400,
+	GUEST_LINEAR_ADDRESS		= 0x0000640a,
+	GUEST_CR0			= 0x00006800,
+	GUEST_CR3			= 0x00006802,
+	GUEST_CR4			= 0x00006804,
+	GUEST_ES_BASE			= 0x00006806,
+	GUEST_CS_BASE			= 0x00006808,
+	GUEST_SS_BASE			= 0x0000680a,
+	GUEST_DS_BASE			= 0x0000680c,
+	GUEST_FS_BASE			= 0x0000680e,
+	GUEST_GS_BASE			= 0x00006810,
+	GUEST_LDTR_BASE			= 0x00006812,
+	GUEST_TR_BASE			= 0x00006814,
+	GUEST_GDTR_BASE			= 0x00006816,
+	GUEST_IDTR_BASE			= 0x00006818,
+	GUEST_DR7			= 0x0000681a,
+	GUEST_RSP			= 0x0000681c,
+	GUEST_RIP			= 0x0000681e,
+	GUEST_RFLAGS			= 0x00006820,
+	GUEST_PENDING_DBG_EXCEPTIONS	= 0x00006822,
+	GUEST_SYSENTER_ESP		= 0x00006824,
+	GUEST_SYSENTER_EIP		= 0x00006826,
+	HOST_CR0			= 0x00006c00,
+	HOST_CR3			= 0x00006c02,
+	HOST_CR4			= 0x00006c04,
+	HOST_FS_BASE			= 0x00006c06,
+	HOST_GS_BASE			= 0x00006c08,
+	HOST_TR_BASE			= 0x00006c0a,
+	HOST_GDTR_BASE			= 0x00006c0c,
+	HOST_IDTR_BASE			= 0x00006c0e,
+	HOST_IA32_SYSENTER_ESP		= 0x00006c10,
+	HOST_IA32_SYSENTER_EIP		= 0x00006c12,
+	HOST_RSP			= 0x00006c14,
+	HOST_RIP			= 0x00006c16,
+};
+
+struct vmx_msr_entry {
+	uint32_t index;
+	uint32_t reserved;
+	uint64_t value;
+} __attribute__ ((aligned(16)));
+
+static inline int vmxon(uint64_t phys)
+{
+	uint8_t ret;
+
+	__asm__ __volatile__ ("vmxon %[pa]; setna %[ret]"
+		: [ret]"=rm"(ret)
+		: [pa]"m"(phys)
+		: "cc", "memory");
+
+	return ret;
+}
+
+static inline void vmxoff(void)
+{
+	__asm__ __volatile__("vmxoff");
+}
+
+static inline int vmclear(uint64_t vmcs_pa)
+{
+	uint8_t ret;
+
+	__asm__ __volatile__ ("vmclear %[pa]; setna %[ret]"
+		: [ret]"=rm"(ret)
+		: [pa]"m"(vmcs_pa)
+		: "cc", "memory");
+
+	return ret;
+}
+
+static inline int vmptrld(uint64_t vmcs_pa)
+{
+	uint8_t ret;
+
+	__asm__ __volatile__ ("vmptrld %[pa]; setna %[ret]"
+		: [ret]"=rm"(ret)
+		: [pa]"m"(vmcs_pa)
+		: "cc", "memory");
+
+	return ret;
+}
+
+static inline int vmptrst(uint64_t *value)
+{
+	uint64_t tmp;
+	uint8_t ret;
+
+	__asm__ __volatile__("vmptrst %[value]; setna %[ret]"
+		: [value]"=m"(tmp), [ret]"=rm"(ret)
+		: : "cc", "memory");
+
+	*value = tmp;
+	return ret;
+}
+
+/*
+ * A wrapper around vmptrst that ignores errors and returns zero if the
+ * vmptrst instruction fails.
+ */
+static inline uint64_t vmptrstz(void)
+{
+	uint64_t value = 0;
+	vmptrst(&value);
+	return value;
+}
+
+/*
+ * No guest state (e.g. GPRs) is established by this vmlaunch.
+ */
+static inline int vmlaunch(void)
+{
+	int ret;
+
+	__asm__ __volatile__("push %%rbp;"
+			     "push %%rcx;"
+			     "push %%rdx;"
+			     "push %%rsi;"
+			     "push %%rdi;"
+			     "push $0;"
+			     "vmwrite %%rsp, %[host_rsp];"
+			     "lea 1f(%%rip), %%rax;"
+			     "vmwrite %%rax, %[host_rip];"
+			     "vmlaunch;"
+			     "incq (%%rsp);"
+			     "1: pop %%rax;"
+			     "pop %%rdi;"
+			     "pop %%rsi;"
+			     "pop %%rdx;"
+			     "pop %%rcx;"
+			     "pop %%rbp;"
+			     : [ret]"=&a"(ret)
+			     : [host_rsp]"r"((uint64_t)HOST_RSP),
+			       [host_rip]"r"((uint64_t)HOST_RIP)
+			     : "memory", "cc", "rbx", "r8", "r9", "r10",
+			       "r11", "r12", "r13", "r14", "r15");
+	return ret;
+}
+
+/*
+ * No guest state (e.g. GPRs) is established by this vmresume.
+ */
+static inline int vmresume(void)
+{
+	int ret;
+
+	__asm__ __volatile__("push %%rbp;"
+			     "push %%rcx;"
+			     "push %%rdx;"
+			     "push %%rsi;"
+			     "push %%rdi;"
+			     "push $0;"
+			     "vmwrite %%rsp, %[host_rsp];"
+			     "lea 1f(%%rip), %%rax;"
+			     "vmwrite %%rax, %[host_rip];"
+			     "vmresume;"
+			     "incq (%%rsp);"
+			     "1: pop %%rax;"
+			     "pop %%rdi;"
+			     "pop %%rsi;"
+			     "pop %%rdx;"
+			     "pop %%rcx;"
+			     "pop %%rbp;"
+			     : [ret]"=&a"(ret)
+			     : [host_rsp]"r"((uint64_t)HOST_RSP),
+			       [host_rip]"r"((uint64_t)HOST_RIP)
+			     : "memory", "cc", "rbx", "r8", "r9", "r10",
+			       "r11", "r12", "r13", "r14", "r15");
+	return ret;
+}
+
+static inline void vmcall(void)
+{
+	/* Currently, L1 destroys our GPRs during vmexits.  */
+	__asm__ __volatile__("push %%rbp; vmcall; pop %%rbp" : : :
+			     "rax", "rbx", "rcx", "rdx",
+			     "rsi", "rdi", "r8", "r9", "r10", "r11", "r12",
+			     "r13", "r14", "r15");
+}
+
+static inline int vmread(uint64_t encoding, uint64_t *value)
+{
+	uint64_t tmp;
+	uint8_t ret;
+
+	__asm__ __volatile__("vmread %[encoding], %[value]; setna %[ret]"
+		: [value]"=rm"(tmp), [ret]"=rm"(ret)
+		: [encoding]"r"(encoding)
+		: "cc", "memory");
+
+	*value = tmp;
+	return ret;
+}
+
+/*
+ * A wrapper around vmread that ignores errors and returns zero if the
+ * vmread instruction fails.
+ */
+static inline uint64_t vmreadz(uint64_t encoding)
+{
+	uint64_t value = 0;
+	vmread(encoding, &value);
+	return value;
+}
+
+static inline int vmwrite(uint64_t encoding, uint64_t value)
+{
+	uint8_t ret;
+
+	__asm__ __volatile__ ("vmwrite %[value], %[encoding]; setna %[ret]"
+		: [ret]"=rm"(ret)
+		: [value]"rm"(value), [encoding]"r"(encoding)
+		: "cc", "memory");
+
+	return ret;
+}
+
+static inline uint32_t vmcs_revision(void)
+{
+	return rdmsr(MSR_IA32_VMX_BASIC);
+}
+
+struct vmx_pages {
+	void *vmxon_hva;
+	uint64_t vmxon_gpa;
+	void *vmxon;
+
+	void *vmcs_hva;
+	uint64_t vmcs_gpa;
+	void *vmcs;
+
+	void *msr_hva;
+	uint64_t msr_gpa;
+	void *msr;
+
+	void *shadow_vmcs_hva;
+	uint64_t shadow_vmcs_gpa;
+	void *shadow_vmcs;
+
+	void *vmread_hva;
+	uint64_t vmread_gpa;
+	void *vmread;
+
+	void *vmwrite_hva;
+	uint64_t vmwrite_gpa;
+	void *vmwrite;
+};
+
+struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva);
+bool prepare_for_vmx_operation(struct vmx_pages *vmx);
+void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp);
+
+#endif /* SELFTEST_KVM_VMX_H */
diff --git a/tools/testing/selftests/kvm/lib/assert.c b/tools/testing/selftests/kvm/lib/assert.c
index cd01144d27c8..6398efe67885 100644
--- a/tools/testing/selftests/kvm/lib/assert.c
+++ b/tools/testing/selftests/kvm/lib/assert.c
@@ -13,7 +13,7 @@
 #include <execinfo.h>
 #include <sys/syscall.h>
 
-#include "../../kselftest.h"
+#include "kselftest.h"
 
 /* Dumps the current stack trace to stderr. */
 static void __attribute__((noinline)) test_dump_stack(void);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index 8fa7c9f7567a..36367be0fe26 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -1,13 +1,13 @@
 /*
- * tools/testing/selftests/kvm/lib/kvm_util.c
+ * tools/testing/selftests/kvm/lib/kvm_util_internal.h
  *
  * Copyright (C) 2018, Google LLC.
  *
  * This work is licensed under the terms of the GNU GPL, version 2.
  */
 
-#ifndef KVM_UTIL_INTERNAL_H
-#define KVM_UTIL_INTERNAL_H 1
+#ifndef SELFTEST_KVM_UTIL_INTERNAL_H
+#define SELFTEST_KVM_UTIL_INTERNAL_H
 
 #include "sparsebit.h"
 
@@ -70,4 +70,4 @@ void regs_dump(FILE *stream, struct kvm_regs *regs,
 void sregs_dump(FILE *stream, struct kvm_sregs *sregs,
 	uint8_t indent);
 
-#endif
+#endif /* SELFTEST_KVM_UTIL_INTERNAL_H */
diff --git a/tools/testing/selftests/kvm/lib/vmx.c b/tools/testing/selftests/kvm/lib/vmx.c
deleted file mode 100644
index b987c3c970eb..000000000000
--- a/tools/testing/selftests/kvm/lib/vmx.c
+++ /dev/null
@@ -1,283 +0,0 @@
-/*
- * tools/testing/selftests/kvm/lib/x86.c
- *
- * Copyright (C) 2018, Google LLC.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- */
-
-#define _GNU_SOURCE /* for program_invocation_name */
-
-#include "test_util.h"
-#include "kvm_util.h"
-#include "x86.h"
-#include "vmx.h"
-
-/* Allocate memory regions for nested VMX tests.
- *
- * Input Args:
- *   vm - The VM to allocate guest-virtual addresses in.
- *
- * Output Args:
- *   p_vmx_gva - The guest virtual address for the struct vmx_pages.
- *
- * Return:
- *   Pointer to structure with the addresses of the VMX areas.
- */
-struct vmx_pages *
-vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva)
-{
-	vm_vaddr_t vmx_gva = vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
-	struct vmx_pages *vmx = addr_gva2hva(vm, vmx_gva);
-
-	/* Setup of a region of guest memory for the vmxon region. */
-	vmx->vmxon = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
-	vmx->vmxon_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmxon);
-	vmx->vmxon_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmxon);
-
-	/* Setup of a region of guest memory for a vmcs. */
-	vmx->vmcs = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
-	vmx->vmcs_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmcs);
-	vmx->vmcs_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmcs);
-
-	/* Setup of a region of guest memory for the MSR bitmap. */
-	vmx->msr = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
-	vmx->msr_hva = addr_gva2hva(vm, (uintptr_t)vmx->msr);
-	vmx->msr_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->msr);
-	memset(vmx->msr_hva, 0, getpagesize());
-
-	/* Setup of a region of guest memory for the shadow VMCS. */
-	vmx->shadow_vmcs = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
-	vmx->shadow_vmcs_hva = addr_gva2hva(vm, (uintptr_t)vmx->shadow_vmcs);
-	vmx->shadow_vmcs_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->shadow_vmcs);
-
-	/* Setup of a region of guest memory for the VMREAD and VMWRITE bitmaps. */
-	vmx->vmread = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
-	vmx->vmread_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmread);
-	vmx->vmread_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmread);
-	memset(vmx->vmread_hva, 0, getpagesize());
-
-	vmx->vmwrite = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
-	vmx->vmwrite_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmwrite);
-	vmx->vmwrite_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmwrite);
-	memset(vmx->vmwrite_hva, 0, getpagesize());
-
-	*p_vmx_gva = vmx_gva;
-	return vmx;
-}
-
-bool prepare_for_vmx_operation(struct vmx_pages *vmx)
-{
-	uint64_t feature_control;
-	uint64_t required;
-	unsigned long cr0;
-	unsigned long cr4;
-
-	/*
-	 * Ensure bits in CR0 and CR4 are valid in VMX operation:
-	 * - Bit X is 1 in _FIXED0: bit X is fixed to 1 in CRx.
-	 * - Bit X is 0 in _FIXED1: bit X is fixed to 0 in CRx.
-	 */
-	__asm__ __volatile__("mov %%cr0, %0" : "=r"(cr0) : : "memory");
-	cr0 &= rdmsr(MSR_IA32_VMX_CR0_FIXED1);
-	cr0 |= rdmsr(MSR_IA32_VMX_CR0_FIXED0);
-	__asm__ __volatile__("mov %0, %%cr0" : : "r"(cr0) : "memory");
-
-	__asm__ __volatile__("mov %%cr4, %0" : "=r"(cr4) : : "memory");
-	cr4 &= rdmsr(MSR_IA32_VMX_CR4_FIXED1);
-	cr4 |= rdmsr(MSR_IA32_VMX_CR4_FIXED0);
-	/* Enable VMX operation */
-	cr4 |= X86_CR4_VMXE;
-	__asm__ __volatile__("mov %0, %%cr4" : : "r"(cr4) : "memory");
-
-	/*
-	 * Configure IA32_FEATURE_CONTROL MSR to allow VMXON:
-	 *  Bit 0: Lock bit. If clear, VMXON causes a #GP.
-	 *  Bit 2: Enables VMXON outside of SMX operation. If clear, VMXON
-	 *    outside of SMX causes a #GP.
-	 */
-	required = FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
-	required |= FEATURE_CONTROL_LOCKED;
-	feature_control = rdmsr(MSR_IA32_FEATURE_CONTROL);
-	if ((feature_control & required) != required)
-		wrmsr(MSR_IA32_FEATURE_CONTROL, feature_control | required);
-
-	/* Enter VMX root operation. */
-	*(uint32_t *)(vmx->vmxon) = vmcs_revision();
-	if (vmxon(vmx->vmxon_gpa))
-		return false;
-
-	/* Load a VMCS. */
-	*(uint32_t *)(vmx->vmcs) = vmcs_revision();
-	if (vmclear(vmx->vmcs_gpa))
-		return false;
-
-	if (vmptrld(vmx->vmcs_gpa))
-		return false;
-
-	/* Setup shadow VMCS, do not load it yet. */
-	*(uint32_t *)(vmx->shadow_vmcs) = vmcs_revision() | 0x80000000ul;
-	if (vmclear(vmx->shadow_vmcs_gpa))
-		return false;
-
-	return true;
-}
-
-/*
- * Initialize the control fields to the most basic settings possible.
- */
-static inline void init_vmcs_control_fields(struct vmx_pages *vmx)
-{
-	vmwrite(VIRTUAL_PROCESSOR_ID, 0);
-	vmwrite(POSTED_INTR_NV, 0);
-
-	vmwrite(PIN_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PINBASED_CTLS));
-	if (!vmwrite(SECONDARY_VM_EXEC_CONTROL, 0))
-		vmwrite(CPU_BASED_VM_EXEC_CONTROL,
-			rdmsr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS) | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS);
-	else
-		vmwrite(CPU_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS));
-	vmwrite(EXCEPTION_BITMAP, 0);
-	vmwrite(PAGE_FAULT_ERROR_CODE_MASK, 0);
-	vmwrite(PAGE_FAULT_ERROR_CODE_MATCH, -1); /* Never match */
-	vmwrite(CR3_TARGET_COUNT, 0);
-	vmwrite(VM_EXIT_CONTROLS, rdmsr(MSR_IA32_VMX_EXIT_CTLS) |
-		VM_EXIT_HOST_ADDR_SPACE_SIZE);	  /* 64-bit host */
-	vmwrite(VM_EXIT_MSR_STORE_COUNT, 0);
-	vmwrite(VM_EXIT_MSR_LOAD_COUNT, 0);
-	vmwrite(VM_ENTRY_CONTROLS, rdmsr(MSR_IA32_VMX_ENTRY_CTLS) |
-		VM_ENTRY_IA32E_MODE);		  /* 64-bit guest */
-	vmwrite(VM_ENTRY_MSR_LOAD_COUNT, 0);
-	vmwrite(VM_ENTRY_INTR_INFO_FIELD, 0);
-	vmwrite(TPR_THRESHOLD, 0);
-
-	vmwrite(CR0_GUEST_HOST_MASK, 0);
-	vmwrite(CR4_GUEST_HOST_MASK, 0);
-	vmwrite(CR0_READ_SHADOW, get_cr0());
-	vmwrite(CR4_READ_SHADOW, get_cr4());
-
-	vmwrite(MSR_BITMAP, vmx->msr_gpa);
-	vmwrite(VMREAD_BITMAP, vmx->vmread_gpa);
-	vmwrite(VMWRITE_BITMAP, vmx->vmwrite_gpa);
-}
-
-/*
- * Initialize the host state fields based on the current host state, with
- * the exception of HOST_RSP and HOST_RIP, which should be set by vmlaunch
- * or vmresume.
- */
-static inline void init_vmcs_host_state(void)
-{
-	uint32_t exit_controls = vmreadz(VM_EXIT_CONTROLS);
-
-	vmwrite(HOST_ES_SELECTOR, get_es());
-	vmwrite(HOST_CS_SELECTOR, get_cs());
-	vmwrite(HOST_SS_SELECTOR, get_ss());
-	vmwrite(HOST_DS_SELECTOR, get_ds());
-	vmwrite(HOST_FS_SELECTOR, get_fs());
-	vmwrite(HOST_GS_SELECTOR, get_gs());
-	vmwrite(HOST_TR_SELECTOR, get_tr());
-
-	if (exit_controls & VM_EXIT_LOAD_IA32_PAT)
-		vmwrite(HOST_IA32_PAT, rdmsr(MSR_IA32_CR_PAT));
-	if (exit_controls & VM_EXIT_LOAD_IA32_EFER)
-		vmwrite(HOST_IA32_EFER, rdmsr(MSR_EFER));
-	if (exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
-		vmwrite(HOST_IA32_PERF_GLOBAL_CTRL,
-			rdmsr(MSR_CORE_PERF_GLOBAL_CTRL));
-
-	vmwrite(HOST_IA32_SYSENTER_CS, rdmsr(MSR_IA32_SYSENTER_CS));
-
-	vmwrite(HOST_CR0, get_cr0());
-	vmwrite(HOST_CR3, get_cr3());
-	vmwrite(HOST_CR4, get_cr4());
-	vmwrite(HOST_FS_BASE, rdmsr(MSR_FS_BASE));
-	vmwrite(HOST_GS_BASE, rdmsr(MSR_GS_BASE));
-	vmwrite(HOST_TR_BASE,
-		get_desc64_base((struct desc64 *)(get_gdt_base() + get_tr())));
-	vmwrite(HOST_GDTR_BASE, get_gdt_base());
-	vmwrite(HOST_IDTR_BASE, get_idt_base());
-	vmwrite(HOST_IA32_SYSENTER_ESP, rdmsr(MSR_IA32_SYSENTER_ESP));
-	vmwrite(HOST_IA32_SYSENTER_EIP, rdmsr(MSR_IA32_SYSENTER_EIP));
-}
-
-/*
- * Initialize the guest state fields essentially as a clone of
- * the host state fields. Some host state fields have fixed
- * values, and we set the corresponding guest state fields accordingly.
- */
-static inline void init_vmcs_guest_state(void *rip, void *rsp)
-{
-	vmwrite(GUEST_ES_SELECTOR, vmreadz(HOST_ES_SELECTOR));
-	vmwrite(GUEST_CS_SELECTOR, vmreadz(HOST_CS_SELECTOR));
-	vmwrite(GUEST_SS_SELECTOR, vmreadz(HOST_SS_SELECTOR));
-	vmwrite(GUEST_DS_SELECTOR, vmreadz(HOST_DS_SELECTOR));
-	vmwrite(GUEST_FS_SELECTOR, vmreadz(HOST_FS_SELECTOR));
-	vmwrite(GUEST_GS_SELECTOR, vmreadz(HOST_GS_SELECTOR));
-	vmwrite(GUEST_LDTR_SELECTOR, 0);
-	vmwrite(GUEST_TR_SELECTOR, vmreadz(HOST_TR_SELECTOR));
-	vmwrite(GUEST_INTR_STATUS, 0);
-	vmwrite(GUEST_PML_INDEX, 0);
-
-	vmwrite(VMCS_LINK_POINTER, -1ll);
-	vmwrite(GUEST_IA32_DEBUGCTL, 0);
-	vmwrite(GUEST_IA32_PAT, vmreadz(HOST_IA32_PAT));
-	vmwrite(GUEST_IA32_EFER, vmreadz(HOST_IA32_EFER));
-	vmwrite(GUEST_IA32_PERF_GLOBAL_CTRL,
-		vmreadz(HOST_IA32_PERF_GLOBAL_CTRL));
-
-	vmwrite(GUEST_ES_LIMIT, -1);
-	vmwrite(GUEST_CS_LIMIT, -1);
-	vmwrite(GUEST_SS_LIMIT, -1);
-	vmwrite(GUEST_DS_LIMIT, -1);
-	vmwrite(GUEST_FS_LIMIT, -1);
-	vmwrite(GUEST_GS_LIMIT, -1);
-	vmwrite(GUEST_LDTR_LIMIT, -1);
-	vmwrite(GUEST_TR_LIMIT, 0x67);
-	vmwrite(GUEST_GDTR_LIMIT, 0xffff);
-	vmwrite(GUEST_IDTR_LIMIT, 0xffff);
-	vmwrite(GUEST_ES_AR_BYTES,
-		vmreadz(GUEST_ES_SELECTOR) == 0 ? 0x10000 : 0xc093);
-	vmwrite(GUEST_CS_AR_BYTES, 0xa09b);
-	vmwrite(GUEST_SS_AR_BYTES, 0xc093);
-	vmwrite(GUEST_DS_AR_BYTES,
-		vmreadz(GUEST_DS_SELECTOR) == 0 ? 0x10000 : 0xc093);
-	vmwrite(GUEST_FS_AR_BYTES,
-		vmreadz(GUEST_FS_SELECTOR) == 0 ? 0x10000 : 0xc093);
-	vmwrite(GUEST_GS_AR_BYTES,
-		vmreadz(GUEST_GS_SELECTOR) == 0 ? 0x10000 : 0xc093);
-	vmwrite(GUEST_LDTR_AR_BYTES, 0x10000);
-	vmwrite(GUEST_TR_AR_BYTES, 0x8b);
-	vmwrite(GUEST_INTERRUPTIBILITY_INFO, 0);
-	vmwrite(GUEST_ACTIVITY_STATE, 0);
-	vmwrite(GUEST_SYSENTER_CS, vmreadz(HOST_IA32_SYSENTER_CS));
-	vmwrite(VMX_PREEMPTION_TIMER_VALUE, 0);
-
-	vmwrite(GUEST_CR0, vmreadz(HOST_CR0));
-	vmwrite(GUEST_CR3, vmreadz(HOST_CR3));
-	vmwrite(GUEST_CR4, vmreadz(HOST_CR4));
-	vmwrite(GUEST_ES_BASE, 0);
-	vmwrite(GUEST_CS_BASE, 0);
-	vmwrite(GUEST_SS_BASE, 0);
-	vmwrite(GUEST_DS_BASE, 0);
-	vmwrite(GUEST_FS_BASE, vmreadz(HOST_FS_BASE));
-	vmwrite(GUEST_GS_BASE, vmreadz(HOST_GS_BASE));
-	vmwrite(GUEST_LDTR_BASE, 0);
-	vmwrite(GUEST_TR_BASE, vmreadz(HOST_TR_BASE));
-	vmwrite(GUEST_GDTR_BASE, vmreadz(HOST_GDTR_BASE));
-	vmwrite(GUEST_IDTR_BASE, vmreadz(HOST_IDTR_BASE));
-	vmwrite(GUEST_DR7, 0x400);
-	vmwrite(GUEST_RSP, (uint64_t)rsp);
-	vmwrite(GUEST_RIP, (uint64_t)rip);
-	vmwrite(GUEST_RFLAGS, 2);
-	vmwrite(GUEST_PENDING_DBG_EXCEPTIONS, 0);
-	vmwrite(GUEST_SYSENTER_ESP, vmreadz(HOST_IA32_SYSENTER_ESP));
-	vmwrite(GUEST_SYSENTER_EIP, vmreadz(HOST_IA32_SYSENTER_EIP));
-}
-
-void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp)
-{
-	init_vmcs_control_fields(vmx);
-	init_vmcs_host_state();
-	init_vmcs_guest_state(guest_rip, guest_rsp);
-}
diff --git a/tools/testing/selftests/kvm/lib/x86.c b/tools/testing/selftests/kvm/lib/x86.c
deleted file mode 100644
index bb6c65ebfa77..000000000000
--- a/tools/testing/selftests/kvm/lib/x86.c
+++ /dev/null
@@ -1,888 +0,0 @@
-/*
- * tools/testing/selftests/kvm/lib/x86.c
- *
- * Copyright (C) 2018, Google LLC.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- */
-
-#define _GNU_SOURCE /* for program_invocation_name */
-
-#include "test_util.h"
-#include "kvm_util.h"
-#include "kvm_util_internal.h"
-#include "x86.h"
-
-/* Minimum physical address used for virtual translation tables. */
-#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
-
-/* Virtual translation table structure declarations */
-struct pageMapL4Entry {
-	uint64_t present:1;
-	uint64_t writable:1;
-	uint64_t user:1;
-	uint64_t write_through:1;
-	uint64_t cache_disable:1;
-	uint64_t accessed:1;
-	uint64_t ignored_06:1;
-	uint64_t page_size:1;
-	uint64_t ignored_11_08:4;
-	uint64_t address:40;
-	uint64_t ignored_62_52:11;
-	uint64_t execute_disable:1;
-};
-
-struct pageDirectoryPointerEntry {
-	uint64_t present:1;
-	uint64_t writable:1;
-	uint64_t user:1;
-	uint64_t write_through:1;
-	uint64_t cache_disable:1;
-	uint64_t accessed:1;
-	uint64_t ignored_06:1;
-	uint64_t page_size:1;
-	uint64_t ignored_11_08:4;
-	uint64_t address:40;
-	uint64_t ignored_62_52:11;
-	uint64_t execute_disable:1;
-};
-
-struct pageDirectoryEntry {
-	uint64_t present:1;
-	uint64_t writable:1;
-	uint64_t user:1;
-	uint64_t write_through:1;
-	uint64_t cache_disable:1;
-	uint64_t accessed:1;
-	uint64_t ignored_06:1;
-	uint64_t page_size:1;
-	uint64_t ignored_11_08:4;
-	uint64_t address:40;
-	uint64_t ignored_62_52:11;
-	uint64_t execute_disable:1;
-};
-
-struct pageTableEntry {
-	uint64_t present:1;
-	uint64_t writable:1;
-	uint64_t user:1;
-	uint64_t write_through:1;
-	uint64_t cache_disable:1;
-	uint64_t accessed:1;
-	uint64_t dirty:1;
-	uint64_t reserved_07:1;
-	uint64_t global:1;
-	uint64_t ignored_11_09:3;
-	uint64_t address:40;
-	uint64_t ignored_62_52:11;
-	uint64_t execute_disable:1;
-};
-
-/* Register Dump
- *
- * Input Args:
- *   indent - Left margin indent amount
- *   regs - register
- *
- * Output Args:
- *   stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps the state of the registers given by regs, to the FILE stream
- * given by steam.
- */
-void regs_dump(FILE *stream, struct kvm_regs *regs,
-	       uint8_t indent)
-{
-	fprintf(stream, "%*srax: 0x%.16llx rbx: 0x%.16llx "
-		"rcx: 0x%.16llx rdx: 0x%.16llx\n",
-		indent, "",
-		regs->rax, regs->rbx, regs->rcx, regs->rdx);
-	fprintf(stream, "%*srsi: 0x%.16llx rdi: 0x%.16llx "
-		"rsp: 0x%.16llx rbp: 0x%.16llx\n",
-		indent, "",
-		regs->rsi, regs->rdi, regs->rsp, regs->rbp);
-	fprintf(stream, "%*sr8:  0x%.16llx r9:  0x%.16llx "
-		"r10: 0x%.16llx r11: 0x%.16llx\n",
-		indent, "",
-		regs->r8, regs->r9, regs->r10, regs->r11);
-	fprintf(stream, "%*sr12: 0x%.16llx r13: 0x%.16llx "
-		"r14: 0x%.16llx r15: 0x%.16llx\n",
-		indent, "",
-		regs->r12, regs->r13, regs->r14, regs->r15);
-	fprintf(stream, "%*srip: 0x%.16llx rfl: 0x%.16llx\n",
-		indent, "",
-		regs->rip, regs->rflags);
-}
-
-/* Segment Dump
- *
- * Input Args:
- *   indent - Left margin indent amount
- *   segment - KVM segment
- *
- * Output Args:
- *   stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps the state of the KVM segment given by segment, to the FILE stream
- * given by steam.
- */
-static void segment_dump(FILE *stream, struct kvm_segment *segment,
-			 uint8_t indent)
-{
-	fprintf(stream, "%*sbase: 0x%.16llx limit: 0x%.8x "
-		"selector: 0x%.4x type: 0x%.2x\n",
-		indent, "", segment->base, segment->limit,
-		segment->selector, segment->type);
-	fprintf(stream, "%*spresent: 0x%.2x dpl: 0x%.2x "
-		"db: 0x%.2x s: 0x%.2x l: 0x%.2x\n",
-		indent, "", segment->present, segment->dpl,
-		segment->db, segment->s, segment->l);
-	fprintf(stream, "%*sg: 0x%.2x avl: 0x%.2x "
-		"unusable: 0x%.2x padding: 0x%.2x\n",
-		indent, "", segment->g, segment->avl,
-		segment->unusable, segment->padding);
-}
-
-/* dtable Dump
- *
- * Input Args:
- *   indent - Left margin indent amount
- *   dtable - KVM dtable
- *
- * Output Args:
- *   stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps the state of the KVM dtable given by dtable, to the FILE stream
- * given by steam.
- */
-static void dtable_dump(FILE *stream, struct kvm_dtable *dtable,
-			uint8_t indent)
-{
-	fprintf(stream, "%*sbase: 0x%.16llx limit: 0x%.4x "
-		"padding: 0x%.4x 0x%.4x 0x%.4x\n",
-		indent, "", dtable->base, dtable->limit,
-		dtable->padding[0], dtable->padding[1], dtable->padding[2]);
-}
-
-/* System Register Dump
- *
- * Input Args:
- *   indent - Left margin indent amount
- *   sregs - System registers
- *
- * Output Args:
- *   stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps the state of the system registers given by sregs, to the FILE stream
- * given by steam.
- */
-void sregs_dump(FILE *stream, struct kvm_sregs *sregs,
-		uint8_t indent)
-{
-	unsigned int i;
-
-	fprintf(stream, "%*scs:\n", indent, "");
-	segment_dump(stream, &sregs->cs, indent + 2);
-	fprintf(stream, "%*sds:\n", indent, "");
-	segment_dump(stream, &sregs->ds, indent + 2);
-	fprintf(stream, "%*ses:\n", indent, "");
-	segment_dump(stream, &sregs->es, indent + 2);
-	fprintf(stream, "%*sfs:\n", indent, "");
-	segment_dump(stream, &sregs->fs, indent + 2);
-	fprintf(stream, "%*sgs:\n", indent, "");
-	segment_dump(stream, &sregs->gs, indent + 2);
-	fprintf(stream, "%*sss:\n", indent, "");
-	segment_dump(stream, &sregs->ss, indent + 2);
-	fprintf(stream, "%*str:\n", indent, "");
-	segment_dump(stream, &sregs->tr, indent + 2);
-	fprintf(stream, "%*sldt:\n", indent, "");
-	segment_dump(stream, &sregs->ldt, indent + 2);
-
-	fprintf(stream, "%*sgdt:\n", indent, "");
-	dtable_dump(stream, &sregs->gdt, indent + 2);
-	fprintf(stream, "%*sidt:\n", indent, "");
-	dtable_dump(stream, &sregs->idt, indent + 2);
-
-	fprintf(stream, "%*scr0: 0x%.16llx cr2: 0x%.16llx "
-		"cr3: 0x%.16llx cr4: 0x%.16llx\n",
-		indent, "",
-		sregs->cr0, sregs->cr2, sregs->cr3, sregs->cr4);
-	fprintf(stream, "%*scr8: 0x%.16llx efer: 0x%.16llx "
-		"apic_base: 0x%.16llx\n",
-		indent, "",
-		sregs->cr8, sregs->efer, sregs->apic_base);
-
-	fprintf(stream, "%*sinterrupt_bitmap:\n", indent, "");
-	for (i = 0; i < (KVM_NR_INTERRUPTS + 63) / 64; i++) {
-		fprintf(stream, "%*s%.16llx\n", indent + 2, "",
-			sregs->interrupt_bitmap[i]);
-	}
-}
-
-void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot)
-{
-	int rc;
-
-	TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
-		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
-
-	/* If needed, create page map l4 table. */
-	if (!vm->pgd_created) {
-		vm_paddr_t paddr = vm_phy_page_alloc(vm,
-			KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
-		vm->pgd = paddr;
-		vm->pgd_created = true;
-	}
-}
-
-/* VM Virtual Page Map
- *
- * Input Args:
- *   vm - Virtual Machine
- *   vaddr - VM Virtual Address
- *   paddr - VM Physical Address
- *   pgd_memslot - Memory region slot for new virtual translation tables
- *
- * Output Args: None
- *
- * Return: None
- *
- * Within the VM given by vm, creates a virtual translation for the page
- * starting at vaddr to the page starting at paddr.
- */
-void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
-	uint32_t pgd_memslot)
-{
-	uint16_t index[4];
-	struct pageMapL4Entry *pml4e;
-
-	TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
-		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
-
-	TEST_ASSERT((vaddr % vm->page_size) == 0,
-		"Virtual address not on page boundary,\n"
-		"  vaddr: 0x%lx vm->page_size: 0x%x",
-		vaddr, vm->page_size);
-	TEST_ASSERT(sparsebit_is_set(vm->vpages_valid,
-		(vaddr >> vm->page_shift)),
-		"Invalid virtual address, vaddr: 0x%lx",
-		vaddr);
-	TEST_ASSERT((paddr % vm->page_size) == 0,
-		"Physical address not on page boundary,\n"
-		"  paddr: 0x%lx vm->page_size: 0x%x",
-		paddr, vm->page_size);
-	TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn,
-		"Physical address beyond beyond maximum supported,\n"
-		"  paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
-		paddr, vm->max_gfn, vm->page_size);
-
-	index[0] = (vaddr >> 12) & 0x1ffu;
-	index[1] = (vaddr >> 21) & 0x1ffu;
-	index[2] = (vaddr >> 30) & 0x1ffu;
-	index[3] = (vaddr >> 39) & 0x1ffu;
-
-	/* Allocate page directory pointer table if not present. */
-	pml4e = addr_gpa2hva(vm, vm->pgd);
-	if (!pml4e[index[3]].present) {
-		pml4e[index[3]].address = vm_phy_page_alloc(vm,
-			KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot)
-			>> vm->page_shift;
-		pml4e[index[3]].writable = true;
-		pml4e[index[3]].present = true;
-	}
-
-	/* Allocate page directory table if not present. */
-	struct pageDirectoryPointerEntry *pdpe;
-	pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
-	if (!pdpe[index[2]].present) {
-		pdpe[index[2]].address = vm_phy_page_alloc(vm,
-			KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot)
-			>> vm->page_shift;
-		pdpe[index[2]].writable = true;
-		pdpe[index[2]].present = true;
-	}
-
-	/* Allocate page table if not present. */
-	struct pageDirectoryEntry *pde;
-	pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
-	if (!pde[index[1]].present) {
-		pde[index[1]].address = vm_phy_page_alloc(vm,
-			KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot)
-			>> vm->page_shift;
-		pde[index[1]].writable = true;
-		pde[index[1]].present = true;
-	}
-
-	/* Fill in page table entry. */
-	struct pageTableEntry *pte;
-	pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
-	pte[index[0]].address = paddr >> vm->page_shift;
-	pte[index[0]].writable = true;
-	pte[index[0]].present = 1;
-}
-
-/* Virtual Translation Tables Dump
- *
- * Input Args:
- *   vm - Virtual Machine
- *   indent - Left margin indent amount
- *
- * Output Args:
- *   stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps to the FILE stream given by stream, the contents of all the
- * virtual translation tables for the VM given by vm.
- */
-void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
-{
-	struct pageMapL4Entry *pml4e, *pml4e_start;
-	struct pageDirectoryPointerEntry *pdpe, *pdpe_start;
-	struct pageDirectoryEntry *pde, *pde_start;
-	struct pageTableEntry *pte, *pte_start;
-
-	if (!vm->pgd_created)
-		return;
-
-	fprintf(stream, "%*s                                          "
-		"                no\n", indent, "");
-	fprintf(stream, "%*s      index hvaddr         gpaddr         "
-		"addr         w exec dirty\n",
-		indent, "");
-	pml4e_start = (struct pageMapL4Entry *) addr_gpa2hva(vm,
-		vm->pgd);
-	for (uint16_t n1 = 0; n1 <= 0x1ffu; n1++) {
-		pml4e = &pml4e_start[n1];
-		if (!pml4e->present)
-			continue;
-		fprintf(stream, "%*spml4e 0x%-3zx %p 0x%-12lx 0x%-10lx %u "
-			" %u\n",
-			indent, "",
-			pml4e - pml4e_start, pml4e,
-			addr_hva2gpa(vm, pml4e), (uint64_t) pml4e->address,
-			pml4e->writable, pml4e->execute_disable);
-
-		pdpe_start = addr_gpa2hva(vm, pml4e->address
-			* vm->page_size);
-		for (uint16_t n2 = 0; n2 <= 0x1ffu; n2++) {
-			pdpe = &pdpe_start[n2];
-			if (!pdpe->present)
-				continue;
-			fprintf(stream, "%*spdpe  0x%-3zx %p 0x%-12lx 0x%-10lx "
-				"%u  %u\n",
-				indent, "",
-				pdpe - pdpe_start, pdpe,
-				addr_hva2gpa(vm, pdpe),
-				(uint64_t) pdpe->address, pdpe->writable,
-				pdpe->execute_disable);
-
-			pde_start = addr_gpa2hva(vm,
-				pdpe->address * vm->page_size);
-			for (uint16_t n3 = 0; n3 <= 0x1ffu; n3++) {
-				pde = &pde_start[n3];
-				if (!pde->present)
-					continue;
-				fprintf(stream, "%*spde   0x%-3zx %p "
-					"0x%-12lx 0x%-10lx %u  %u\n",
-					indent, "", pde - pde_start, pde,
-					addr_hva2gpa(vm, pde),
-					(uint64_t) pde->address, pde->writable,
-					pde->execute_disable);
-
-				pte_start = addr_gpa2hva(vm,
-					pde->address * vm->page_size);
-				for (uint16_t n4 = 0; n4 <= 0x1ffu; n4++) {
-					pte = &pte_start[n4];
-					if (!pte->present)
-						continue;
-					fprintf(stream, "%*spte   0x%-3zx %p "
-						"0x%-12lx 0x%-10lx %u  %u "
-						"    %u    0x%-10lx\n",
-						indent, "",
-						pte - pte_start, pte,
-						addr_hva2gpa(vm, pte),
-						(uint64_t) pte->address,
-						pte->writable,
-						pte->execute_disable,
-						pte->dirty,
-						((uint64_t) n1 << 27)
-							| ((uint64_t) n2 << 18)
-							| ((uint64_t) n3 << 9)
-							| ((uint64_t) n4));
-				}
-			}
-		}
-	}
-}
-
-/* Set Unusable Segment
- *
- * Input Args: None
- *
- * Output Args:
- *   segp - Pointer to segment register
- *
- * Return: None
- *
- * Sets the segment register pointed to by segp to an unusable state.
- */
-static void kvm_seg_set_unusable(struct kvm_segment *segp)
-{
-	memset(segp, 0, sizeof(*segp));
-	segp->unusable = true;
-}
-
-static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp)
-{
-	void *gdt = addr_gva2hva(vm, vm->gdt);
-	struct desc64 *desc = gdt + (segp->selector >> 3) * 8;
-
-	desc->limit0 = segp->limit & 0xFFFF;
-	desc->base0 = segp->base & 0xFFFF;
-	desc->base1 = segp->base >> 16;
-	desc->s = segp->s;
-	desc->type = segp->type;
-	desc->dpl = segp->dpl;
-	desc->p = segp->present;
-	desc->limit1 = segp->limit >> 16;
-	desc->l = segp->l;
-	desc->db = segp->db;
-	desc->g = segp->g;
-	desc->base2 = segp->base >> 24;
-	if (!segp->s)
-		desc->base3 = segp->base >> 32;
-}
-
-
-/* Set Long Mode Flat Kernel Code Segment
- *
- * Input Args:
- *   vm - VM whose GDT is being filled, or NULL to only write segp
- *   selector - selector value
- *
- * Output Args:
- *   segp - Pointer to KVM segment
- *
- * Return: None
- *
- * Sets up the KVM segment pointed to by segp, to be a code segment
- * with the selector value given by selector.
- */
-static void kvm_seg_set_kernel_code_64bit(struct kvm_vm *vm, uint16_t selector,
-	struct kvm_segment *segp)
-{
-	memset(segp, 0, sizeof(*segp));
-	segp->selector = selector;
-	segp->limit = 0xFFFFFFFFu;
-	segp->s = 0x1; /* kTypeCodeData */
-	segp->type = 0x08 | 0x01 | 0x02; /* kFlagCode | kFlagCodeAccessed
-					  * | kFlagCodeReadable
-					  */
-	segp->g = true;
-	segp->l = true;
-	segp->present = 1;
-	if (vm)
-		kvm_seg_fill_gdt_64bit(vm, segp);
-}
-
-/* Set Long Mode Flat Kernel Data Segment
- *
- * Input Args:
- *   vm - VM whose GDT is being filled, or NULL to only write segp
- *   selector - selector value
- *
- * Output Args:
- *   segp - Pointer to KVM segment
- *
- * Return: None
- *
- * Sets up the KVM segment pointed to by segp, to be a data segment
- * with the selector value given by selector.
- */
-static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector,
-	struct kvm_segment *segp)
-{
-	memset(segp, 0, sizeof(*segp));
-	segp->selector = selector;
-	segp->limit = 0xFFFFFFFFu;
-	segp->s = 0x1; /* kTypeCodeData */
-	segp->type = 0x00 | 0x01 | 0x02; /* kFlagData | kFlagDataAccessed
-					  * | kFlagDataWritable
-					  */
-	segp->g = true;
-	segp->present = true;
-	if (vm)
-		kvm_seg_fill_gdt_64bit(vm, segp);
-}
-
-/* Address Guest Virtual to Guest Physical
- *
- * Input Args:
- *   vm - Virtual Machine
- *   gpa - VM virtual address
- *
- * Output Args: None
- *
- * Return:
- *   Equivalent VM physical address
- *
- * Translates the VM virtual address given by gva to a VM physical
- * address and then locates the memory region containing the VM
- * physical address, within the VM given by vm.  When found, the host
- * virtual address providing the memory to the vm physical address is returned.
- * A TEST_ASSERT failure occurs if no region containing translated
- * VM virtual address exists.
- */
-vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
-{
-	uint16_t index[4];
-	struct pageMapL4Entry *pml4e;
-	struct pageDirectoryPointerEntry *pdpe;
-	struct pageDirectoryEntry *pde;
-	struct pageTableEntry *pte;
-	void *hva;
-
-	TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
-		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
-
-	index[0] = (gva >> 12) & 0x1ffu;
-	index[1] = (gva >> 21) & 0x1ffu;
-	index[2] = (gva >> 30) & 0x1ffu;
-	index[3] = (gva >> 39) & 0x1ffu;
-
-	if (!vm->pgd_created)
-		goto unmapped_gva;
-	pml4e = addr_gpa2hva(vm, vm->pgd);
-	if (!pml4e[index[3]].present)
-		goto unmapped_gva;
-
-	pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
-	if (!pdpe[index[2]].present)
-		goto unmapped_gva;
-
-	pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
-	if (!pde[index[1]].present)
-		goto unmapped_gva;
-
-	pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
-	if (!pte[index[0]].present)
-		goto unmapped_gva;
-
-	return (pte[index[0]].address * vm->page_size) + (gva & 0xfffu);
-
-unmapped_gva:
-	TEST_ASSERT(false, "No mapping for vm virtual address, "
-		    "gva: 0x%lx", gva);
-}
-
-static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt, int gdt_memslot,
-			  int pgd_memslot)
-{
-	if (!vm->gdt)
-		vm->gdt = vm_vaddr_alloc(vm, getpagesize(),
-			KVM_UTIL_MIN_VADDR, gdt_memslot, pgd_memslot);
-
-	dt->base = vm->gdt;
-	dt->limit = getpagesize();
-}
-
-static void kvm_setup_tss_64bit(struct kvm_vm *vm, struct kvm_segment *segp,
-				int selector, int gdt_memslot,
-				int pgd_memslot)
-{
-	if (!vm->tss)
-		vm->tss = vm_vaddr_alloc(vm, getpagesize(),
-			KVM_UTIL_MIN_VADDR, gdt_memslot, pgd_memslot);
-
-	memset(segp, 0, sizeof(*segp));
-	segp->base = vm->tss;
-	segp->limit = 0x67;
-	segp->selector = selector;
-	segp->type = 0xb;
-	segp->present = 1;
-	kvm_seg_fill_gdt_64bit(vm, segp);
-}
-
-void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot)
-{
-	struct kvm_sregs sregs;
-
-	/* Set mode specific system register values. */
-	vcpu_sregs_get(vm, vcpuid, &sregs);
-
-	sregs.idt.limit = 0;
-
-	kvm_setup_gdt(vm, &sregs.gdt, gdt_memslot, pgd_memslot);
-
-	switch (vm->mode) {
-	case VM_MODE_FLAT48PG:
-		sregs.cr0 = X86_CR0_PE | X86_CR0_NE | X86_CR0_PG;
-		sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR;
-		sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
-
-		kvm_seg_set_unusable(&sregs.ldt);
-		kvm_seg_set_kernel_code_64bit(vm, 0x8, &sregs.cs);
-		kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.ds);
-		kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.es);
-		kvm_setup_tss_64bit(vm, &sregs.tr, 0x18, gdt_memslot, pgd_memslot);
-		break;
-
-	default:
-		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", vm->mode);
-	}
-
-	sregs.cr3 = vm->pgd;
-	vcpu_sregs_set(vm, vcpuid, &sregs);
-}
-/* Adds a vCPU with reasonable defaults (i.e., a stack)
- *
- * Input Args:
- *   vcpuid - The id of the VCPU to add to the VM.
- *   guest_code - The vCPU's entry point
- */
-void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
-{
-	struct kvm_mp_state mp_state;
-	struct kvm_regs regs;
-	vm_vaddr_t stack_vaddr;
-	stack_vaddr = vm_vaddr_alloc(vm, DEFAULT_STACK_PGS * getpagesize(),
-				     DEFAULT_GUEST_STACK_VADDR_MIN, 0, 0);
-
-	/* Create VCPU */
-	vm_vcpu_add(vm, vcpuid, 0, 0);
-
-	/* Setup guest general purpose registers */
-	vcpu_regs_get(vm, vcpuid, &regs);
-	regs.rflags = regs.rflags | 0x2;
-	regs.rsp = stack_vaddr + (DEFAULT_STACK_PGS * getpagesize());
-	regs.rip = (unsigned long) guest_code;
-	vcpu_regs_set(vm, vcpuid, &regs);
-
-	/* Setup the MP state */
-	mp_state.mp_state = 0;
-	vcpu_set_mp_state(vm, vcpuid, &mp_state);
-}
-
-/* VM VCPU CPUID Set
- *
- * Input Args:
- *   vm - Virtual Machine
- *   vcpuid - VCPU id
- *   cpuid - The CPUID values to set.
- *
- * Output Args: None
- *
- * Return: void
- *
- * Set the VCPU's CPUID.
- */
-void vcpu_set_cpuid(struct kvm_vm *vm,
-		uint32_t vcpuid, struct kvm_cpuid2 *cpuid)
-{
-	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
-	int rc;
-
-	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
-
-	rc = ioctl(vcpu->fd, KVM_SET_CPUID2, cpuid);
-	TEST_ASSERT(rc == 0, "KVM_SET_CPUID2 failed, rc: %i errno: %i",
-		    rc, errno);
-
-}
-/* Create a VM with reasonable defaults
- *
- * Input Args:
- *   vcpuid - The id of the single VCPU to add to the VM.
- *   extra_mem_pages - The size of extra memories to add (this will
- *                     decide how much extra space we will need to
- *                     setup the page tables using mem slot 0)
- *   guest_code - The vCPU's entry point
- *
- * Output Args: None
- *
- * Return:
- *   Pointer to opaque structure that describes the created VM.
- */
-struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
-				 void *guest_code)
-{
-	struct kvm_vm *vm;
-	/*
-	 * For x86 the maximum page table size for a memory region
-	 * will be when only 4K pages are used.  In that case the
-	 * total extra size for page tables (for extra N pages) will
-	 * be: N/512+N/512^2+N/512^3+... which is definitely smaller
-	 * than N/512*2.
-	 */
-	uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
-
-	/* Create VM */
-	vm = vm_create(VM_MODE_FLAT48PG,
-		       DEFAULT_GUEST_PHY_PAGES + extra_pg_pages,
-		       O_RDWR);
-
-	/* Setup guest code */
-	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
-
-	/* Setup IRQ Chip */
-	vm_create_irqchip(vm);
-
-	/* Add the first vCPU. */
-	vm_vcpu_add_default(vm, vcpuid, guest_code);
-
-	return vm;
-}
-
-struct kvm_x86_state {
-	struct kvm_vcpu_events events;
-	struct kvm_mp_state mp_state;
-	struct kvm_regs regs;
-	struct kvm_xsave xsave;
-	struct kvm_xcrs xcrs;
-	struct kvm_sregs sregs;
-	struct kvm_debugregs debugregs;
-	union {
-		struct kvm_nested_state nested;
-		char nested_[16384];
-	};
-	struct kvm_msrs msrs;
-};
-
-static int kvm_get_num_msrs(struct kvm_vm *vm)
-{
-	struct kvm_msr_list nmsrs;
-	int r;
-
-	nmsrs.nmsrs = 0;
-	r = ioctl(vm->kvm_fd, KVM_GET_MSR_INDEX_LIST, &nmsrs);
-	TEST_ASSERT(r == -1 && errno == E2BIG, "Unexpected result from KVM_GET_MSR_INDEX_LIST probe, r: %i",
-		r);
-
-	return nmsrs.nmsrs;
-}
-
-struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
-{
-	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
-	struct kvm_msr_list *list;
-	struct kvm_x86_state *state;
-	int nmsrs, r, i;
-	static int nested_size = -1;
-
-	if (nested_size == -1) {
-		nested_size = kvm_check_cap(KVM_CAP_NESTED_STATE);
-		TEST_ASSERT(nested_size <= sizeof(state->nested_),
-			    "Nested state size too big, %i > %zi",
-			    nested_size, sizeof(state->nested_));
-	}
-
-	nmsrs = kvm_get_num_msrs(vm);
-	list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
-	list->nmsrs = nmsrs;
-	r = ioctl(vm->kvm_fd, KVM_GET_MSR_INDEX_LIST, list);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MSR_INDEX_LIST, r: %i",
-                r);
-
-	state = malloc(sizeof(*state) + nmsrs * sizeof(state->msrs.entries[0]));
-	r = ioctl(vcpu->fd, KVM_GET_VCPU_EVENTS, &state->events);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_VCPU_EVENTS, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_GET_MP_STATE, &state->mp_state);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MP_STATE, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_GET_REGS, &state->regs);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_REGS, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_GET_XSAVE, &state->xsave);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_GET_XCRS, &state->xcrs);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XCRS, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_GET_SREGS, &state->sregs);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i",
-                r);
-
-	if (nested_size) {
-		state->nested.size = sizeof(state->nested_);
-		r = ioctl(vcpu->fd, KVM_GET_NESTED_STATE, &state->nested);
-		TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_NESTED_STATE, r: %i",
-			r);
-		TEST_ASSERT(state->nested.size <= nested_size,
-			"Nested state size too big, %i (KVM_CHECK_CAP gave %i)",
-			state->nested.size, nested_size);
-	} else
-		state->nested.size = 0;
-
-	state->msrs.nmsrs = nmsrs;
-	for (i = 0; i < nmsrs; i++)
-		state->msrs.entries[i].index = list->indices[i];
-	r = ioctl(vcpu->fd, KVM_GET_MSRS, &state->msrs);
-        TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed at %x)",
-                r, r == nmsrs ? -1 : list->indices[r]);
-
-	r = ioctl(vcpu->fd, KVM_GET_DEBUGREGS, &state->debugregs);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_DEBUGREGS, r: %i",
-                r);
-
-	free(list);
-	return state;
-}
-
-void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *state)
-{
-	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
-	int r;
-
-	if (state->nested.size) {
-		r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested);
-		TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i",
-			r);
-	}
-
-	r = ioctl(vcpu->fd, KVM_SET_XSAVE, &state->xsave);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_SET_XCRS, &state->xcrs);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XCRS, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_SET_SREGS, &state->sregs);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_SET_MSRS, &state->msrs);
-        TEST_ASSERT(r == state->msrs.nmsrs, "Unexpected result from KVM_SET_MSRS, r: %i (failed at %x)",
-                r, r == state->msrs.nmsrs ? -1 : state->msrs.entries[r].index);
-
-	r = ioctl(vcpu->fd, KVM_SET_VCPU_EVENTS, &state->events);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_VCPU_EVENTS, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_SET_MP_STATE, &state->mp_state);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_MP_STATE, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_SET_DEBUGREGS, &state->debugregs);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_DEBUGREGS, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_SET_REGS, &state->regs);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i",
-                r);
-}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
new file mode 100644
index 000000000000..79c2c5c203c0
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -0,0 +1,888 @@
+/*
+ * tools/testing/selftests/kvm/lib/x86_64/processor.c
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_name */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "../kvm_util_internal.h"
+#include "processor.h"
+
+/* Minimum physical address used for virtual translation tables. */
+#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
+
+/* Virtual translation table structure declarations */
+struct pageMapL4Entry {
+	uint64_t present:1;
+	uint64_t writable:1;
+	uint64_t user:1;
+	uint64_t write_through:1;
+	uint64_t cache_disable:1;
+	uint64_t accessed:1;
+	uint64_t ignored_06:1;
+	uint64_t page_size:1;
+	uint64_t ignored_11_08:4;
+	uint64_t address:40;
+	uint64_t ignored_62_52:11;
+	uint64_t execute_disable:1;
+};
+
+struct pageDirectoryPointerEntry {
+	uint64_t present:1;
+	uint64_t writable:1;
+	uint64_t user:1;
+	uint64_t write_through:1;
+	uint64_t cache_disable:1;
+	uint64_t accessed:1;
+	uint64_t ignored_06:1;
+	uint64_t page_size:1;
+	uint64_t ignored_11_08:4;
+	uint64_t address:40;
+	uint64_t ignored_62_52:11;
+	uint64_t execute_disable:1;
+};
+
+struct pageDirectoryEntry {
+	uint64_t present:1;
+	uint64_t writable:1;
+	uint64_t user:1;
+	uint64_t write_through:1;
+	uint64_t cache_disable:1;
+	uint64_t accessed:1;
+	uint64_t ignored_06:1;
+	uint64_t page_size:1;
+	uint64_t ignored_11_08:4;
+	uint64_t address:40;
+	uint64_t ignored_62_52:11;
+	uint64_t execute_disable:1;
+};
+
+struct pageTableEntry {
+	uint64_t present:1;
+	uint64_t writable:1;
+	uint64_t user:1;
+	uint64_t write_through:1;
+	uint64_t cache_disable:1;
+	uint64_t accessed:1;
+	uint64_t dirty:1;
+	uint64_t reserved_07:1;
+	uint64_t global:1;
+	uint64_t ignored_11_09:3;
+	uint64_t address:40;
+	uint64_t ignored_62_52:11;
+	uint64_t execute_disable:1;
+};
+
+/* Register Dump
+ *
+ * Input Args:
+ *   indent - Left margin indent amount
+ *   regs - register
+ *
+ * Output Args:
+ *   stream - Output FILE stream
+ *
+ * Return: None
+ *
+ * Dumps the state of the registers given by regs, to the FILE stream
+ * given by steam.
+ */
+void regs_dump(FILE *stream, struct kvm_regs *regs,
+	       uint8_t indent)
+{
+	fprintf(stream, "%*srax: 0x%.16llx rbx: 0x%.16llx "
+		"rcx: 0x%.16llx rdx: 0x%.16llx\n",
+		indent, "",
+		regs->rax, regs->rbx, regs->rcx, regs->rdx);
+	fprintf(stream, "%*srsi: 0x%.16llx rdi: 0x%.16llx "
+		"rsp: 0x%.16llx rbp: 0x%.16llx\n",
+		indent, "",
+		regs->rsi, regs->rdi, regs->rsp, regs->rbp);
+	fprintf(stream, "%*sr8:  0x%.16llx r9:  0x%.16llx "
+		"r10: 0x%.16llx r11: 0x%.16llx\n",
+		indent, "",
+		regs->r8, regs->r9, regs->r10, regs->r11);
+	fprintf(stream, "%*sr12: 0x%.16llx r13: 0x%.16llx "
+		"r14: 0x%.16llx r15: 0x%.16llx\n",
+		indent, "",
+		regs->r12, regs->r13, regs->r14, regs->r15);
+	fprintf(stream, "%*srip: 0x%.16llx rfl: 0x%.16llx\n",
+		indent, "",
+		regs->rip, regs->rflags);
+}
+
+/* Segment Dump
+ *
+ * Input Args:
+ *   indent - Left margin indent amount
+ *   segment - KVM segment
+ *
+ * Output Args:
+ *   stream - Output FILE stream
+ *
+ * Return: None
+ *
+ * Dumps the state of the KVM segment given by segment, to the FILE stream
+ * given by steam.
+ */
+static void segment_dump(FILE *stream, struct kvm_segment *segment,
+			 uint8_t indent)
+{
+	fprintf(stream, "%*sbase: 0x%.16llx limit: 0x%.8x "
+		"selector: 0x%.4x type: 0x%.2x\n",
+		indent, "", segment->base, segment->limit,
+		segment->selector, segment->type);
+	fprintf(stream, "%*spresent: 0x%.2x dpl: 0x%.2x "
+		"db: 0x%.2x s: 0x%.2x l: 0x%.2x\n",
+		indent, "", segment->present, segment->dpl,
+		segment->db, segment->s, segment->l);
+	fprintf(stream, "%*sg: 0x%.2x avl: 0x%.2x "
+		"unusable: 0x%.2x padding: 0x%.2x\n",
+		indent, "", segment->g, segment->avl,
+		segment->unusable, segment->padding);
+}
+
+/* dtable Dump
+ *
+ * Input Args:
+ *   indent - Left margin indent amount
+ *   dtable - KVM dtable
+ *
+ * Output Args:
+ *   stream - Output FILE stream
+ *
+ * Return: None
+ *
+ * Dumps the state of the KVM dtable given by dtable, to the FILE stream
+ * given by steam.
+ */
+static void dtable_dump(FILE *stream, struct kvm_dtable *dtable,
+			uint8_t indent)
+{
+	fprintf(stream, "%*sbase: 0x%.16llx limit: 0x%.4x "
+		"padding: 0x%.4x 0x%.4x 0x%.4x\n",
+		indent, "", dtable->base, dtable->limit,
+		dtable->padding[0], dtable->padding[1], dtable->padding[2]);
+}
+
+/* System Register Dump
+ *
+ * Input Args:
+ *   indent - Left margin indent amount
+ *   sregs - System registers
+ *
+ * Output Args:
+ *   stream - Output FILE stream
+ *
+ * Return: None
+ *
+ * Dumps the state of the system registers given by sregs, to the FILE stream
+ * given by steam.
+ */
+void sregs_dump(FILE *stream, struct kvm_sregs *sregs,
+		uint8_t indent)
+{
+	unsigned int i;
+
+	fprintf(stream, "%*scs:\n", indent, "");
+	segment_dump(stream, &sregs->cs, indent + 2);
+	fprintf(stream, "%*sds:\n", indent, "");
+	segment_dump(stream, &sregs->ds, indent + 2);
+	fprintf(stream, "%*ses:\n", indent, "");
+	segment_dump(stream, &sregs->es, indent + 2);
+	fprintf(stream, "%*sfs:\n", indent, "");
+	segment_dump(stream, &sregs->fs, indent + 2);
+	fprintf(stream, "%*sgs:\n", indent, "");
+	segment_dump(stream, &sregs->gs, indent + 2);
+	fprintf(stream, "%*sss:\n", indent, "");
+	segment_dump(stream, &sregs->ss, indent + 2);
+	fprintf(stream, "%*str:\n", indent, "");
+	segment_dump(stream, &sregs->tr, indent + 2);
+	fprintf(stream, "%*sldt:\n", indent, "");
+	segment_dump(stream, &sregs->ldt, indent + 2);
+
+	fprintf(stream, "%*sgdt:\n", indent, "");
+	dtable_dump(stream, &sregs->gdt, indent + 2);
+	fprintf(stream, "%*sidt:\n", indent, "");
+	dtable_dump(stream, &sregs->idt, indent + 2);
+
+	fprintf(stream, "%*scr0: 0x%.16llx cr2: 0x%.16llx "
+		"cr3: 0x%.16llx cr4: 0x%.16llx\n",
+		indent, "",
+		sregs->cr0, sregs->cr2, sregs->cr3, sregs->cr4);
+	fprintf(stream, "%*scr8: 0x%.16llx efer: 0x%.16llx "
+		"apic_base: 0x%.16llx\n",
+		indent, "",
+		sregs->cr8, sregs->efer, sregs->apic_base);
+
+	fprintf(stream, "%*sinterrupt_bitmap:\n", indent, "");
+	for (i = 0; i < (KVM_NR_INTERRUPTS + 63) / 64; i++) {
+		fprintf(stream, "%*s%.16llx\n", indent + 2, "",
+			sregs->interrupt_bitmap[i]);
+	}
+}
+
+void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot)
+{
+	int rc;
+
+	TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
+		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+
+	/* If needed, create page map l4 table. */
+	if (!vm->pgd_created) {
+		vm_paddr_t paddr = vm_phy_page_alloc(vm,
+			KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
+		vm->pgd = paddr;
+		vm->pgd_created = true;
+	}
+}
+
+/* VM Virtual Page Map
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vaddr - VM Virtual Address
+ *   paddr - VM Physical Address
+ *   pgd_memslot - Memory region slot for new virtual translation tables
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Within the VM given by vm, creates a virtual translation for the page
+ * starting at vaddr to the page starting at paddr.
+ */
+void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+	uint32_t pgd_memslot)
+{
+	uint16_t index[4];
+	struct pageMapL4Entry *pml4e;
+
+	TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
+		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+
+	TEST_ASSERT((vaddr % vm->page_size) == 0,
+		"Virtual address not on page boundary,\n"
+		"  vaddr: 0x%lx vm->page_size: 0x%x",
+		vaddr, vm->page_size);
+	TEST_ASSERT(sparsebit_is_set(vm->vpages_valid,
+		(vaddr >> vm->page_shift)),
+		"Invalid virtual address, vaddr: 0x%lx",
+		vaddr);
+	TEST_ASSERT((paddr % vm->page_size) == 0,
+		"Physical address not on page boundary,\n"
+		"  paddr: 0x%lx vm->page_size: 0x%x",
+		paddr, vm->page_size);
+	TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn,
+		"Physical address beyond beyond maximum supported,\n"
+		"  paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
+		paddr, vm->max_gfn, vm->page_size);
+
+	index[0] = (vaddr >> 12) & 0x1ffu;
+	index[1] = (vaddr >> 21) & 0x1ffu;
+	index[2] = (vaddr >> 30) & 0x1ffu;
+	index[3] = (vaddr >> 39) & 0x1ffu;
+
+	/* Allocate page directory pointer table if not present. */
+	pml4e = addr_gpa2hva(vm, vm->pgd);
+	if (!pml4e[index[3]].present) {
+		pml4e[index[3]].address = vm_phy_page_alloc(vm,
+			KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot)
+			>> vm->page_shift;
+		pml4e[index[3]].writable = true;
+		pml4e[index[3]].present = true;
+	}
+
+	/* Allocate page directory table if not present. */
+	struct pageDirectoryPointerEntry *pdpe;
+	pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
+	if (!pdpe[index[2]].present) {
+		pdpe[index[2]].address = vm_phy_page_alloc(vm,
+			KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot)
+			>> vm->page_shift;
+		pdpe[index[2]].writable = true;
+		pdpe[index[2]].present = true;
+	}
+
+	/* Allocate page table if not present. */
+	struct pageDirectoryEntry *pde;
+	pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
+	if (!pde[index[1]].present) {
+		pde[index[1]].address = vm_phy_page_alloc(vm,
+			KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot)
+			>> vm->page_shift;
+		pde[index[1]].writable = true;
+		pde[index[1]].present = true;
+	}
+
+	/* Fill in page table entry. */
+	struct pageTableEntry *pte;
+	pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
+	pte[index[0]].address = paddr >> vm->page_shift;
+	pte[index[0]].writable = true;
+	pte[index[0]].present = 1;
+}
+
+/* Virtual Translation Tables Dump
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   indent - Left margin indent amount
+ *
+ * Output Args:
+ *   stream - Output FILE stream
+ *
+ * Return: None
+ *
+ * Dumps to the FILE stream given by stream, the contents of all the
+ * virtual translation tables for the VM given by vm.
+ */
+void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
+{
+	struct pageMapL4Entry *pml4e, *pml4e_start;
+	struct pageDirectoryPointerEntry *pdpe, *pdpe_start;
+	struct pageDirectoryEntry *pde, *pde_start;
+	struct pageTableEntry *pte, *pte_start;
+
+	if (!vm->pgd_created)
+		return;
+
+	fprintf(stream, "%*s                                          "
+		"                no\n", indent, "");
+	fprintf(stream, "%*s      index hvaddr         gpaddr         "
+		"addr         w exec dirty\n",
+		indent, "");
+	pml4e_start = (struct pageMapL4Entry *) addr_gpa2hva(vm,
+		vm->pgd);
+	for (uint16_t n1 = 0; n1 <= 0x1ffu; n1++) {
+		pml4e = &pml4e_start[n1];
+		if (!pml4e->present)
+			continue;
+		fprintf(stream, "%*spml4e 0x%-3zx %p 0x%-12lx 0x%-10lx %u "
+			" %u\n",
+			indent, "",
+			pml4e - pml4e_start, pml4e,
+			addr_hva2gpa(vm, pml4e), (uint64_t) pml4e->address,
+			pml4e->writable, pml4e->execute_disable);
+
+		pdpe_start = addr_gpa2hva(vm, pml4e->address
+			* vm->page_size);
+		for (uint16_t n2 = 0; n2 <= 0x1ffu; n2++) {
+			pdpe = &pdpe_start[n2];
+			if (!pdpe->present)
+				continue;
+			fprintf(stream, "%*spdpe  0x%-3zx %p 0x%-12lx 0x%-10lx "
+				"%u  %u\n",
+				indent, "",
+				pdpe - pdpe_start, pdpe,
+				addr_hva2gpa(vm, pdpe),
+				(uint64_t) pdpe->address, pdpe->writable,
+				pdpe->execute_disable);
+
+			pde_start = addr_gpa2hva(vm,
+				pdpe->address * vm->page_size);
+			for (uint16_t n3 = 0; n3 <= 0x1ffu; n3++) {
+				pde = &pde_start[n3];
+				if (!pde->present)
+					continue;
+				fprintf(stream, "%*spde   0x%-3zx %p "
+					"0x%-12lx 0x%-10lx %u  %u\n",
+					indent, "", pde - pde_start, pde,
+					addr_hva2gpa(vm, pde),
+					(uint64_t) pde->address, pde->writable,
+					pde->execute_disable);
+
+				pte_start = addr_gpa2hva(vm,
+					pde->address * vm->page_size);
+				for (uint16_t n4 = 0; n4 <= 0x1ffu; n4++) {
+					pte = &pte_start[n4];
+					if (!pte->present)
+						continue;
+					fprintf(stream, "%*spte   0x%-3zx %p "
+						"0x%-12lx 0x%-10lx %u  %u "
+						"    %u    0x%-10lx\n",
+						indent, "",
+						pte - pte_start, pte,
+						addr_hva2gpa(vm, pte),
+						(uint64_t) pte->address,
+						pte->writable,
+						pte->execute_disable,
+						pte->dirty,
+						((uint64_t) n1 << 27)
+							| ((uint64_t) n2 << 18)
+							| ((uint64_t) n3 << 9)
+							| ((uint64_t) n4));
+				}
+			}
+		}
+	}
+}
+
+/* Set Unusable Segment
+ *
+ * Input Args: None
+ *
+ * Output Args:
+ *   segp - Pointer to segment register
+ *
+ * Return: None
+ *
+ * Sets the segment register pointed to by segp to an unusable state.
+ */
+static void kvm_seg_set_unusable(struct kvm_segment *segp)
+{
+	memset(segp, 0, sizeof(*segp));
+	segp->unusable = true;
+}
+
+static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp)
+{
+	void *gdt = addr_gva2hva(vm, vm->gdt);
+	struct desc64 *desc = gdt + (segp->selector >> 3) * 8;
+
+	desc->limit0 = segp->limit & 0xFFFF;
+	desc->base0 = segp->base & 0xFFFF;
+	desc->base1 = segp->base >> 16;
+	desc->s = segp->s;
+	desc->type = segp->type;
+	desc->dpl = segp->dpl;
+	desc->p = segp->present;
+	desc->limit1 = segp->limit >> 16;
+	desc->l = segp->l;
+	desc->db = segp->db;
+	desc->g = segp->g;
+	desc->base2 = segp->base >> 24;
+	if (!segp->s)
+		desc->base3 = segp->base >> 32;
+}
+
+
+/* Set Long Mode Flat Kernel Code Segment
+ *
+ * Input Args:
+ *   vm - VM whose GDT is being filled, or NULL to only write segp
+ *   selector - selector value
+ *
+ * Output Args:
+ *   segp - Pointer to KVM segment
+ *
+ * Return: None
+ *
+ * Sets up the KVM segment pointed to by segp, to be a code segment
+ * with the selector value given by selector.
+ */
+static void kvm_seg_set_kernel_code_64bit(struct kvm_vm *vm, uint16_t selector,
+	struct kvm_segment *segp)
+{
+	memset(segp, 0, sizeof(*segp));
+	segp->selector = selector;
+	segp->limit = 0xFFFFFFFFu;
+	segp->s = 0x1; /* kTypeCodeData */
+	segp->type = 0x08 | 0x01 | 0x02; /* kFlagCode | kFlagCodeAccessed
+					  * | kFlagCodeReadable
+					  */
+	segp->g = true;
+	segp->l = true;
+	segp->present = 1;
+	if (vm)
+		kvm_seg_fill_gdt_64bit(vm, segp);
+}
+
+/* Set Long Mode Flat Kernel Data Segment
+ *
+ * Input Args:
+ *   vm - VM whose GDT is being filled, or NULL to only write segp
+ *   selector - selector value
+ *
+ * Output Args:
+ *   segp - Pointer to KVM segment
+ *
+ * Return: None
+ *
+ * Sets up the KVM segment pointed to by segp, to be a data segment
+ * with the selector value given by selector.
+ */
+static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector,
+	struct kvm_segment *segp)
+{
+	memset(segp, 0, sizeof(*segp));
+	segp->selector = selector;
+	segp->limit = 0xFFFFFFFFu;
+	segp->s = 0x1; /* kTypeCodeData */
+	segp->type = 0x00 | 0x01 | 0x02; /* kFlagData | kFlagDataAccessed
+					  * | kFlagDataWritable
+					  */
+	segp->g = true;
+	segp->present = true;
+	if (vm)
+		kvm_seg_fill_gdt_64bit(vm, segp);
+}
+
+/* Address Guest Virtual to Guest Physical
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   gpa - VM virtual address
+ *
+ * Output Args: None
+ *
+ * Return:
+ *   Equivalent VM physical address
+ *
+ * Translates the VM virtual address given by gva to a VM physical
+ * address and then locates the memory region containing the VM
+ * physical address, within the VM given by vm.  When found, the host
+ * virtual address providing the memory to the vm physical address is returned.
+ * A TEST_ASSERT failure occurs if no region containing translated
+ * VM virtual address exists.
+ */
+vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+	uint16_t index[4];
+	struct pageMapL4Entry *pml4e;
+	struct pageDirectoryPointerEntry *pdpe;
+	struct pageDirectoryEntry *pde;
+	struct pageTableEntry *pte;
+	void *hva;
+
+	TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
+		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+
+	index[0] = (gva >> 12) & 0x1ffu;
+	index[1] = (gva >> 21) & 0x1ffu;
+	index[2] = (gva >> 30) & 0x1ffu;
+	index[3] = (gva >> 39) & 0x1ffu;
+
+	if (!vm->pgd_created)
+		goto unmapped_gva;
+	pml4e = addr_gpa2hva(vm, vm->pgd);
+	if (!pml4e[index[3]].present)
+		goto unmapped_gva;
+
+	pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
+	if (!pdpe[index[2]].present)
+		goto unmapped_gva;
+
+	pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
+	if (!pde[index[1]].present)
+		goto unmapped_gva;
+
+	pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
+	if (!pte[index[0]].present)
+		goto unmapped_gva;
+
+	return (pte[index[0]].address * vm->page_size) + (gva & 0xfffu);
+
+unmapped_gva:
+	TEST_ASSERT(false, "No mapping for vm virtual address, "
+		    "gva: 0x%lx", gva);
+}
+
+static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt, int gdt_memslot,
+			  int pgd_memslot)
+{
+	if (!vm->gdt)
+		vm->gdt = vm_vaddr_alloc(vm, getpagesize(),
+			KVM_UTIL_MIN_VADDR, gdt_memslot, pgd_memslot);
+
+	dt->base = vm->gdt;
+	dt->limit = getpagesize();
+}
+
+static void kvm_setup_tss_64bit(struct kvm_vm *vm, struct kvm_segment *segp,
+				int selector, int gdt_memslot,
+				int pgd_memslot)
+{
+	if (!vm->tss)
+		vm->tss = vm_vaddr_alloc(vm, getpagesize(),
+			KVM_UTIL_MIN_VADDR, gdt_memslot, pgd_memslot);
+
+	memset(segp, 0, sizeof(*segp));
+	segp->base = vm->tss;
+	segp->limit = 0x67;
+	segp->selector = selector;
+	segp->type = 0xb;
+	segp->present = 1;
+	kvm_seg_fill_gdt_64bit(vm, segp);
+}
+
+void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot)
+{
+	struct kvm_sregs sregs;
+
+	/* Set mode specific system register values. */
+	vcpu_sregs_get(vm, vcpuid, &sregs);
+
+	sregs.idt.limit = 0;
+
+	kvm_setup_gdt(vm, &sregs.gdt, gdt_memslot, pgd_memslot);
+
+	switch (vm->mode) {
+	case VM_MODE_FLAT48PG:
+		sregs.cr0 = X86_CR0_PE | X86_CR0_NE | X86_CR0_PG;
+		sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR;
+		sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
+
+		kvm_seg_set_unusable(&sregs.ldt);
+		kvm_seg_set_kernel_code_64bit(vm, 0x8, &sregs.cs);
+		kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.ds);
+		kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.es);
+		kvm_setup_tss_64bit(vm, &sregs.tr, 0x18, gdt_memslot, pgd_memslot);
+		break;
+
+	default:
+		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", vm->mode);
+	}
+
+	sregs.cr3 = vm->pgd;
+	vcpu_sregs_set(vm, vcpuid, &sregs);
+}
+/* Adds a vCPU with reasonable defaults (i.e., a stack)
+ *
+ * Input Args:
+ *   vcpuid - The id of the VCPU to add to the VM.
+ *   guest_code - The vCPU's entry point
+ */
+void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
+{
+	struct kvm_mp_state mp_state;
+	struct kvm_regs regs;
+	vm_vaddr_t stack_vaddr;
+	stack_vaddr = vm_vaddr_alloc(vm, DEFAULT_STACK_PGS * getpagesize(),
+				     DEFAULT_GUEST_STACK_VADDR_MIN, 0, 0);
+
+	/* Create VCPU */
+	vm_vcpu_add(vm, vcpuid, 0, 0);
+
+	/* Setup guest general purpose registers */
+	vcpu_regs_get(vm, vcpuid, &regs);
+	regs.rflags = regs.rflags | 0x2;
+	regs.rsp = stack_vaddr + (DEFAULT_STACK_PGS * getpagesize());
+	regs.rip = (unsigned long) guest_code;
+	vcpu_regs_set(vm, vcpuid, &regs);
+
+	/* Setup the MP state */
+	mp_state.mp_state = 0;
+	vcpu_set_mp_state(vm, vcpuid, &mp_state);
+}
+
+/* VM VCPU CPUID Set
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpuid - VCPU id
+ *   cpuid - The CPUID values to set.
+ *
+ * Output Args: None
+ *
+ * Return: void
+ *
+ * Set the VCPU's CPUID.
+ */
+void vcpu_set_cpuid(struct kvm_vm *vm,
+		uint32_t vcpuid, struct kvm_cpuid2 *cpuid)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+	int rc;
+
+	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+	rc = ioctl(vcpu->fd, KVM_SET_CPUID2, cpuid);
+	TEST_ASSERT(rc == 0, "KVM_SET_CPUID2 failed, rc: %i errno: %i",
+		    rc, errno);
+
+}
+/* Create a VM with reasonable defaults
+ *
+ * Input Args:
+ *   vcpuid - The id of the single VCPU to add to the VM.
+ *   extra_mem_pages - The size of extra memories to add (this will
+ *                     decide how much extra space we will need to
+ *                     setup the page tables using mem slot 0)
+ *   guest_code - The vCPU's entry point
+ *
+ * Output Args: None
+ *
+ * Return:
+ *   Pointer to opaque structure that describes the created VM.
+ */
+struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
+				 void *guest_code)
+{
+	struct kvm_vm *vm;
+	/*
+	 * For x86 the maximum page table size for a memory region
+	 * will be when only 4K pages are used.  In that case the
+	 * total extra size for page tables (for extra N pages) will
+	 * be: N/512+N/512^2+N/512^3+... which is definitely smaller
+	 * than N/512*2.
+	 */
+	uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
+
+	/* Create VM */
+	vm = vm_create(VM_MODE_FLAT48PG,
+		       DEFAULT_GUEST_PHY_PAGES + extra_pg_pages,
+		       O_RDWR);
+
+	/* Setup guest code */
+	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+
+	/* Setup IRQ Chip */
+	vm_create_irqchip(vm);
+
+	/* Add the first vCPU. */
+	vm_vcpu_add_default(vm, vcpuid, guest_code);
+
+	return vm;
+}
+
+struct kvm_x86_state {
+	struct kvm_vcpu_events events;
+	struct kvm_mp_state mp_state;
+	struct kvm_regs regs;
+	struct kvm_xsave xsave;
+	struct kvm_xcrs xcrs;
+	struct kvm_sregs sregs;
+	struct kvm_debugregs debugregs;
+	union {
+		struct kvm_nested_state nested;
+		char nested_[16384];
+	};
+	struct kvm_msrs msrs;
+};
+
+static int kvm_get_num_msrs(struct kvm_vm *vm)
+{
+	struct kvm_msr_list nmsrs;
+	int r;
+
+	nmsrs.nmsrs = 0;
+	r = ioctl(vm->kvm_fd, KVM_GET_MSR_INDEX_LIST, &nmsrs);
+	TEST_ASSERT(r == -1 && errno == E2BIG, "Unexpected result from KVM_GET_MSR_INDEX_LIST probe, r: %i",
+		r);
+
+	return nmsrs.nmsrs;
+}
+
+struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+	struct kvm_msr_list *list;
+	struct kvm_x86_state *state;
+	int nmsrs, r, i;
+	static int nested_size = -1;
+
+	if (nested_size == -1) {
+		nested_size = kvm_check_cap(KVM_CAP_NESTED_STATE);
+		TEST_ASSERT(nested_size <= sizeof(state->nested_),
+			    "Nested state size too big, %i > %zi",
+			    nested_size, sizeof(state->nested_));
+	}
+
+	nmsrs = kvm_get_num_msrs(vm);
+	list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
+	list->nmsrs = nmsrs;
+	r = ioctl(vm->kvm_fd, KVM_GET_MSR_INDEX_LIST, list);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MSR_INDEX_LIST, r: %i",
+                r);
+
+	state = malloc(sizeof(*state) + nmsrs * sizeof(state->msrs.entries[0]));
+	r = ioctl(vcpu->fd, KVM_GET_VCPU_EVENTS, &state->events);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_VCPU_EVENTS, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_GET_MP_STATE, &state->mp_state);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MP_STATE, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_GET_REGS, &state->regs);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_REGS, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_GET_XSAVE, &state->xsave);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_GET_XCRS, &state->xcrs);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XCRS, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_GET_SREGS, &state->sregs);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i",
+                r);
+
+	if (nested_size) {
+		state->nested.size = sizeof(state->nested_);
+		r = ioctl(vcpu->fd, KVM_GET_NESTED_STATE, &state->nested);
+		TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_NESTED_STATE, r: %i",
+			r);
+		TEST_ASSERT(state->nested.size <= nested_size,
+			"Nested state size too big, %i (KVM_CHECK_CAP gave %i)",
+			state->nested.size, nested_size);
+	} else
+		state->nested.size = 0;
+
+	state->msrs.nmsrs = nmsrs;
+	for (i = 0; i < nmsrs; i++)
+		state->msrs.entries[i].index = list->indices[i];
+	r = ioctl(vcpu->fd, KVM_GET_MSRS, &state->msrs);
+        TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed at %x)",
+                r, r == nmsrs ? -1 : list->indices[r]);
+
+	r = ioctl(vcpu->fd, KVM_GET_DEBUGREGS, &state->debugregs);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_DEBUGREGS, r: %i",
+                r);
+
+	free(list);
+	return state;
+}
+
+void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *state)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+	int r;
+
+	if (state->nested.size) {
+		r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested);
+		TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i",
+			r);
+	}
+
+	r = ioctl(vcpu->fd, KVM_SET_XSAVE, &state->xsave);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_SET_XCRS, &state->xcrs);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XCRS, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_SET_SREGS, &state->sregs);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_SET_MSRS, &state->msrs);
+        TEST_ASSERT(r == state->msrs.nmsrs, "Unexpected result from KVM_SET_MSRS, r: %i (failed at %x)",
+                r, r == state->msrs.nmsrs ? -1 : state->msrs.entries[r].index);
+
+	r = ioctl(vcpu->fd, KVM_SET_VCPU_EVENTS, &state->events);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_VCPU_EVENTS, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_SET_MP_STATE, &state->mp_state);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_MP_STATE, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_SET_DEBUGREGS, &state->debugregs);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_DEBUGREGS, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_SET_REGS, &state->regs);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i",
+                r);
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
new file mode 100644
index 000000000000..d7c401472247
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -0,0 +1,283 @@
+/*
+ * tools/testing/selftests/kvm/lib/x86_64/vmx.c
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_name */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "vmx.h"
+
+/* Allocate memory regions for nested VMX tests.
+ *
+ * Input Args:
+ *   vm - The VM to allocate guest-virtual addresses in.
+ *
+ * Output Args:
+ *   p_vmx_gva - The guest virtual address for the struct vmx_pages.
+ *
+ * Return:
+ *   Pointer to structure with the addresses of the VMX areas.
+ */
+struct vmx_pages *
+vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva)
+{
+	vm_vaddr_t vmx_gva = vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+	struct vmx_pages *vmx = addr_gva2hva(vm, vmx_gva);
+
+	/* Setup of a region of guest memory for the vmxon region. */
+	vmx->vmxon = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+	vmx->vmxon_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmxon);
+	vmx->vmxon_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmxon);
+
+	/* Setup of a region of guest memory for a vmcs. */
+	vmx->vmcs = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+	vmx->vmcs_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmcs);
+	vmx->vmcs_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmcs);
+
+	/* Setup of a region of guest memory for the MSR bitmap. */
+	vmx->msr = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+	vmx->msr_hva = addr_gva2hva(vm, (uintptr_t)vmx->msr);
+	vmx->msr_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->msr);
+	memset(vmx->msr_hva, 0, getpagesize());
+
+	/* Setup of a region of guest memory for the shadow VMCS. */
+	vmx->shadow_vmcs = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+	vmx->shadow_vmcs_hva = addr_gva2hva(vm, (uintptr_t)vmx->shadow_vmcs);
+	vmx->shadow_vmcs_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->shadow_vmcs);
+
+	/* Setup of a region of guest memory for the VMREAD and VMWRITE bitmaps. */
+	vmx->vmread = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+	vmx->vmread_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmread);
+	vmx->vmread_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmread);
+	memset(vmx->vmread_hva, 0, getpagesize());
+
+	vmx->vmwrite = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+	vmx->vmwrite_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmwrite);
+	vmx->vmwrite_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmwrite);
+	memset(vmx->vmwrite_hva, 0, getpagesize());
+
+	*p_vmx_gva = vmx_gva;
+	return vmx;
+}
+
+bool prepare_for_vmx_operation(struct vmx_pages *vmx)
+{
+	uint64_t feature_control;
+	uint64_t required;
+	unsigned long cr0;
+	unsigned long cr4;
+
+	/*
+	 * Ensure bits in CR0 and CR4 are valid in VMX operation:
+	 * - Bit X is 1 in _FIXED0: bit X is fixed to 1 in CRx.
+	 * - Bit X is 0 in _FIXED1: bit X is fixed to 0 in CRx.
+	 */
+	__asm__ __volatile__("mov %%cr0, %0" : "=r"(cr0) : : "memory");
+	cr0 &= rdmsr(MSR_IA32_VMX_CR0_FIXED1);
+	cr0 |= rdmsr(MSR_IA32_VMX_CR0_FIXED0);
+	__asm__ __volatile__("mov %0, %%cr0" : : "r"(cr0) : "memory");
+
+	__asm__ __volatile__("mov %%cr4, %0" : "=r"(cr4) : : "memory");
+	cr4 &= rdmsr(MSR_IA32_VMX_CR4_FIXED1);
+	cr4 |= rdmsr(MSR_IA32_VMX_CR4_FIXED0);
+	/* Enable VMX operation */
+	cr4 |= X86_CR4_VMXE;
+	__asm__ __volatile__("mov %0, %%cr4" : : "r"(cr4) : "memory");
+
+	/*
+	 * Configure IA32_FEATURE_CONTROL MSR to allow VMXON:
+	 *  Bit 0: Lock bit. If clear, VMXON causes a #GP.
+	 *  Bit 2: Enables VMXON outside of SMX operation. If clear, VMXON
+	 *    outside of SMX causes a #GP.
+	 */
+	required = FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+	required |= FEATURE_CONTROL_LOCKED;
+	feature_control = rdmsr(MSR_IA32_FEATURE_CONTROL);
+	if ((feature_control & required) != required)
+		wrmsr(MSR_IA32_FEATURE_CONTROL, feature_control | required);
+
+	/* Enter VMX root operation. */
+	*(uint32_t *)(vmx->vmxon) = vmcs_revision();
+	if (vmxon(vmx->vmxon_gpa))
+		return false;
+
+	/* Load a VMCS. */
+	*(uint32_t *)(vmx->vmcs) = vmcs_revision();
+	if (vmclear(vmx->vmcs_gpa))
+		return false;
+
+	if (vmptrld(vmx->vmcs_gpa))
+		return false;
+
+	/* Setup shadow VMCS, do not load it yet. */
+	*(uint32_t *)(vmx->shadow_vmcs) = vmcs_revision() | 0x80000000ul;
+	if (vmclear(vmx->shadow_vmcs_gpa))
+		return false;
+
+	return true;
+}
+
+/*
+ * Initialize the control fields to the most basic settings possible.
+ */
+static inline void init_vmcs_control_fields(struct vmx_pages *vmx)
+{
+	vmwrite(VIRTUAL_PROCESSOR_ID, 0);
+	vmwrite(POSTED_INTR_NV, 0);
+
+	vmwrite(PIN_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PINBASED_CTLS));
+	if (!vmwrite(SECONDARY_VM_EXEC_CONTROL, 0))
+		vmwrite(CPU_BASED_VM_EXEC_CONTROL,
+			rdmsr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS) | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS);
+	else
+		vmwrite(CPU_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS));
+	vmwrite(EXCEPTION_BITMAP, 0);
+	vmwrite(PAGE_FAULT_ERROR_CODE_MASK, 0);
+	vmwrite(PAGE_FAULT_ERROR_CODE_MATCH, -1); /* Never match */
+	vmwrite(CR3_TARGET_COUNT, 0);
+	vmwrite(VM_EXIT_CONTROLS, rdmsr(MSR_IA32_VMX_EXIT_CTLS) |
+		VM_EXIT_HOST_ADDR_SPACE_SIZE);	  /* 64-bit host */
+	vmwrite(VM_EXIT_MSR_STORE_COUNT, 0);
+	vmwrite(VM_EXIT_MSR_LOAD_COUNT, 0);
+	vmwrite(VM_ENTRY_CONTROLS, rdmsr(MSR_IA32_VMX_ENTRY_CTLS) |
+		VM_ENTRY_IA32E_MODE);		  /* 64-bit guest */
+	vmwrite(VM_ENTRY_MSR_LOAD_COUNT, 0);
+	vmwrite(VM_ENTRY_INTR_INFO_FIELD, 0);
+	vmwrite(TPR_THRESHOLD, 0);
+
+	vmwrite(CR0_GUEST_HOST_MASK, 0);
+	vmwrite(CR4_GUEST_HOST_MASK, 0);
+	vmwrite(CR0_READ_SHADOW, get_cr0());
+	vmwrite(CR4_READ_SHADOW, get_cr4());
+
+	vmwrite(MSR_BITMAP, vmx->msr_gpa);
+	vmwrite(VMREAD_BITMAP, vmx->vmread_gpa);
+	vmwrite(VMWRITE_BITMAP, vmx->vmwrite_gpa);
+}
+
+/*
+ * Initialize the host state fields based on the current host state, with
+ * the exception of HOST_RSP and HOST_RIP, which should be set by vmlaunch
+ * or vmresume.
+ */
+static inline void init_vmcs_host_state(void)
+{
+	uint32_t exit_controls = vmreadz(VM_EXIT_CONTROLS);
+
+	vmwrite(HOST_ES_SELECTOR, get_es());
+	vmwrite(HOST_CS_SELECTOR, get_cs());
+	vmwrite(HOST_SS_SELECTOR, get_ss());
+	vmwrite(HOST_DS_SELECTOR, get_ds());
+	vmwrite(HOST_FS_SELECTOR, get_fs());
+	vmwrite(HOST_GS_SELECTOR, get_gs());
+	vmwrite(HOST_TR_SELECTOR, get_tr());
+
+	if (exit_controls & VM_EXIT_LOAD_IA32_PAT)
+		vmwrite(HOST_IA32_PAT, rdmsr(MSR_IA32_CR_PAT));
+	if (exit_controls & VM_EXIT_LOAD_IA32_EFER)
+		vmwrite(HOST_IA32_EFER, rdmsr(MSR_EFER));
+	if (exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
+		vmwrite(HOST_IA32_PERF_GLOBAL_CTRL,
+			rdmsr(MSR_CORE_PERF_GLOBAL_CTRL));
+
+	vmwrite(HOST_IA32_SYSENTER_CS, rdmsr(MSR_IA32_SYSENTER_CS));
+
+	vmwrite(HOST_CR0, get_cr0());
+	vmwrite(HOST_CR3, get_cr3());
+	vmwrite(HOST_CR4, get_cr4());
+	vmwrite(HOST_FS_BASE, rdmsr(MSR_FS_BASE));
+	vmwrite(HOST_GS_BASE, rdmsr(MSR_GS_BASE));
+	vmwrite(HOST_TR_BASE,
+		get_desc64_base((struct desc64 *)(get_gdt_base() + get_tr())));
+	vmwrite(HOST_GDTR_BASE, get_gdt_base());
+	vmwrite(HOST_IDTR_BASE, get_idt_base());
+	vmwrite(HOST_IA32_SYSENTER_ESP, rdmsr(MSR_IA32_SYSENTER_ESP));
+	vmwrite(HOST_IA32_SYSENTER_EIP, rdmsr(MSR_IA32_SYSENTER_EIP));
+}
+
+/*
+ * Initialize the guest state fields essentially as a clone of
+ * the host state fields. Some host state fields have fixed
+ * values, and we set the corresponding guest state fields accordingly.
+ */
+static inline void init_vmcs_guest_state(void *rip, void *rsp)
+{
+	vmwrite(GUEST_ES_SELECTOR, vmreadz(HOST_ES_SELECTOR));
+	vmwrite(GUEST_CS_SELECTOR, vmreadz(HOST_CS_SELECTOR));
+	vmwrite(GUEST_SS_SELECTOR, vmreadz(HOST_SS_SELECTOR));
+	vmwrite(GUEST_DS_SELECTOR, vmreadz(HOST_DS_SELECTOR));
+	vmwrite(GUEST_FS_SELECTOR, vmreadz(HOST_FS_SELECTOR));
+	vmwrite(GUEST_GS_SELECTOR, vmreadz(HOST_GS_SELECTOR));
+	vmwrite(GUEST_LDTR_SELECTOR, 0);
+	vmwrite(GUEST_TR_SELECTOR, vmreadz(HOST_TR_SELECTOR));
+	vmwrite(GUEST_INTR_STATUS, 0);
+	vmwrite(GUEST_PML_INDEX, 0);
+
+	vmwrite(VMCS_LINK_POINTER, -1ll);
+	vmwrite(GUEST_IA32_DEBUGCTL, 0);
+	vmwrite(GUEST_IA32_PAT, vmreadz(HOST_IA32_PAT));
+	vmwrite(GUEST_IA32_EFER, vmreadz(HOST_IA32_EFER));
+	vmwrite(GUEST_IA32_PERF_GLOBAL_CTRL,
+		vmreadz(HOST_IA32_PERF_GLOBAL_CTRL));
+
+	vmwrite(GUEST_ES_LIMIT, -1);
+	vmwrite(GUEST_CS_LIMIT, -1);
+	vmwrite(GUEST_SS_LIMIT, -1);
+	vmwrite(GUEST_DS_LIMIT, -1);
+	vmwrite(GUEST_FS_LIMIT, -1);
+	vmwrite(GUEST_GS_LIMIT, -1);
+	vmwrite(GUEST_LDTR_LIMIT, -1);
+	vmwrite(GUEST_TR_LIMIT, 0x67);
+	vmwrite(GUEST_GDTR_LIMIT, 0xffff);
+	vmwrite(GUEST_IDTR_LIMIT, 0xffff);
+	vmwrite(GUEST_ES_AR_BYTES,
+		vmreadz(GUEST_ES_SELECTOR) == 0 ? 0x10000 : 0xc093);
+	vmwrite(GUEST_CS_AR_BYTES, 0xa09b);
+	vmwrite(GUEST_SS_AR_BYTES, 0xc093);
+	vmwrite(GUEST_DS_AR_BYTES,
+		vmreadz(GUEST_DS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+	vmwrite(GUEST_FS_AR_BYTES,
+		vmreadz(GUEST_FS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+	vmwrite(GUEST_GS_AR_BYTES,
+		vmreadz(GUEST_GS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+	vmwrite(GUEST_LDTR_AR_BYTES, 0x10000);
+	vmwrite(GUEST_TR_AR_BYTES, 0x8b);
+	vmwrite(GUEST_INTERRUPTIBILITY_INFO, 0);
+	vmwrite(GUEST_ACTIVITY_STATE, 0);
+	vmwrite(GUEST_SYSENTER_CS, vmreadz(HOST_IA32_SYSENTER_CS));
+	vmwrite(VMX_PREEMPTION_TIMER_VALUE, 0);
+
+	vmwrite(GUEST_CR0, vmreadz(HOST_CR0));
+	vmwrite(GUEST_CR3, vmreadz(HOST_CR3));
+	vmwrite(GUEST_CR4, vmreadz(HOST_CR4));
+	vmwrite(GUEST_ES_BASE, 0);
+	vmwrite(GUEST_CS_BASE, 0);
+	vmwrite(GUEST_SS_BASE, 0);
+	vmwrite(GUEST_DS_BASE, 0);
+	vmwrite(GUEST_FS_BASE, vmreadz(HOST_FS_BASE));
+	vmwrite(GUEST_GS_BASE, vmreadz(HOST_GS_BASE));
+	vmwrite(GUEST_LDTR_BASE, 0);
+	vmwrite(GUEST_TR_BASE, vmreadz(HOST_TR_BASE));
+	vmwrite(GUEST_GDTR_BASE, vmreadz(HOST_GDTR_BASE));
+	vmwrite(GUEST_IDTR_BASE, vmreadz(HOST_IDTR_BASE));
+	vmwrite(GUEST_DR7, 0x400);
+	vmwrite(GUEST_RSP, (uint64_t)rsp);
+	vmwrite(GUEST_RIP, (uint64_t)rip);
+	vmwrite(GUEST_RFLAGS, 2);
+	vmwrite(GUEST_PENDING_DBG_EXCEPTIONS, 0);
+	vmwrite(GUEST_SYSENTER_ESP, vmreadz(HOST_IA32_SYSENTER_ESP));
+	vmwrite(GUEST_SYSENTER_EIP, vmreadz(HOST_IA32_SYSENTER_EIP));
+}
+
+void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp)
+{
+	init_vmcs_control_fields(vmx);
+	init_vmcs_host_state();
+	init_vmcs_guest_state(guest_rip, guest_rsp);
+}
diff --git a/tools/testing/selftests/kvm/platform_info_test.c b/tools/testing/selftests/kvm/platform_info_test.c
deleted file mode 100644
index aa6a14331461..000000000000
--- a/tools/testing/selftests/kvm/platform_info_test.c
+++ /dev/null
@@ -1,110 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Test for x86 KVM_CAP_MSR_PLATFORM_INFO
- *
- * Copyright (C) 2018, Google LLC.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- *
- * Verifies expected behavior of controlling guest access to
- * MSR_PLATFORM_INFO.
- */
-
-#define _GNU_SOURCE /* for program_invocation_short_name */
-#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 "x86.h"
-
-#define VCPU_ID 0
-#define MSR_PLATFORM_INFO_MAX_TURBO_RATIO 0xff00
-
-static void guest_code(void)
-{
-	uint64_t msr_platform_info;
-
-	for (;;) {
-		msr_platform_info = rdmsr(MSR_PLATFORM_INFO);
-		GUEST_SYNC(msr_platform_info);
-		asm volatile ("inc %r11");
-	}
-}
-
-static void set_msr_platform_info_enabled(struct kvm_vm *vm, bool enable)
-{
-	struct kvm_enable_cap cap = {};
-
-	cap.cap = KVM_CAP_MSR_PLATFORM_INFO;
-	cap.flags = 0;
-	cap.args[0] = (int)enable;
-	vm_enable_cap(vm, &cap);
-}
-
-static void test_msr_platform_info_enabled(struct kvm_vm *vm)
-{
-	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
-	struct ucall uc;
-
-	set_msr_platform_info_enabled(vm, true);
-	vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-			"Exit_reason other than KVM_EXIT_IO: %u (%s),\n",
-			run->exit_reason,
-			exit_reason_str(run->exit_reason));
-	get_ucall(vm, VCPU_ID, &uc);
-	TEST_ASSERT(uc.cmd == UCALL_SYNC,
-			"Received ucall other than UCALL_SYNC: %u\n",
-			ucall);
-	TEST_ASSERT((uc.args[1] & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) ==
-		MSR_PLATFORM_INFO_MAX_TURBO_RATIO,
-		"Expected MSR_PLATFORM_INFO to have max turbo ratio mask: %i.",
-		MSR_PLATFORM_INFO_MAX_TURBO_RATIO);
-}
-
-static void test_msr_platform_info_disabled(struct kvm_vm *vm)
-{
-	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
-
-	set_msr_platform_info_enabled(vm, false);
-	vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN,
-			"Exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n",
-			run->exit_reason,
-			exit_reason_str(run->exit_reason));
-}
-
-int main(int argc, char *argv[])
-{
-	struct kvm_vm *vm;
-	struct kvm_run *state;
-	int rv;
-	uint64_t msr_platform_info;
-
-	/* Tell stdout not to buffer its content */
-	setbuf(stdout, NULL);
-
-	rv = kvm_check_cap(KVM_CAP_MSR_PLATFORM_INFO);
-	if (!rv) {
-		fprintf(stderr,
-			"KVM_CAP_MSR_PLATFORM_INFO not supported, skip test\n");
-		exit(KSFT_SKIP);
-	}
-
-	vm = vm_create_default(VCPU_ID, 0, guest_code);
-
-	msr_platform_info = vcpu_get_msr(vm, VCPU_ID, MSR_PLATFORM_INFO);
-	vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO,
-		msr_platform_info | MSR_PLATFORM_INFO_MAX_TURBO_RATIO);
-	test_msr_platform_info_disabled(vm);
-	test_msr_platform_info_enabled(vm);
-	vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, msr_platform_info);
-
-	kvm_vm_free(vm);
-
-	return 0;
-}
diff --git a/tools/testing/selftests/kvm/set_sregs_test.c b/tools/testing/selftests/kvm/set_sregs_test.c
deleted file mode 100644
index 881419d5746e..000000000000
--- a/tools/testing/selftests/kvm/set_sregs_test.c
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- * KVM_SET_SREGS tests
- *
- * Copyright (C) 2018, Google LLC.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- *
- * This is a regression test for the bug fixed by the following commit:
- * d3802286fa0f ("kvm: x86: Disallow illegal IA32_APIC_BASE MSR values")
- *
- * That bug allowed a user-mode program that called the KVM_SET_SREGS
- * ioctl to put a VCPU's local APIC into an invalid state.
- *
- */
-#define _GNU_SOURCE /* for program_invocation_short_name */
-#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 "x86.h"
-
-#define VCPU_ID                  5
-
-int main(int argc, char *argv[])
-{
-	struct kvm_sregs sregs;
-	struct kvm_vm *vm;
-	int rc;
-
-	/* Tell stdout not to buffer its content */
-	setbuf(stdout, NULL);
-
-	/* Create VM */
-	vm = vm_create_default(VCPU_ID, 0, NULL);
-
-	vcpu_sregs_get(vm, VCPU_ID, &sregs);
-	sregs.apic_base = 1 << 10;
-	rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs);
-	TEST_ASSERT(rc, "Set IA32_APIC_BASE to %llx (invalid)",
-		    sregs.apic_base);
-	sregs.apic_base = 1 << 11;
-	rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs);
-	TEST_ASSERT(!rc, "Couldn't set IA32_APIC_BASE to %llx (valid)",
-		    sregs.apic_base);
-
-	kvm_vm_free(vm);
-
-	return 0;
-}
diff --git a/tools/testing/selftests/kvm/state_test.c b/tools/testing/selftests/kvm/state_test.c
deleted file mode 100644
index cdf82735d6e7..000000000000
--- a/tools/testing/selftests/kvm/state_test.c
+++ /dev/null
@@ -1,197 +0,0 @@
-/*
- * KVM_GET/SET_* tests
- *
- * Copyright (C) 2018, Red Hat, Inc.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- *
- * Tests for vCPU state save/restore, including nested guest state.
- */
-#define _GNU_SOURCE /* for program_invocation_short_name */
-#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 "x86.h"
-#include "vmx.h"
-
-#define VCPU_ID		5
-
-static bool have_nested_state;
-
-void l2_guest_code(void)
-{
-	GUEST_SYNC(5);
-
-        /* Exit to L1 */
-	vmcall();
-
-	/* L1 has now set up a shadow VMCS for us.  */
-	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
-	GUEST_SYNC(9);
-	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
-	GUEST_ASSERT(!vmwrite(GUEST_RIP, 0xc0fffee));
-	GUEST_SYNC(10);
-	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0fffee);
-	GUEST_ASSERT(!vmwrite(GUEST_RIP, 0xc0ffffee));
-	GUEST_SYNC(11);
-
-	/* Done, exit to L1 and never come back.  */
-	vmcall();
-}
-
-void l1_guest_code(struct vmx_pages *vmx_pages)
-{
-#define L2_GUEST_STACK_SIZE 64
-        unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
-
-	GUEST_ASSERT(vmx_pages->vmcs_gpa);
-	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
-	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
-
-	GUEST_SYNC(3);
-	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
-
-	prepare_vmcs(vmx_pages, l2_guest_code,
-		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
-
-	GUEST_SYNC(4);
-	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
-	GUEST_ASSERT(!vmlaunch());
-	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
-	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
-
-	/* Check that the launched state is preserved.  */
-	GUEST_ASSERT(vmlaunch());
-
-	GUEST_ASSERT(!vmresume());
-	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
-
-	GUEST_SYNC(6);
-	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
-
-	GUEST_ASSERT(!vmresume());
-	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
-
-	vmwrite(GUEST_RIP, vmreadz(GUEST_RIP) + 3);
-
-	vmwrite(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_SHADOW_VMCS);
-	vmwrite(VMCS_LINK_POINTER, vmx_pages->shadow_vmcs_gpa);
-
-	GUEST_ASSERT(!vmptrld(vmx_pages->shadow_vmcs_gpa));
-	GUEST_ASSERT(vmlaunch());
-	GUEST_SYNC(7);
-	GUEST_ASSERT(vmlaunch());
-	GUEST_ASSERT(vmresume());
-
-	vmwrite(GUEST_RIP, 0xc0ffee);
-	GUEST_SYNC(8);
-	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
-
-	GUEST_ASSERT(!vmptrld(vmx_pages->vmcs_gpa));
-	GUEST_ASSERT(!vmresume());
-	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
-
-	GUEST_ASSERT(!vmptrld(vmx_pages->shadow_vmcs_gpa));
-	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffffee);
-	GUEST_ASSERT(vmlaunch());
-	GUEST_ASSERT(vmresume());
-	GUEST_SYNC(12);
-	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffffee);
-	GUEST_ASSERT(vmlaunch());
-	GUEST_ASSERT(vmresume());
-}
-
-void guest_code(struct vmx_pages *vmx_pages)
-{
-	GUEST_SYNC(1);
-	GUEST_SYNC(2);
-
-	if (vmx_pages)
-		l1_guest_code(vmx_pages);
-
-	GUEST_DONE();
-}
-
-int main(int argc, char *argv[])
-{
-	struct vmx_pages *vmx_pages = NULL;
-	vm_vaddr_t vmx_pages_gva = 0;
-
-	struct kvm_regs regs1, regs2;
-	struct kvm_vm *vm;
-	struct kvm_run *run;
-	struct kvm_x86_state *state;
-	struct ucall uc;
-	int stage;
-
-	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
-
-	/* Create VM */
-	vm = vm_create_default(VCPU_ID, 0, guest_code);
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
-	run = vcpu_state(vm, VCPU_ID);
-
-	vcpu_regs_get(vm, VCPU_ID, &regs1);
-
-	if (kvm_check_cap(KVM_CAP_NESTED_STATE)) {
-		vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva);
-		vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
-	} else {
-		printf("will skip nested state checks\n");
-		vcpu_args_set(vm, VCPU_ID, 1, 0);
-	}
-
-	for (stage = 1;; stage++) {
-		_vcpu_run(vm, VCPU_ID);
-		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-			    "Unexpected exit reason: %u (%s),\n",
-			    run->exit_reason,
-			    exit_reason_str(run->exit_reason));
-
-		memset(&regs1, 0, sizeof(regs1));
-		vcpu_regs_get(vm, VCPU_ID, &regs1);
-		switch (get_ucall(vm, VCPU_ID, &uc)) {
-		case UCALL_ABORT:
-			TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
-				    __FILE__, uc.args[1]);
-			/* NOT REACHED */
-		case UCALL_SYNC:
-			break;
-		case UCALL_DONE:
-			goto done;
-		default:
-			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
-		}
-
-		/* UCALL_SYNC is handled here.  */
-		TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
-			    uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx",
-			    stage, (ulong)uc.args[1]);
-
-		state = vcpu_save_state(vm, VCPU_ID);
-		kvm_vm_release(vm);
-
-		/* Restore state in a new VM.  */
-		kvm_vm_restart(vm, O_RDWR);
-		vm_vcpu_add(vm, VCPU_ID, 0, 0);
-		vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
-		vcpu_load_state(vm, VCPU_ID, state);
-		run = vcpu_state(vm, VCPU_ID);
-		free(state);
-
-		memset(&regs2, 0, sizeof(regs2));
-		vcpu_regs_get(vm, VCPU_ID, &regs2);
-		TEST_ASSERT(!memcmp(&regs1, &regs2, sizeof(regs2)),
-			    "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx",
-			    (ulong) regs2.rdi, (ulong) regs2.rsi);
-	}
-
-done:
-	kvm_vm_free(vm);
-}
diff --git a/tools/testing/selftests/kvm/sync_regs_test.c b/tools/testing/selftests/kvm/sync_regs_test.c
deleted file mode 100644
index 213343e5dff9..000000000000
--- a/tools/testing/selftests/kvm/sync_regs_test.c
+++ /dev/null
@@ -1,237 +0,0 @@
-/*
- * Test for x86 KVM_CAP_SYNC_REGS
- *
- * Copyright (C) 2018, Google LLC.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- *
- * Verifies expected behavior of x86 KVM_CAP_SYNC_REGS functionality,
- * including requesting an invalid register set, updates to/from values
- * in kvm_run.s.regs when kvm_valid_regs and kvm_dirty_regs are toggled.
- */
-
-#define _GNU_SOURCE /* for program_invocation_short_name */
-#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 "x86.h"
-
-#define VCPU_ID 5
-
-void guest_code(void)
-{
-	for (;;) {
-		GUEST_SYNC(0);
-		asm volatile ("inc %r11");
-	}
-}
-
-static void compare_regs(struct kvm_regs *left, struct kvm_regs *right)
-{
-#define REG_COMPARE(reg) \
-	TEST_ASSERT(left->reg == right->reg, \
-		    "Register " #reg \
-		    " values did not match: 0x%llx, 0x%llx\n", \
-		    left->reg, right->reg)
-	REG_COMPARE(rax);
-	REG_COMPARE(rbx);
-	REG_COMPARE(rcx);
-	REG_COMPARE(rdx);
-	REG_COMPARE(rsi);
-	REG_COMPARE(rdi);
-	REG_COMPARE(rsp);
-	REG_COMPARE(rbp);
-	REG_COMPARE(r8);
-	REG_COMPARE(r9);
-	REG_COMPARE(r10);
-	REG_COMPARE(r11);
-	REG_COMPARE(r12);
-	REG_COMPARE(r13);
-	REG_COMPARE(r14);
-	REG_COMPARE(r15);
-	REG_COMPARE(rip);
-	REG_COMPARE(rflags);
-#undef REG_COMPARE
-}
-
-static void compare_sregs(struct kvm_sregs *left, struct kvm_sregs *right)
-{
-}
-
-static void compare_vcpu_events(struct kvm_vcpu_events *left,
-				struct kvm_vcpu_events *right)
-{
-}
-
-#define TEST_SYNC_FIELDS   (KVM_SYNC_X86_REGS|KVM_SYNC_X86_SREGS|KVM_SYNC_X86_EVENTS)
-#define INVALID_SYNC_FIELD 0x80000000
-
-int main(int argc, char *argv[])
-{
-	struct kvm_vm *vm;
-	struct kvm_run *run;
-	struct kvm_regs regs;
-	struct kvm_sregs sregs;
-	struct kvm_vcpu_events events;
-	int rv, cap;
-
-	/* Tell stdout not to buffer its content */
-	setbuf(stdout, NULL);
-
-	cap = kvm_check_cap(KVM_CAP_SYNC_REGS);
-	if ((cap & TEST_SYNC_FIELDS) != TEST_SYNC_FIELDS) {
-		fprintf(stderr, "KVM_CAP_SYNC_REGS not supported, skipping test\n");
-		exit(KSFT_SKIP);
-	}
-	if ((cap & INVALID_SYNC_FIELD) != 0) {
-		fprintf(stderr, "The \"invalid\" field is not invalid, skipping test\n");
-		exit(KSFT_SKIP);
-	}
-
-	/* Create VM */
-	vm = vm_create_default(VCPU_ID, 0, guest_code);
-
-	run = vcpu_state(vm, VCPU_ID);
-
-	/* Request reading invalid register set from VCPU. */
-	run->kvm_valid_regs = INVALID_SYNC_FIELD;
-	rv = _vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
-		    rv);
-	vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0;
-
-	run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
-	rv = _vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
-		    rv);
-	vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0;
-
-	/* Request setting invalid register set into VCPU. */
-	run->kvm_dirty_regs = INVALID_SYNC_FIELD;
-	rv = _vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
-		    rv);
-	vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0;
-
-	run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
-	rv = _vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
-		    rv);
-	vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0;
-
-	/* Request and verify all valid register sets. */
-	/* TODO: BUILD TIME CHECK: TEST_ASSERT(KVM_SYNC_X86_NUM_FIELDS != 3); */
-	run->kvm_valid_regs = TEST_SYNC_FIELDS;
-	rv = _vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-		    "Unexpected exit reason: %u (%s),\n",
-		    run->exit_reason,
-		    exit_reason_str(run->exit_reason));
-
-	vcpu_regs_get(vm, VCPU_ID, &regs);
-	compare_regs(&regs, &run->s.regs.regs);
-
-	vcpu_sregs_get(vm, VCPU_ID, &sregs);
-	compare_sregs(&sregs, &run->s.regs.sregs);
-
-	vcpu_events_get(vm, VCPU_ID, &events);
-	compare_vcpu_events(&events, &run->s.regs.events);
-
-	/* Set and verify various register values. */
-	run->s.regs.regs.r11 = 0xBAD1DEA;
-	run->s.regs.sregs.apic_base = 1 << 11;
-	/* TODO run->s.regs.events.XYZ = ABC; */
-
-	run->kvm_valid_regs = TEST_SYNC_FIELDS;
-	run->kvm_dirty_regs = KVM_SYNC_X86_REGS | KVM_SYNC_X86_SREGS;
-	rv = _vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-		    "Unexpected exit reason: %u (%s),\n",
-		    run->exit_reason,
-		    exit_reason_str(run->exit_reason));
-	TEST_ASSERT(run->s.regs.regs.r11 == 0xBAD1DEA + 1,
-		    "r11 sync regs value incorrect 0x%llx.",
-		    run->s.regs.regs.r11);
-	TEST_ASSERT(run->s.regs.sregs.apic_base == 1 << 11,
-		    "apic_base sync regs value incorrect 0x%llx.",
-		    run->s.regs.sregs.apic_base);
-
-	vcpu_regs_get(vm, VCPU_ID, &regs);
-	compare_regs(&regs, &run->s.regs.regs);
-
-	vcpu_sregs_get(vm, VCPU_ID, &sregs);
-	compare_sregs(&sregs, &run->s.regs.sregs);
-
-	vcpu_events_get(vm, VCPU_ID, &events);
-	compare_vcpu_events(&events, &run->s.regs.events);
-
-	/* Clear kvm_dirty_regs bits, verify new s.regs values are
-	 * overwritten with existing guest values.
-	 */
-	run->kvm_valid_regs = TEST_SYNC_FIELDS;
-	run->kvm_dirty_regs = 0;
-	run->s.regs.regs.r11 = 0xDEADBEEF;
-	rv = _vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-		    "Unexpected exit reason: %u (%s),\n",
-		    run->exit_reason,
-		    exit_reason_str(run->exit_reason));
-	TEST_ASSERT(run->s.regs.regs.r11 != 0xDEADBEEF,
-		    "r11 sync regs value incorrect 0x%llx.",
-		    run->s.regs.regs.r11);
-
-	/* Clear kvm_valid_regs bits and kvm_dirty_bits.
-	 * Verify s.regs values are not overwritten with existing guest values
-	 * and that guest values are not overwritten with kvm_sync_regs values.
-	 */
-	run->kvm_valid_regs = 0;
-	run->kvm_dirty_regs = 0;
-	run->s.regs.regs.r11 = 0xAAAA;
-	regs.r11 = 0xBAC0;
-	vcpu_regs_set(vm, VCPU_ID, &regs);
-	rv = _vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-		    "Unexpected exit reason: %u (%s),\n",
-		    run->exit_reason,
-		    exit_reason_str(run->exit_reason));
-	TEST_ASSERT(run->s.regs.regs.r11 == 0xAAAA,
-		    "r11 sync regs value incorrect 0x%llx.",
-		    run->s.regs.regs.r11);
-	vcpu_regs_get(vm, VCPU_ID, &regs);
-	TEST_ASSERT(regs.r11 == 0xBAC0 + 1,
-		    "r11 guest value incorrect 0x%llx.",
-		    regs.r11);
-
-	/* Clear kvm_valid_regs bits. Verify s.regs values are not overwritten
-	 * with existing guest values but that guest values are overwritten
-	 * with kvm_sync_regs values.
-	 */
-	run->kvm_valid_regs = 0;
-	run->kvm_dirty_regs = TEST_SYNC_FIELDS;
-	run->s.regs.regs.r11 = 0xBBBB;
-	rv = _vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-		    "Unexpected exit reason: %u (%s),\n",
-		    run->exit_reason,
-		    exit_reason_str(run->exit_reason));
-	TEST_ASSERT(run->s.regs.regs.r11 == 0xBBBB,
-		    "r11 sync regs value incorrect 0x%llx.",
-		    run->s.regs.regs.r11);
-	vcpu_regs_get(vm, VCPU_ID, &regs);
-	TEST_ASSERT(regs.r11 == 0xBBBB + 1,
-		    "r11 guest value incorrect 0x%llx.",
-		    regs.r11);
-
-	kvm_vm_free(vm);
-
-	return 0;
-}
diff --git a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
deleted file mode 100644
index 8d487c78796a..000000000000
--- a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
+++ /dev/null
@@ -1,174 +0,0 @@
-/*
- * gtests/tests/vmx_tsc_adjust_test.c
- *
- * Copyright (C) 2018, Google LLC.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- *
- *
- * IA32_TSC_ADJUST test
- *
- * According to the SDM, "if an execution of WRMSR to the
- * IA32_TIME_STAMP_COUNTER MSR adds (or subtracts) value X from the TSC,
- * the logical processor also adds (or subtracts) value X from the
- * IA32_TSC_ADJUST MSR.
- *
- * Note that when L1 doesn't intercept writes to IA32_TSC, a
- * WRMSR(IA32_TSC) from L2 sets L1's TSC value, not L2's perceived TSC
- * value.
- *
- * This test verifies that this unusual case is handled correctly.
- */
-
-#include "test_util.h"
-#include "kvm_util.h"
-#include "x86.h"
-#include "vmx.h"
-
-#include <string.h>
-#include <sys/ioctl.h>
-
-#include "../kselftest.h"
-
-#ifndef MSR_IA32_TSC_ADJUST
-#define MSR_IA32_TSC_ADJUST 0x3b
-#endif
-
-#define PAGE_SIZE	4096
-#define VCPU_ID		5
-
-#define TSC_ADJUST_VALUE (1ll << 32)
-#define TSC_OFFSET_VALUE -(1ll << 48)
-
-enum {
-	PORT_ABORT = 0x1000,
-	PORT_REPORT,
-	PORT_DONE,
-};
-
-enum {
-	VMXON_PAGE = 0,
-	VMCS_PAGE,
-	MSR_BITMAP_PAGE,
-
-	NUM_VMX_PAGES,
-};
-
-struct kvm_single_msr {
-	struct kvm_msrs header;
-	struct kvm_msr_entry entry;
-} __attribute__((packed));
-
-/* The virtual machine object. */
-static struct kvm_vm *vm;
-
-static void check_ia32_tsc_adjust(int64_t max)
-{
-	int64_t adjust;
-
-	adjust = rdmsr(MSR_IA32_TSC_ADJUST);
-	GUEST_SYNC(adjust);
-	GUEST_ASSERT(adjust <= max);
-}
-
-static void l2_guest_code(void)
-{
-	uint64_t l1_tsc = rdtsc() - TSC_OFFSET_VALUE;
-
-	wrmsr(MSR_IA32_TSC, l1_tsc - TSC_ADJUST_VALUE);
-	check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
-
-	/* Exit to L1 */
-	__asm__ __volatile__("vmcall");
-}
-
-static void l1_guest_code(struct vmx_pages *vmx_pages)
-{
-#define L2_GUEST_STACK_SIZE 64
-	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
-	uint32_t control;
-	uintptr_t save_cr3;
-
-	GUEST_ASSERT(rdtsc() < TSC_ADJUST_VALUE);
-	wrmsr(MSR_IA32_TSC, rdtsc() - TSC_ADJUST_VALUE);
-	check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
-
-	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
-
-	/* Prepare the VMCS for L2 execution. */
-	prepare_vmcs(vmx_pages, l2_guest_code,
-		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
-	control = vmreadz(CPU_BASED_VM_EXEC_CONTROL);
-	control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETING;
-	vmwrite(CPU_BASED_VM_EXEC_CONTROL, control);
-	vmwrite(TSC_OFFSET, TSC_OFFSET_VALUE);
-
-	/* Jump into L2.  First, test failure to load guest CR3.  */
-	save_cr3 = vmreadz(GUEST_CR3);
-	vmwrite(GUEST_CR3, -1ull);
-	GUEST_ASSERT(!vmlaunch());
-	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) ==
-		     (EXIT_REASON_FAILED_VMENTRY | EXIT_REASON_INVALID_STATE));
-	check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
-	vmwrite(GUEST_CR3, save_cr3);
-
-	GUEST_ASSERT(!vmlaunch());
-	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
-
-	check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
-
-	GUEST_DONE();
-}
-
-void report(int64_t val)
-{
-	printf("IA32_TSC_ADJUST is %ld (%lld * TSC_ADJUST_VALUE + %lld).\n",
-	       val, val / TSC_ADJUST_VALUE, val % TSC_ADJUST_VALUE);
-}
-
-int main(int argc, char *argv[])
-{
-	struct vmx_pages *vmx_pages;
-	vm_vaddr_t vmx_pages_gva;
-	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
-
-	if (!(entry->ecx & CPUID_VMX)) {
-		fprintf(stderr, "nested VMX not enabled, skipping test\n");
-		exit(KSFT_SKIP);
-	}
-
-	vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
-
-	/* Allocate VMX pages and shared descriptors (vmx_pages). */
-	vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva);
-	vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
-
-	for (;;) {
-		volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
-		struct ucall uc;
-
-		vcpu_run(vm, VCPU_ID);
-		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-			    "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n",
-			    run->exit_reason,
-			    exit_reason_str(run->exit_reason));
-
-		switch (get_ucall(vm, VCPU_ID, &uc)) {
-		case UCALL_ABORT:
-			TEST_ASSERT(false, "%s", (const char *)uc.args[0]);
-			/* NOT REACHED */
-		case UCALL_SYNC:
-			report(uc.args[1]);
-			break;
-		case UCALL_DONE:
-			goto done;
-		default:
-			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
-		}
-	}
-
-	kvm_vm_free(vm);
-done:
-	return 0;
-}
diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
new file mode 100644
index 000000000000..d503a51fad30
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * CR4 and CPUID sync test
+ *
+ * Copyright 2018, Red Hat, Inc. and/or its affiliates.
+ *
+ * Author:
+ *   Wei Huang <wei@redhat.com>
+ */
+
+#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 X86_FEATURE_XSAVE	(1<<26)
+#define X86_FEATURE_OSXSAVE	(1<<27)
+#define VCPU_ID			1
+
+static inline bool cr4_cpuid_is_sync(void)
+{
+	int func, subfunc;
+	uint32_t eax, ebx, ecx, edx;
+	uint64_t cr4;
+
+	func = 0x1;
+	subfunc = 0x0;
+	__asm__ __volatile__("cpuid"
+			     : "=a"(eax), "=b"(ebx), "=c"(ecx), "=d"(edx)
+			     : "a"(func), "c"(subfunc));
+
+	cr4 = get_cr4();
+
+	return (!!(ecx & X86_FEATURE_OSXSAVE)) == (!!(cr4 & X86_CR4_OSXSAVE));
+}
+
+static void guest_code(void)
+{
+	uint64_t cr4;
+
+	/* turn on CR4.OSXSAVE */
+	cr4 = get_cr4();
+	cr4 |= X86_CR4_OSXSAVE;
+	set_cr4(cr4);
+
+	/* verify CR4.OSXSAVE == CPUID.OSXSAVE */
+	GUEST_ASSERT(cr4_cpuid_is_sync());
+
+	/* notify hypervisor to change CR4 */
+	GUEST_SYNC(0);
+
+	/* check again */
+	GUEST_ASSERT(cr4_cpuid_is_sync());
+
+	GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_run *run;
+	struct kvm_vm *vm;
+	struct kvm_sregs sregs;
+	struct kvm_cpuid_entry2 *entry;
+	struct ucall uc;
+	int rc;
+
+	entry = kvm_get_supported_cpuid_entry(1);
+	if (!(entry->ecx & X86_FEATURE_XSAVE)) {
+		printf("XSAVE feature not supported, skipping test\n");
+		return 0;
+	}
+
+	/* Tell stdout not to buffer its content */
+	setbuf(stdout, NULL);
+
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+	run = vcpu_state(vm, VCPU_ID);
+
+	while (1) {
+		rc = _vcpu_run(vm, VCPU_ID);
+
+		if (run->exit_reason == KVM_EXIT_IO) {
+			switch (get_ucall(vm, VCPU_ID, &uc)) {
+			case UCALL_SYNC:
+				/* emulate hypervisor clearing CR4.OSXSAVE */
+				vcpu_sregs_get(vm, VCPU_ID, &sregs);
+				sregs.cr4 &= ~X86_CR4_OSXSAVE;
+				vcpu_sregs_set(vm, VCPU_ID, &sregs);
+				break;
+			case UCALL_ABORT:
+				TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
+				break;
+			case UCALL_DONE:
+				goto done;
+			default:
+				TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+			}
+		}
+	}
+
+	kvm_vm_free(vm);
+
+done:
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/dirty_log_test.c
new file mode 100644
index 000000000000..7cf3e4ae6046
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/dirty_log_test.c
@@ -0,0 +1,307 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM dirty page logging test
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <time.h>
+#include <pthread.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+
+#define  DEBUG                 printf
+
+#define  VCPU_ID                        1
+/* The memory slot index to track dirty pages */
+#define  TEST_MEM_SLOT_INDEX            1
+/*
+ * GPA offset of the testing memory slot. Must be bigger than the
+ * default vm mem slot, which is DEFAULT_GUEST_PHY_PAGES.
+ */
+#define  TEST_MEM_OFFSET                (1ULL << 30) /* 1G */
+/* Size of the testing memory slot */
+#define  TEST_MEM_PAGES                 (1ULL << 18) /* 1G for 4K pages */
+/* How many pages to dirty for each guest loop */
+#define  TEST_PAGES_PER_LOOP            1024
+/* How many host loops to run (one KVM_GET_DIRTY_LOG for each loop) */
+#define  TEST_HOST_LOOP_N               32
+/* Interval for each host loop (ms) */
+#define  TEST_HOST_LOOP_INTERVAL        10
+
+/*
+ * Guest variables.  We use these variables to share data between host
+ * and guest.  There are two copies of the variables, one in host memory
+ * (which is unused) and one in guest memory.  When the host wants to
+ * access these variables, it needs to call addr_gva2hva() to access the
+ * guest copy.
+ */
+uint64_t guest_random_array[TEST_PAGES_PER_LOOP];
+uint64_t guest_iteration;
+uint64_t guest_page_size;
+
+/*
+ * Writes to the first byte of a random page within the testing memory
+ * region continuously.
+ */
+void guest_code(void)
+{
+	int i = 0;
+	uint64_t volatile *array = guest_random_array;
+	uint64_t volatile *guest_addr;
+
+	while (true) {
+		for (i = 0; i < TEST_PAGES_PER_LOOP; i++) {
+			/*
+			 * Write to the first 8 bytes of a random page
+			 * on the testing memory region.
+			 */
+			guest_addr = (uint64_t *)
+			    (TEST_MEM_OFFSET +
+			     (array[i] % TEST_MEM_PAGES) * guest_page_size);
+			*guest_addr = guest_iteration;
+		}
+		/* Tell the host that we need more random numbers */
+		GUEST_SYNC(1);
+	}
+}
+
+/*
+ * Host variables.  These variables should only be used by the host
+ * rather than the guest.
+ */
+bool host_quit;
+
+/* Points to the test VM memory region on which we track dirty logs */
+void *host_test_mem;
+
+/* For statistics only */
+uint64_t host_dirty_count;
+uint64_t host_clear_count;
+uint64_t host_track_next_count;
+
+/*
+ * We use this bitmap to track some pages that should have its dirty
+ * bit set in the _next_ iteration.  For example, if we detected the
+ * page value changed to current iteration but at the same time the
+ * page bit is cleared in the latest bitmap, then the system must
+ * report that write in the next get dirty log call.
+ */
+unsigned long *host_bmap_track;
+
+void generate_random_array(uint64_t *guest_array, uint64_t size)
+{
+	uint64_t i;
+
+	for (i = 0; i < size; i++) {
+		guest_array[i] = random();
+	}
+}
+
+void *vcpu_worker(void *data)
+{
+	int ret;
+	uint64_t loops, *guest_array, pages_count = 0;
+	struct kvm_vm *vm = data;
+	struct kvm_run *run;
+	struct ucall uc;
+
+	run = vcpu_state(vm, VCPU_ID);
+
+	/* Retrieve the guest random array pointer and cache it */
+	guest_array = addr_gva2hva(vm, (vm_vaddr_t)guest_random_array);
+
+	DEBUG("VCPU starts\n");
+
+	generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
+
+	while (!READ_ONCE(host_quit)) {
+		/* Let the guest to dirty these random pages */
+		ret = _vcpu_run(vm, VCPU_ID);
+		if (run->exit_reason == KVM_EXIT_IO &&
+		    get_ucall(vm, VCPU_ID, &uc) == UCALL_SYNC) {
+			pages_count += TEST_PAGES_PER_LOOP;
+			generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
+		} else {
+			TEST_ASSERT(false,
+				    "Invalid guest sync status: "
+				    "exit_reason=%s\n",
+				    exit_reason_str(run->exit_reason));
+		}
+	}
+
+	DEBUG("VCPU exits, dirtied %"PRIu64" pages\n", pages_count);
+
+	return NULL;
+}
+
+void vm_dirty_log_verify(unsigned long *bmap, uint64_t iteration)
+{
+	uint64_t page;
+	uint64_t volatile *value_ptr;
+
+	for (page = 0; page < TEST_MEM_PAGES; page++) {
+		value_ptr = host_test_mem + page * getpagesize();
+
+		/* If this is a special page that we were tracking... */
+		if (test_and_clear_bit(page, host_bmap_track)) {
+			host_track_next_count++;
+			TEST_ASSERT(test_bit(page, bmap),
+				    "Page %"PRIu64" should have its dirty bit "
+				    "set in this iteration but it is missing",
+				    page);
+		}
+
+		if (test_bit(page, bmap)) {
+			host_dirty_count++;
+			/*
+			 * If the bit is set, the value written onto
+			 * the corresponding page should be either the
+			 * previous iteration number or the current one.
+			 */
+			TEST_ASSERT(*value_ptr == iteration ||
+				    *value_ptr == iteration - 1,
+				    "Set page %"PRIu64" value %"PRIu64
+				    " incorrect (iteration=%"PRIu64")",
+				    page, *value_ptr, iteration);
+		} else {
+			host_clear_count++;
+			/*
+			 * If cleared, the value written can be any
+			 * value smaller or equals to the iteration
+			 * number.  Note that the value can be exactly
+			 * (iteration-1) if that write can happen
+			 * like this:
+			 *
+			 * (1) increase loop count to "iteration-1"
+			 * (2) write to page P happens (with value
+			 *     "iteration-1")
+			 * (3) get dirty log for "iteration-1"; we'll
+			 *     see that page P bit is set (dirtied),
+			 *     and not set the bit in host_bmap_track
+			 * (4) increase loop count to "iteration"
+			 *     (which is current iteration)
+			 * (5) get dirty log for current iteration,
+			 *     we'll see that page P is cleared, with
+			 *     value "iteration-1".
+			 */
+			TEST_ASSERT(*value_ptr <= iteration,
+				    "Clear page %"PRIu64" value %"PRIu64
+				    " incorrect (iteration=%"PRIu64")",
+				    page, *value_ptr, iteration);
+			if (*value_ptr == iteration) {
+				/*
+				 * This page is _just_ modified; it
+				 * should report its dirtyness in the
+				 * next run
+				 */
+				set_bit(page, host_bmap_track);
+			}
+		}
+	}
+}
+
+void help(char *name)
+{
+	puts("");
+	printf("usage: %s [-i iterations] [-I interval] [-h]\n", name);
+	puts("");
+	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
+	       TEST_HOST_LOOP_N);
+	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
+	       TEST_HOST_LOOP_INTERVAL);
+	puts("");
+	exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+	pthread_t vcpu_thread;
+	struct kvm_vm *vm;
+	uint64_t volatile *psize, *iteration;
+	unsigned long *bmap, iterations = TEST_HOST_LOOP_N,
+	    interval = TEST_HOST_LOOP_INTERVAL;
+	int opt;
+
+	while ((opt = getopt(argc, argv, "hi:I:")) != -1) {
+		switch (opt) {
+		case 'i':
+			iterations = strtol(optarg, NULL, 10);
+			break;
+		case 'I':
+			interval = strtol(optarg, NULL, 10);
+			break;
+		case 'h':
+		default:
+			help(argv[0]);
+			break;
+		}
+	}
+
+	TEST_ASSERT(iterations > 2, "Iteration must be bigger than zero\n");
+	TEST_ASSERT(interval > 0, "Interval must be bigger than zero");
+
+	DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
+	      iterations, interval);
+
+	srandom(time(0));
+
+	bmap = bitmap_alloc(TEST_MEM_PAGES);
+	host_bmap_track = bitmap_alloc(TEST_MEM_PAGES);
+
+	vm = vm_create_default(VCPU_ID, TEST_MEM_PAGES, guest_code);
+
+	/* Add an extra memory slot for testing dirty logging */
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+				    TEST_MEM_OFFSET,
+				    TEST_MEM_SLOT_INDEX,
+				    TEST_MEM_PAGES,
+				    KVM_MEM_LOG_DIRTY_PAGES);
+	/* Cache the HVA pointer of the region */
+	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)TEST_MEM_OFFSET);
+
+	/* Do 1:1 mapping for the dirty track memory slot */
+	virt_map(vm, TEST_MEM_OFFSET, TEST_MEM_OFFSET,
+		 TEST_MEM_PAGES * getpagesize(), 0);
+
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+	/* Tell the guest about the page size on the system */
+	psize = addr_gva2hva(vm, (vm_vaddr_t)&guest_page_size);
+	*psize = getpagesize();
+
+	/* Start the iterations */
+	iteration = addr_gva2hva(vm, (vm_vaddr_t)&guest_iteration);
+	*iteration = 1;
+
+	/* Start dirtying pages */
+	pthread_create(&vcpu_thread, NULL, vcpu_worker, vm);
+
+	while (*iteration < iterations) {
+		/* Give the vcpu thread some time to dirty some pages */
+		usleep(interval * 1000);
+		kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
+		vm_dirty_log_verify(bmap, *iteration);
+		(*iteration)++;
+	}
+
+	/* Tell the vcpu thread to quit */
+	host_quit = true;
+	pthread_join(vcpu_thread, NULL);
+
+	DEBUG("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), "
+	      "track_next (%"PRIu64")\n", host_dirty_count, host_clear_count,
+	      host_track_next_count);
+
+	free(bmap);
+	free(host_bmap_track);
+	kvm_vm_free(vm);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
new file mode 100644
index 000000000000..eb3e7a838cb4
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test for x86 KVM_CAP_MSR_PLATFORM_INFO
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Verifies expected behavior of controlling guest access to
+ * MSR_PLATFORM_INFO.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#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 0
+#define MSR_PLATFORM_INFO_MAX_TURBO_RATIO 0xff00
+
+static void guest_code(void)
+{
+	uint64_t msr_platform_info;
+
+	for (;;) {
+		msr_platform_info = rdmsr(MSR_PLATFORM_INFO);
+		GUEST_SYNC(msr_platform_info);
+		asm volatile ("inc %r11");
+	}
+}
+
+static void set_msr_platform_info_enabled(struct kvm_vm *vm, bool enable)
+{
+	struct kvm_enable_cap cap = {};
+
+	cap.cap = KVM_CAP_MSR_PLATFORM_INFO;
+	cap.flags = 0;
+	cap.args[0] = (int)enable;
+	vm_enable_cap(vm, &cap);
+}
+
+static void test_msr_platform_info_enabled(struct kvm_vm *vm)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+	struct ucall uc;
+
+	set_msr_platform_info_enabled(vm, true);
+	vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			"Exit_reason other than KVM_EXIT_IO: %u (%s),\n",
+			run->exit_reason,
+			exit_reason_str(run->exit_reason));
+	get_ucall(vm, VCPU_ID, &uc);
+	TEST_ASSERT(uc.cmd == UCALL_SYNC,
+			"Received ucall other than UCALL_SYNC: %u\n",
+			ucall);
+	TEST_ASSERT((uc.args[1] & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) ==
+		MSR_PLATFORM_INFO_MAX_TURBO_RATIO,
+		"Expected MSR_PLATFORM_INFO to have max turbo ratio mask: %i.",
+		MSR_PLATFORM_INFO_MAX_TURBO_RATIO);
+}
+
+static void test_msr_platform_info_disabled(struct kvm_vm *vm)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+
+	set_msr_platform_info_enabled(vm, false);
+	vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN,
+			"Exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n",
+			run->exit_reason,
+			exit_reason_str(run->exit_reason));
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_vm *vm;
+	struct kvm_run *state;
+	int rv;
+	uint64_t msr_platform_info;
+
+	/* Tell stdout not to buffer its content */
+	setbuf(stdout, NULL);
+
+	rv = kvm_check_cap(KVM_CAP_MSR_PLATFORM_INFO);
+	if (!rv) {
+		fprintf(stderr,
+			"KVM_CAP_MSR_PLATFORM_INFO not supported, skip test\n");
+		exit(KSFT_SKIP);
+	}
+
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+	msr_platform_info = vcpu_get_msr(vm, VCPU_ID, MSR_PLATFORM_INFO);
+	vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO,
+		msr_platform_info | MSR_PLATFORM_INFO_MAX_TURBO_RATIO);
+	test_msr_platform_info_disabled(vm);
+	test_msr_platform_info_enabled(vm);
+	vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, msr_platform_info);
+
+	kvm_vm_free(vm);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c
new file mode 100644
index 000000000000..35640e8e95bc
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c
@@ -0,0 +1,54 @@
+/*
+ * KVM_SET_SREGS tests
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * This is a regression test for the bug fixed by the following commit:
+ * d3802286fa0f ("kvm: x86: Disallow illegal IA32_APIC_BASE MSR values")
+ *
+ * That bug allowed a user-mode program that called the KVM_SET_SREGS
+ * ioctl to put a VCPU's local APIC into an invalid state.
+ *
+ */
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#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                  5
+
+int main(int argc, char *argv[])
+{
+	struct kvm_sregs sregs;
+	struct kvm_vm *vm;
+	int rc;
+
+	/* Tell stdout not to buffer its content */
+	setbuf(stdout, NULL);
+
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, NULL);
+
+	vcpu_sregs_get(vm, VCPU_ID, &sregs);
+	sregs.apic_base = 1 << 10;
+	rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs);
+	TEST_ASSERT(rc, "Set IA32_APIC_BASE to %llx (invalid)",
+		    sregs.apic_base);
+	sregs.apic_base = 1 << 11;
+	rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs);
+	TEST_ASSERT(!rc, "Couldn't set IA32_APIC_BASE to %llx (valid)",
+		    sregs.apic_base);
+
+	kvm_vm_free(vm);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c
new file mode 100644
index 000000000000..43df194a7c1e
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/state_test.c
@@ -0,0 +1,197 @@
+/*
+ * KVM_GET/SET_* tests
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Tests for vCPU state save/restore, including nested guest state.
+ */
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#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"
+#include "vmx.h"
+
+#define VCPU_ID		5
+
+static bool have_nested_state;
+
+void l2_guest_code(void)
+{
+	GUEST_SYNC(5);
+
+        /* Exit to L1 */
+	vmcall();
+
+	/* L1 has now set up a shadow VMCS for us.  */
+	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
+	GUEST_SYNC(9);
+	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
+	GUEST_ASSERT(!vmwrite(GUEST_RIP, 0xc0fffee));
+	GUEST_SYNC(10);
+	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0fffee);
+	GUEST_ASSERT(!vmwrite(GUEST_RIP, 0xc0ffffee));
+	GUEST_SYNC(11);
+
+	/* Done, exit to L1 and never come back.  */
+	vmcall();
+}
+
+void l1_guest_code(struct vmx_pages *vmx_pages)
+{
+#define L2_GUEST_STACK_SIZE 64
+        unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+
+	GUEST_ASSERT(vmx_pages->vmcs_gpa);
+	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
+
+	GUEST_SYNC(3);
+	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
+
+	prepare_vmcs(vmx_pages, l2_guest_code,
+		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	GUEST_SYNC(4);
+	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
+	GUEST_ASSERT(!vmlaunch());
+	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+	/* Check that the launched state is preserved.  */
+	GUEST_ASSERT(vmlaunch());
+
+	GUEST_ASSERT(!vmresume());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+	GUEST_SYNC(6);
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+	GUEST_ASSERT(!vmresume());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+	vmwrite(GUEST_RIP, vmreadz(GUEST_RIP) + 3);
+
+	vmwrite(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_SHADOW_VMCS);
+	vmwrite(VMCS_LINK_POINTER, vmx_pages->shadow_vmcs_gpa);
+
+	GUEST_ASSERT(!vmptrld(vmx_pages->shadow_vmcs_gpa));
+	GUEST_ASSERT(vmlaunch());
+	GUEST_SYNC(7);
+	GUEST_ASSERT(vmlaunch());
+	GUEST_ASSERT(vmresume());
+
+	vmwrite(GUEST_RIP, 0xc0ffee);
+	GUEST_SYNC(8);
+	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
+
+	GUEST_ASSERT(!vmptrld(vmx_pages->vmcs_gpa));
+	GUEST_ASSERT(!vmresume());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+	GUEST_ASSERT(!vmptrld(vmx_pages->shadow_vmcs_gpa));
+	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffffee);
+	GUEST_ASSERT(vmlaunch());
+	GUEST_ASSERT(vmresume());
+	GUEST_SYNC(12);
+	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffffee);
+	GUEST_ASSERT(vmlaunch());
+	GUEST_ASSERT(vmresume());
+}
+
+void guest_code(struct vmx_pages *vmx_pages)
+{
+	GUEST_SYNC(1);
+	GUEST_SYNC(2);
+
+	if (vmx_pages)
+		l1_guest_code(vmx_pages);
+
+	GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+	struct vmx_pages *vmx_pages = NULL;
+	vm_vaddr_t vmx_pages_gva = 0;
+
+	struct kvm_regs regs1, regs2;
+	struct kvm_vm *vm;
+	struct kvm_run *run;
+	struct kvm_x86_state *state;
+	struct ucall uc;
+	int stage;
+
+	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
+
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+	run = vcpu_state(vm, VCPU_ID);
+
+	vcpu_regs_get(vm, VCPU_ID, &regs1);
+
+	if (kvm_check_cap(KVM_CAP_NESTED_STATE)) {
+		vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva);
+		vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
+	} else {
+		printf("will skip nested state checks\n");
+		vcpu_args_set(vm, VCPU_ID, 1, 0);
+	}
+
+	for (stage = 1;; stage++) {
+		_vcpu_run(vm, VCPU_ID);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Unexpected exit reason: %u (%s),\n",
+			    run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		memset(&regs1, 0, sizeof(regs1));
+		vcpu_regs_get(vm, VCPU_ID, &regs1);
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_ABORT:
+			TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
+				    __FILE__, uc.args[1]);
+			/* NOT REACHED */
+		case UCALL_SYNC:
+			break;
+		case UCALL_DONE:
+			goto done;
+		default:
+			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+		}
+
+		/* UCALL_SYNC is handled here.  */
+		TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
+			    uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx",
+			    stage, (ulong)uc.args[1]);
+
+		state = vcpu_save_state(vm, VCPU_ID);
+		kvm_vm_release(vm);
+
+		/* Restore state in a new VM.  */
+		kvm_vm_restart(vm, O_RDWR);
+		vm_vcpu_add(vm, VCPU_ID, 0, 0);
+		vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+		vcpu_load_state(vm, VCPU_ID, state);
+		run = vcpu_state(vm, VCPU_ID);
+		free(state);
+
+		memset(&regs2, 0, sizeof(regs2));
+		vcpu_regs_get(vm, VCPU_ID, &regs2);
+		TEST_ASSERT(!memcmp(&regs1, &regs2, sizeof(regs2)),
+			    "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx",
+			    (ulong) regs2.rdi, (ulong) regs2.rsi);
+	}
+
+done:
+	kvm_vm_free(vm);
+}
diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
new file mode 100644
index 000000000000..c8478ce9ea77
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
@@ -0,0 +1,237 @@
+/*
+ * Test for x86 KVM_CAP_SYNC_REGS
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Verifies expected behavior of x86 KVM_CAP_SYNC_REGS functionality,
+ * including requesting an invalid register set, updates to/from values
+ * in kvm_run.s.regs when kvm_valid_regs and kvm_dirty_regs are toggled.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#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 5
+
+void guest_code(void)
+{
+	for (;;) {
+		GUEST_SYNC(0);
+		asm volatile ("inc %r11");
+	}
+}
+
+static void compare_regs(struct kvm_regs *left, struct kvm_regs *right)
+{
+#define REG_COMPARE(reg) \
+	TEST_ASSERT(left->reg == right->reg, \
+		    "Register " #reg \
+		    " values did not match: 0x%llx, 0x%llx\n", \
+		    left->reg, right->reg)
+	REG_COMPARE(rax);
+	REG_COMPARE(rbx);
+	REG_COMPARE(rcx);
+	REG_COMPARE(rdx);
+	REG_COMPARE(rsi);
+	REG_COMPARE(rdi);
+	REG_COMPARE(rsp);
+	REG_COMPARE(rbp);
+	REG_COMPARE(r8);
+	REG_COMPARE(r9);
+	REG_COMPARE(r10);
+	REG_COMPARE(r11);
+	REG_COMPARE(r12);
+	REG_COMPARE(r13);
+	REG_COMPARE(r14);
+	REG_COMPARE(r15);
+	REG_COMPARE(rip);
+	REG_COMPARE(rflags);
+#undef REG_COMPARE
+}
+
+static void compare_sregs(struct kvm_sregs *left, struct kvm_sregs *right)
+{
+}
+
+static void compare_vcpu_events(struct kvm_vcpu_events *left,
+				struct kvm_vcpu_events *right)
+{
+}
+
+#define TEST_SYNC_FIELDS   (KVM_SYNC_X86_REGS|KVM_SYNC_X86_SREGS|KVM_SYNC_X86_EVENTS)
+#define INVALID_SYNC_FIELD 0x80000000
+
+int main(int argc, char *argv[])
+{
+	struct kvm_vm *vm;
+	struct kvm_run *run;
+	struct kvm_regs regs;
+	struct kvm_sregs sregs;
+	struct kvm_vcpu_events events;
+	int rv, cap;
+
+	/* Tell stdout not to buffer its content */
+	setbuf(stdout, NULL);
+
+	cap = kvm_check_cap(KVM_CAP_SYNC_REGS);
+	if ((cap & TEST_SYNC_FIELDS) != TEST_SYNC_FIELDS) {
+		fprintf(stderr, "KVM_CAP_SYNC_REGS not supported, skipping test\n");
+		exit(KSFT_SKIP);
+	}
+	if ((cap & INVALID_SYNC_FIELD) != 0) {
+		fprintf(stderr, "The \"invalid\" field is not invalid, skipping test\n");
+		exit(KSFT_SKIP);
+	}
+
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+	run = vcpu_state(vm, VCPU_ID);
+
+	/* Request reading invalid register set from VCPU. */
+	run->kvm_valid_regs = INVALID_SYNC_FIELD;
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(rv < 0 && errno == EINVAL,
+		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+		    rv);
+	vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0;
+
+	run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(rv < 0 && errno == EINVAL,
+		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+		    rv);
+	vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0;
+
+	/* Request setting invalid register set into VCPU. */
+	run->kvm_dirty_regs = INVALID_SYNC_FIELD;
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(rv < 0 && errno == EINVAL,
+		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+		    rv);
+	vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0;
+
+	run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(rv < 0 && errno == EINVAL,
+		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+		    rv);
+	vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0;
+
+	/* Request and verify all valid register sets. */
+	/* TODO: BUILD TIME CHECK: TEST_ASSERT(KVM_SYNC_X86_NUM_FIELDS != 3); */
+	run->kvm_valid_regs = TEST_SYNC_FIELDS;
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+		    "Unexpected exit reason: %u (%s),\n",
+		    run->exit_reason,
+		    exit_reason_str(run->exit_reason));
+
+	vcpu_regs_get(vm, VCPU_ID, &regs);
+	compare_regs(&regs, &run->s.regs.regs);
+
+	vcpu_sregs_get(vm, VCPU_ID, &sregs);
+	compare_sregs(&sregs, &run->s.regs.sregs);
+
+	vcpu_events_get(vm, VCPU_ID, &events);
+	compare_vcpu_events(&events, &run->s.regs.events);
+
+	/* Set and verify various register values. */
+	run->s.regs.regs.r11 = 0xBAD1DEA;
+	run->s.regs.sregs.apic_base = 1 << 11;
+	/* TODO run->s.regs.events.XYZ = ABC; */
+
+	run->kvm_valid_regs = TEST_SYNC_FIELDS;
+	run->kvm_dirty_regs = KVM_SYNC_X86_REGS | KVM_SYNC_X86_SREGS;
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+		    "Unexpected exit reason: %u (%s),\n",
+		    run->exit_reason,
+		    exit_reason_str(run->exit_reason));
+	TEST_ASSERT(run->s.regs.regs.r11 == 0xBAD1DEA + 1,
+		    "r11 sync regs value incorrect 0x%llx.",
+		    run->s.regs.regs.r11);
+	TEST_ASSERT(run->s.regs.sregs.apic_base == 1 << 11,
+		    "apic_base sync regs value incorrect 0x%llx.",
+		    run->s.regs.sregs.apic_base);
+
+	vcpu_regs_get(vm, VCPU_ID, &regs);
+	compare_regs(&regs, &run->s.regs.regs);
+
+	vcpu_sregs_get(vm, VCPU_ID, &sregs);
+	compare_sregs(&sregs, &run->s.regs.sregs);
+
+	vcpu_events_get(vm, VCPU_ID, &events);
+	compare_vcpu_events(&events, &run->s.regs.events);
+
+	/* Clear kvm_dirty_regs bits, verify new s.regs values are
+	 * overwritten with existing guest values.
+	 */
+	run->kvm_valid_regs = TEST_SYNC_FIELDS;
+	run->kvm_dirty_regs = 0;
+	run->s.regs.regs.r11 = 0xDEADBEEF;
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+		    "Unexpected exit reason: %u (%s),\n",
+		    run->exit_reason,
+		    exit_reason_str(run->exit_reason));
+	TEST_ASSERT(run->s.regs.regs.r11 != 0xDEADBEEF,
+		    "r11 sync regs value incorrect 0x%llx.",
+		    run->s.regs.regs.r11);
+
+	/* Clear kvm_valid_regs bits and kvm_dirty_bits.
+	 * Verify s.regs values are not overwritten with existing guest values
+	 * and that guest values are not overwritten with kvm_sync_regs values.
+	 */
+	run->kvm_valid_regs = 0;
+	run->kvm_dirty_regs = 0;
+	run->s.regs.regs.r11 = 0xAAAA;
+	regs.r11 = 0xBAC0;
+	vcpu_regs_set(vm, VCPU_ID, &regs);
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+		    "Unexpected exit reason: %u (%s),\n",
+		    run->exit_reason,
+		    exit_reason_str(run->exit_reason));
+	TEST_ASSERT(run->s.regs.regs.r11 == 0xAAAA,
+		    "r11 sync regs value incorrect 0x%llx.",
+		    run->s.regs.regs.r11);
+	vcpu_regs_get(vm, VCPU_ID, &regs);
+	TEST_ASSERT(regs.r11 == 0xBAC0 + 1,
+		    "r11 guest value incorrect 0x%llx.",
+		    regs.r11);
+
+	/* Clear kvm_valid_regs bits. Verify s.regs values are not overwritten
+	 * with existing guest values but that guest values are overwritten
+	 * with kvm_sync_regs values.
+	 */
+	run->kvm_valid_regs = 0;
+	run->kvm_dirty_regs = TEST_SYNC_FIELDS;
+	run->s.regs.regs.r11 = 0xBBBB;
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+		    "Unexpected exit reason: %u (%s),\n",
+		    run->exit_reason,
+		    exit_reason_str(run->exit_reason));
+	TEST_ASSERT(run->s.regs.regs.r11 == 0xBBBB,
+		    "r11 sync regs value incorrect 0x%llx.",
+		    run->s.regs.regs.r11);
+	vcpu_regs_get(vm, VCPU_ID, &regs);
+	TEST_ASSERT(regs.r11 == 0xBBBB + 1,
+		    "r11 guest value incorrect 0x%llx.",
+		    regs.r11);
+
+	kvm_vm_free(vm);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
new file mode 100644
index 000000000000..38a91a5f04ac
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
@@ -0,0 +1,174 @@
+/*
+ * vmx_tsc_adjust_test
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ *
+ * IA32_TSC_ADJUST test
+ *
+ * According to the SDM, "if an execution of WRMSR to the
+ * IA32_TIME_STAMP_COUNTER MSR adds (or subtracts) value X from the TSC,
+ * the logical processor also adds (or subtracts) value X from the
+ * IA32_TSC_ADJUST MSR.
+ *
+ * Note that when L1 doesn't intercept writes to IA32_TSC, a
+ * WRMSR(IA32_TSC) from L2 sets L1's TSC value, not L2's perceived TSC
+ * value.
+ *
+ * This test verifies that this unusual case is handled correctly.
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "vmx.h"
+
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "kselftest.h"
+
+#ifndef MSR_IA32_TSC_ADJUST
+#define MSR_IA32_TSC_ADJUST 0x3b
+#endif
+
+#define PAGE_SIZE	4096
+#define VCPU_ID		5
+
+#define TSC_ADJUST_VALUE (1ll << 32)
+#define TSC_OFFSET_VALUE -(1ll << 48)
+
+enum {
+	PORT_ABORT = 0x1000,
+	PORT_REPORT,
+	PORT_DONE,
+};
+
+enum {
+	VMXON_PAGE = 0,
+	VMCS_PAGE,
+	MSR_BITMAP_PAGE,
+
+	NUM_VMX_PAGES,
+};
+
+struct kvm_single_msr {
+	struct kvm_msrs header;
+	struct kvm_msr_entry entry;
+} __attribute__((packed));
+
+/* The virtual machine object. */
+static struct kvm_vm *vm;
+
+static void check_ia32_tsc_adjust(int64_t max)
+{
+	int64_t adjust;
+
+	adjust = rdmsr(MSR_IA32_TSC_ADJUST);
+	GUEST_SYNC(adjust);
+	GUEST_ASSERT(adjust <= max);
+}
+
+static void l2_guest_code(void)
+{
+	uint64_t l1_tsc = rdtsc() - TSC_OFFSET_VALUE;
+
+	wrmsr(MSR_IA32_TSC, l1_tsc - TSC_ADJUST_VALUE);
+	check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
+
+	/* Exit to L1 */
+	__asm__ __volatile__("vmcall");
+}
+
+static void l1_guest_code(struct vmx_pages *vmx_pages)
+{
+#define L2_GUEST_STACK_SIZE 64
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	uint32_t control;
+	uintptr_t save_cr3;
+
+	GUEST_ASSERT(rdtsc() < TSC_ADJUST_VALUE);
+	wrmsr(MSR_IA32_TSC, rdtsc() - TSC_ADJUST_VALUE);
+	check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
+
+	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+
+	/* Prepare the VMCS for L2 execution. */
+	prepare_vmcs(vmx_pages, l2_guest_code,
+		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+	control = vmreadz(CPU_BASED_VM_EXEC_CONTROL);
+	control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETING;
+	vmwrite(CPU_BASED_VM_EXEC_CONTROL, control);
+	vmwrite(TSC_OFFSET, TSC_OFFSET_VALUE);
+
+	/* Jump into L2.  First, test failure to load guest CR3.  */
+	save_cr3 = vmreadz(GUEST_CR3);
+	vmwrite(GUEST_CR3, -1ull);
+	GUEST_ASSERT(!vmlaunch());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) ==
+		     (EXIT_REASON_FAILED_VMENTRY | EXIT_REASON_INVALID_STATE));
+	check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
+	vmwrite(GUEST_CR3, save_cr3);
+
+	GUEST_ASSERT(!vmlaunch());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+	check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
+
+	GUEST_DONE();
+}
+
+void report(int64_t val)
+{
+	printf("IA32_TSC_ADJUST is %ld (%lld * TSC_ADJUST_VALUE + %lld).\n",
+	       val, val / TSC_ADJUST_VALUE, val % TSC_ADJUST_VALUE);
+}
+
+int main(int argc, char *argv[])
+{
+	struct vmx_pages *vmx_pages;
+	vm_vaddr_t vmx_pages_gva;
+	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
+
+	if (!(entry->ecx & CPUID_VMX)) {
+		fprintf(stderr, "nested VMX not enabled, skipping test\n");
+		exit(KSFT_SKIP);
+	}
+
+	vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+	/* Allocate VMX pages and shared descriptors (vmx_pages). */
+	vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva);
+	vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
+
+	for (;;) {
+		volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+		struct ucall uc;
+
+		vcpu_run(vm, VCPU_ID);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n",
+			    run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_ABORT:
+			TEST_ASSERT(false, "%s", (const char *)uc.args[0]);
+			/* NOT REACHED */
+		case UCALL_SYNC:
+			report(uc.args[1]);
+			break;
+		case UCALL_DONE:
+			goto done;
+		default:
+			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+		}
+	}
+
+	kvm_vm_free(vm);
+done:
+	return 0;
+}
-- 
cgit 


From eea192bfd96db157151d27dd9c5e3e6a50c5d6be Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:27 +0200
Subject: kvm: selftests: add cscope make target

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/Makefile | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 734a60da9776..959be146f789 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -29,7 +29,7 @@ include ../lib.mk
 
 STATIC_LIBS := $(OUTPUT)/libkvm.a
 LIBKVM_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM))
-EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS)
+EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS) cscope.*
 
 x := $(shell mkdir -p $(sort $(dir $(LIBKVM_OBJ))))
 $(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c
@@ -41,3 +41,12 @@ $(OUTPUT)/libkvm.a: $(LIBKVM_OBJ)
 all: $(STATIC_LIBS)
 $(TEST_GEN_PROGS): $(STATIC_LIBS)
 $(STATIC_LIBS):| khdr
+
+cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib ..
+cscope:
+	$(RM) cscope.*
+	(find $(include_paths) -name '*.h' \
+		-exec realpath --relative-base=$(PWD) {} \;; \
+	find . -name '*.c' \
+		-exec realpath --relative-base=$(PWD) {} \;) | sort -u > cscope.files
+	cscope -b
-- 
cgit 


From eabe7881d264fd8ee074636fe50c8a8af08fedfd Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:28 +0200
Subject: kvm: selftests: tidy up kvm_util

Tidy up kvm-util code: code/comment formatting, remove unused code,
and move x86 specific code out. We also move vcpu_dump() out of
common code, because not all arches (AArch64) have KVM_GET_REGS.

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/kvm_util.h     |  80 ++--
 .../selftests/kvm/include/x86_64/processor.h       |  20 +-
 tools/testing/selftests/kvm/lib/kvm_util.c         | 438 +++++----------------
 .../testing/selftests/kvm/lib/kvm_util_internal.h  |  22 +-
 tools/testing/selftests/kvm/lib/x86_64/processor.c | 245 ++++++++++++
 .../testing/selftests/kvm/x86_64/dirty_log_test.c  |   1 +
 6 files changed, 407 insertions(+), 399 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 7830c46f27d8..4d5e405ff246 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -17,12 +17,6 @@
 
 #include "sparsebit.h"
 
-/*
- * Memslots can't cover the gfn starting at this gpa otherwise vCPUs can't be
- * created. Only applies to VMs using EPT.
- */
-#define KVM_DEFAULT_IDENTITY_MAP_ADDRESS 0xfffbc000ul
-
 
 /* Callers of kvm_util only have an incomplete/opaque description of the
  * structure kvm_util is using to maintain the state of a VM.
@@ -33,11 +27,11 @@ typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */
 typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
 
 /* Minimum allocated guest virtual and physical addresses */
-#define KVM_UTIL_MIN_VADDR 0x2000
+#define KVM_UTIL_MIN_VADDR		0x2000
 
 #define DEFAULT_GUEST_PHY_PAGES		512
 #define DEFAULT_GUEST_STACK_VADDR_MIN	0xab6000
-#define DEFAULT_STACK_PGS               5
+#define DEFAULT_STACK_PGS		5
 
 enum vm_guest_mode {
 	VM_MODE_FLAT48PG,
@@ -58,15 +52,15 @@ void kvm_vm_restart(struct kvm_vm *vmp, int perm);
 void kvm_vm_release(struct kvm_vm *vmp);
 void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log);
 
-int kvm_memcmp_hva_gva(void *hva,
-	struct kvm_vm *vm, const vm_vaddr_t gva, size_t len);
+int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva,
+		       size_t len);
 
 void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename,
-	uint32_t data_memslot, uint32_t pgd_memslot);
+		     uint32_t data_memslot, uint32_t pgd_memslot);
 
 void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
-void vcpu_dump(FILE *stream, struct kvm_vm *vm,
-	uint32_t vcpuid, uint8_t indent);
+void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid,
+	       uint8_t indent);
 
 void vm_create_irqchip(struct kvm_vm *vm);
 
@@ -75,13 +69,14 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	uint64_t guest_paddr, uint32_t slot, uint64_t npages,
 	uint32_t flags);
 
-void vcpu_ioctl(struct kvm_vm *vm,
-	uint32_t vcpuid, unsigned long ioctl, void *arg);
+void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
+		void *arg);
 void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
 void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
-void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot, int gdt_memslot);
+void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot,
+		 int gdt_memslot);
 vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
-	uint32_t data_memslot, uint32_t pgd_memslot);
+			  uint32_t data_memslot, uint32_t pgd_memslot);
 void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 	      size_t size, uint32_t pgd_memslot);
 void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa);
@@ -93,56 +88,33 @@ struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
 int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
-	struct kvm_mp_state *mp_state);
-void vcpu_regs_get(struct kvm_vm *vm,
-	uint32_t vcpuid, struct kvm_regs *regs);
-void vcpu_regs_set(struct kvm_vm *vm,
-	uint32_t vcpuid, struct kvm_regs *regs);
+		       struct kvm_mp_state *mp_state);
+void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
+void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
 void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...);
-void vcpu_sregs_get(struct kvm_vm *vm,
-	uint32_t vcpuid, struct kvm_sregs *sregs);
-void vcpu_sregs_set(struct kvm_vm *vm,
-	uint32_t vcpuid, struct kvm_sregs *sregs);
-int _vcpu_sregs_set(struct kvm_vm *vm,
-	uint32_t vcpuid, struct kvm_sregs *sregs);
+void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid,
+		    struct kvm_sregs *sregs);
+void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid,
+		    struct kvm_sregs *sregs);
+int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid,
+		    struct kvm_sregs *sregs);
 void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid,
-			  struct kvm_vcpu_events *events);
+		     struct kvm_vcpu_events *events);
 void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid,
-			  struct kvm_vcpu_events *events);
-uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index);
-void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
-	uint64_t msr_value);
+		     struct kvm_vcpu_events *events);
 
 const char *exit_reason_str(unsigned int exit_reason);
 
 void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot);
 void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
-	uint32_t pgd_memslot);
-vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm,
-	vm_paddr_t paddr_min, uint32_t memslot);
-
-struct kvm_cpuid2 *kvm_get_supported_cpuid(void);
-void vcpu_set_cpuid(
-	struct kvm_vm *vm, uint32_t vcpuid, struct kvm_cpuid2 *cpuid);
-
-struct kvm_cpuid_entry2 *
-kvm_get_supported_cpuid_index(uint32_t function, uint32_t index);
-
-static inline struct kvm_cpuid_entry2 *
-kvm_get_supported_cpuid_entry(uint32_t function)
-{
-	return kvm_get_supported_cpuid_index(function, 0);
-}
+		 uint32_t pgd_memslot);
+vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
+			     uint32_t memslot);
 
 struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_size,
 				 void *guest_code);
 void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code);
 
-typedef void (*vmx_guest_code_t)(vm_vaddr_t vmxon_vaddr,
-				 vm_paddr_t vmxon_paddr,
-				 vm_vaddr_t vmcs_vaddr,
-				 vm_paddr_t vmcs_paddr);
-
 struct kvm_userspace_memory_region *
 kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
 				 uint64_t end);
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index bb76e8db9b2b..e2884c2b81ff 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -305,7 +305,25 @@ static inline unsigned long get_xmm(int n)
 
 struct kvm_x86_state;
 struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid);
-void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *state);
+void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid,
+		     struct kvm_x86_state *state);
+
+struct kvm_cpuid2 *kvm_get_supported_cpuid(void);
+void vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid,
+		    struct kvm_cpuid2 *cpuid);
+
+struct kvm_cpuid_entry2 *
+kvm_get_supported_cpuid_index(uint32_t function, uint32_t index);
+
+static inline struct kvm_cpuid_entry2 *
+kvm_get_supported_cpuid_entry(uint32_t function)
+{
+	return kvm_get_supported_cpuid_index(function, 0);
+}
+
+uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index);
+void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
+	  	  uint64_t msr_value);
 
 /*
  * Basic CPU control in CR0
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 4bd31bf04f53..1a8f8f9e3635 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -16,8 +16,6 @@
 #include <sys/stat.h>
 #include <linux/kernel.h>
 
-#define KVM_DEV_PATH "/dev/kvm"
-
 #define KVM_UTIL_PGS_PER_HUGEPG 512
 #define KVM_UTIL_MIN_PADDR      0x2000
 
@@ -30,7 +28,8 @@ static void *align(void *x, size_t size)
 	return (void *) (((size_t) x + mask) & ~mask);
 }
 
-/* Capability
+/*
+ * Capability
  *
  * Input Args:
  *   cap - Capability
@@ -92,13 +91,13 @@ static void vm_open(struct kvm_vm *vm, int perm)
 	if (vm->kvm_fd < 0)
 		exit(KSFT_SKIP);
 
-	/* Create VM. */
 	vm->fd = ioctl(vm->kvm_fd, KVM_CREATE_VM, NULL);
 	TEST_ASSERT(vm->fd >= 0, "KVM_CREATE_VM ioctl failed, "
 		"rc: %i errno: %i", vm->fd, errno);
 }
 
-/* VM Create
+/*
+ * VM Create
  *
  * Input Args:
  *   mode - VM Mode (e.g. VM_MODE_FLAT48PG)
@@ -121,7 +120,6 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	struct kvm_vm *vm;
 	int kvm_fd;
 
-	/* Allocate memory. */
 	vm = calloc(1, sizeof(*vm));
 	TEST_ASSERT(vm != NULL, "Insufficent Memory");
 
@@ -160,7 +158,8 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	return vm;
 }
 
-/* VM Restart
+/*
+ * VM Restart
  *
  * Input Args:
  *   vm - VM that has been released before
@@ -187,7 +186,8 @@ void kvm_vm_restart(struct kvm_vm *vmp, int perm)
 			    "  rc: %i errno: %i\n"
 			    "  slot: %u flags: 0x%x\n"
 			    "  guest_phys_addr: 0x%lx size: 0x%lx",
-			    ret, errno, region->region.slot, region->region.flags,
+			    ret, errno, region->region.slot,
+			    region->region.flags,
 			    region->region.guest_phys_addr,
 			    region->region.memory_size);
 	}
@@ -203,7 +203,8 @@ void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log)
 		    strerror(-ret));
 }
 
-/* Userspace Memory Region Find
+/*
+ * Userspace Memory Region Find
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -221,8 +222,8 @@ void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log)
  * of the regions is returned.  Null is returned only when no overlapping
  * region exists.
  */
-static struct userspace_mem_region *userspace_mem_region_find(
-	struct kvm_vm *vm, uint64_t start, uint64_t end)
+static struct userspace_mem_region *
+userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end)
 {
 	struct userspace_mem_region *region;
 
@@ -238,7 +239,8 @@ static struct userspace_mem_region *userspace_mem_region_find(
 	return NULL;
 }
 
-/* KVM Userspace Memory Region Find
+/*
+ * KVM Userspace Memory Region Find
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -266,7 +268,8 @@ kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
 	return &region->region;
 }
 
-/* VCPU Find
+/*
+ * VCPU Find
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -281,8 +284,7 @@ kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
  * returns a pointer to it.  Returns NULL if the VM doesn't contain a VCPU
  * for the specified vcpuid.
  */
-struct vcpu *vcpu_find(struct kvm_vm *vm,
-	uint32_t vcpuid)
+struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid)
 {
 	struct vcpu *vcpup;
 
@@ -294,7 +296,8 @@ struct vcpu *vcpu_find(struct kvm_vm *vm,
 	return NULL;
 }
 
-/* VM VCPU Remove
+/*
+ * VM VCPU Remove
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -331,11 +334,9 @@ void kvm_vm_release(struct kvm_vm *vmp)
 {
 	int ret;
 
-	/* Free VCPUs. */
 	while (vmp->vcpu_head)
 		vm_vcpu_rm(vmp, vmp->vcpu_head->id);
 
-	/* Close file descriptor for the VM. */
 	ret = close(vmp->fd);
 	TEST_ASSERT(ret == 0, "Close of vm fd failed,\n"
 		"  vmp->fd: %i rc: %i errno: %i", vmp->fd, ret, errno);
@@ -345,7 +346,8 @@ void kvm_vm_release(struct kvm_vm *vmp)
 		"  vmp->kvm_fd: %i rc: %i errno: %i", vmp->kvm_fd, ret, errno);
 }
 
-/* Destroys and frees the VM pointed to by vmp.
+/*
+ * Destroys and frees the VM pointed to by vmp.
  */
 void kvm_vm_free(struct kvm_vm *vmp)
 {
@@ -384,7 +386,8 @@ void kvm_vm_free(struct kvm_vm *vmp)
 	free(vmp);
 }
 
-/* Memory Compare, host virtual to guest virtual
+/*
+ * Memory Compare, host virtual to guest virtual
  *
  * Input Args:
  *   hva - Starting host virtual address
@@ -406,23 +409,25 @@ void kvm_vm_free(struct kvm_vm *vmp)
  * a length of len, to the guest bytes starting at the guest virtual
  * address given by gva.
  */
-int kvm_memcmp_hva_gva(void *hva,
-	struct kvm_vm *vm, vm_vaddr_t gva, size_t len)
+int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len)
 {
 	size_t amt;
 
-	/* Compare a batch of bytes until either a match is found
+	/*
+	 * Compare a batch of bytes until either a match is found
 	 * or all the bytes have been compared.
 	 */
 	for (uintptr_t offset = 0; offset < len; offset += amt) {
 		uintptr_t ptr1 = (uintptr_t)hva + offset;
 
-		/* Determine host address for guest virtual address
+		/*
+		 * Determine host address for guest virtual address
 		 * at offset.
 		 */
 		uintptr_t ptr2 = (uintptr_t)addr_gva2hva(vm, gva + offset);
 
-		/* Determine amount to compare on this pass.
+		/*
+		 * Determine amount to compare on this pass.
 		 * Don't allow the comparsion to cross a page boundary.
 		 */
 		amt = len - offset;
@@ -434,7 +439,8 @@ int kvm_memcmp_hva_gva(void *hva,
 		assert((ptr1 >> vm->page_shift) == ((ptr1 + amt - 1) >> vm->page_shift));
 		assert((ptr2 >> vm->page_shift) == ((ptr2 + amt - 1) >> vm->page_shift));
 
-		/* Perform the comparison.  If there is a difference
+		/*
+		 * Perform the comparison.  If there is a difference
 		 * return that result to the caller, otherwise need
 		 * to continue on looking for a mismatch.
 		 */
@@ -443,109 +449,15 @@ int kvm_memcmp_hva_gva(void *hva,
 			return ret;
 	}
 
-	/* No mismatch found.  Let the caller know the two memory
+	/*
+	 * No mismatch found.  Let the caller know the two memory
 	 * areas are equal.
 	 */
 	return 0;
 }
 
-/* Allocate an instance of struct kvm_cpuid2
- *
- * Input Args: None
- *
- * Output Args: None
- *
- * Return: A pointer to the allocated struct. The caller is responsible
- * for freeing this struct.
- *
- * Since kvm_cpuid2 uses a 0-length array to allow a the size of the
- * array to be decided at allocation time, allocation is slightly
- * complicated. This function uses a reasonable default length for
- * the array and performs the appropriate allocation.
- */
-static struct kvm_cpuid2 *allocate_kvm_cpuid2(void)
-{
-	struct kvm_cpuid2 *cpuid;
-	int nent = 100;
-	size_t size;
-
-	size = sizeof(*cpuid);
-	size += nent * sizeof(struct kvm_cpuid_entry2);
-	cpuid = malloc(size);
-	if (!cpuid) {
-		perror("malloc");
-		abort();
-	}
-
-	cpuid->nent = nent;
-
-	return cpuid;
-}
-
-/* KVM Supported CPUID Get
- *
- * Input Args: None
- *
- * Output Args:
- *
- * Return: The supported KVM CPUID
- *
- * Get the guest CPUID supported by KVM.
- */
-struct kvm_cpuid2 *kvm_get_supported_cpuid(void)
-{
-	static struct kvm_cpuid2 *cpuid;
-	int ret;
-	int kvm_fd;
-
-	if (cpuid)
-		return cpuid;
-
-	cpuid = allocate_kvm_cpuid2();
-	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
-	if (kvm_fd < 0)
-		exit(KSFT_SKIP);
-
-	ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid);
-	TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n",
-		    ret, errno);
-
-	close(kvm_fd);
-	return cpuid;
-}
-
-/* Locate a cpuid entry.
- *
- * Input Args:
- *   cpuid: The cpuid.
- *   function: The function of the cpuid entry to find.
- *
- * Output Args: None
- *
- * Return: A pointer to the cpuid entry. Never returns NULL.
- */
-struct kvm_cpuid_entry2 *
-kvm_get_supported_cpuid_index(uint32_t function, uint32_t index)
-{
-	struct kvm_cpuid2 *cpuid;
-	struct kvm_cpuid_entry2 *entry = NULL;
-	int i;
-
-	cpuid = kvm_get_supported_cpuid();
-	for (i = 0; i < cpuid->nent; i++) {
-		if (cpuid->entries[i].function == function &&
-		    cpuid->entries[i].index == index) {
-			entry = &cpuid->entries[i];
-			break;
-		}
-	}
-
-	TEST_ASSERT(entry, "Guest CPUID entry not found: (EAX=%x, ECX=%x).",
-		    function, index);
-	return entry;
-}
-
-/* VM Userspace Memory Region Add
+/*
+ * VM Userspace Memory Region Add
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -587,7 +499,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 		"  vm->max_gfn: 0x%lx vm->page_size: 0x%x",
 		guest_paddr, npages, vm->max_gfn, vm->page_size);
 
-	/* Confirm a mem region with an overlapping address doesn't
+	/*
+	 * Confirm a mem region with an overlapping address doesn't
 	 * already exist.
 	 */
 	region = (struct userspace_mem_region *) userspace_mem_region_find(
@@ -678,7 +591,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	vm->userspace_mem_region_head = region;
 }
 
-/* Memslot to region
+/*
+ * Memslot to region
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -692,8 +606,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
  *   on error (e.g. currently no memory region using memslot as a KVM
  *   memory slot ID).
  */
-static struct userspace_mem_region *memslot2region(struct kvm_vm *vm,
-	uint32_t memslot)
+static struct userspace_mem_region *
+memslot2region(struct kvm_vm *vm, uint32_t memslot)
 {
 	struct userspace_mem_region *region;
 
@@ -713,7 +627,8 @@ static struct userspace_mem_region *memslot2region(struct kvm_vm *vm,
 	return region;
 }
 
-/* VM Memory Region Flags Set
+/*
+ * VM Memory Region Flags Set
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -731,7 +646,6 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags)
 	int ret;
 	struct userspace_mem_region *region;
 
-	/* Locate memory region. */
 	region = memslot2region(vm, slot);
 
 	region->region.flags = flags;
@@ -743,7 +657,8 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags)
 		ret, errno, slot, flags);
 }
 
-/* VCPU mmap Size
+/*
+ * VCPU mmap Size
  *
  * Input Args: None
  *
@@ -773,7 +688,8 @@ static int vcpu_mmap_sz(void)
 	return ret;
 }
 
-/* VM VCPU Add
+/*
+ * VM VCPU Add
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -786,7 +702,8 @@ static int vcpu_mmap_sz(void)
  * Creates and adds to the VM specified by vm and virtual CPU with
  * the ID given by vcpuid.
  */
-void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot, int gdt_memslot)
+void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot,
+		 int gdt_memslot)
 {
 	struct vcpu *vcpu;
 
@@ -824,7 +741,8 @@ void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot, int gdt_me
 	vcpu_setup(vm, vcpuid, pgd_memslot, gdt_memslot);
 }
 
-/* VM Virtual Address Unused Gap
+/*
+ * VM Virtual Address Unused Gap
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -844,14 +762,14 @@ void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot, int gdt_me
  * sz unallocated bytes >= vaddr_min is available.
  */
 static vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz,
-	vm_vaddr_t vaddr_min)
+				      vm_vaddr_t vaddr_min)
 {
 	uint64_t pages = (sz + vm->page_size - 1) >> vm->page_shift;
 
 	/* Determine lowest permitted virtual page index. */
 	uint64_t pgidx_start = (vaddr_min + vm->page_size - 1) >> vm->page_shift;
 	if ((pgidx_start * vm->page_size) < vaddr_min)
-			goto no_va_found;
+		goto no_va_found;
 
 	/* Loop over section with enough valid virtual page indexes. */
 	if (!sparsebit_is_set_num(vm->vpages_valid,
@@ -910,7 +828,8 @@ va_found:
 	return pgidx_start * vm->page_size;
 }
 
-/* VM Virtual Address Allocate
+/*
+ * VM Virtual Address Allocate
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -931,13 +850,14 @@ va_found:
  * a page.
  */
 vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
-	uint32_t data_memslot, uint32_t pgd_memslot)
+			  uint32_t data_memslot, uint32_t pgd_memslot)
 {
 	uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0);
 
 	virt_pgd_alloc(vm, pgd_memslot);
 
-	/* Find an unused range of virtual page addresses of at least
+	/*
+	 * Find an unused range of virtual page addresses of at least
 	 * pages in length.
 	 */
 	vm_vaddr_t vaddr_start = vm_vaddr_unused_gap(vm, sz, vaddr_min);
@@ -991,7 +911,8 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 	}
 }
 
-/* Address VM Physical to Host Virtual
+/*
+ * Address VM Physical to Host Virtual
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1023,7 +944,8 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa)
 	return NULL;
 }
 
-/* Address Host Virtual to VM Physical
+/*
+ * Address Host Virtual to VM Physical
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1057,7 +979,8 @@ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva)
 	return -1;
 }
 
-/* VM Create IRQ Chip
+/*
+ * VM Create IRQ Chip
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1079,7 +1002,8 @@ void vm_create_irqchip(struct kvm_vm *vm)
 	vm->has_irqchip = true;
 }
 
-/* VM VCPU State
+/*
+ * VM VCPU State
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1101,7 +1025,8 @@ struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid)
 	return vcpu->state;
 }
 
-/* VM VCPU Run
+/*
+ * VM VCPU Run
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1127,13 +1052,14 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid)
 	int rc;
 
 	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
-        do {
+	do {
 		rc = ioctl(vcpu->fd, KVM_RUN, NULL);
 	} while (rc == -1 && errno == EINTR);
 	return rc;
 }
 
-/* VM VCPU Set MP State
+/*
+ * VM VCPU Set MP State
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1148,7 +1074,7 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid)
  * by mp_state.
  */
 void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
-	struct kvm_mp_state *mp_state)
+		       struct kvm_mp_state *mp_state)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	int ret;
@@ -1160,7 +1086,8 @@ void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
 		"rc: %i errno: %i", ret, errno);
 }
 
-/* VM VCPU Regs Get
+/*
+ * VM VCPU Regs Get
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1174,21 +1101,20 @@ void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
  * Obtains the current register state for the VCPU specified by vcpuid
  * and stores it at the location given by regs.
  */
-void vcpu_regs_get(struct kvm_vm *vm,
-	uint32_t vcpuid, struct kvm_regs *regs)
+void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	int ret;
 
 	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
 
-	/* Get the regs. */
 	ret = ioctl(vcpu->fd, KVM_GET_REGS, regs);
 	TEST_ASSERT(ret == 0, "KVM_GET_REGS failed, rc: %i errno: %i",
 		ret, errno);
 }
 
-/* VM VCPU Regs Set
+/*
+ * VM VCPU Regs Set
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1202,165 +1128,46 @@ void vcpu_regs_get(struct kvm_vm *vm,
  * Sets the regs of the VCPU specified by vcpuid to the values
  * given by regs.
  */
-void vcpu_regs_set(struct kvm_vm *vm,
-	uint32_t vcpuid, struct kvm_regs *regs)
+void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	int ret;
 
 	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
 
-	/* Set the regs. */
 	ret = ioctl(vcpu->fd, KVM_SET_REGS, regs);
 	TEST_ASSERT(ret == 0, "KVM_SET_REGS failed, rc: %i errno: %i",
 		ret, errno);
 }
 
 void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid,
-			  struct kvm_vcpu_events *events)
+		     struct kvm_vcpu_events *events)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	int ret;
 
 	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
 
-	/* Get the regs. */
 	ret = ioctl(vcpu->fd, KVM_GET_VCPU_EVENTS, events);
 	TEST_ASSERT(ret == 0, "KVM_GET_VCPU_EVENTS, failed, rc: %i errno: %i",
 		ret, errno);
 }
 
 void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid,
-			  struct kvm_vcpu_events *events)
+		     struct kvm_vcpu_events *events)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	int ret;
 
 	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
 
-	/* Set the regs. */
 	ret = ioctl(vcpu->fd, KVM_SET_VCPU_EVENTS, events);
 	TEST_ASSERT(ret == 0, "KVM_SET_VCPU_EVENTS, failed, rc: %i errno: %i",
 		ret, errno);
 }
 
-/* VCPU Get MSR
- *
- * Input Args:
- *   vm - Virtual Machine
- *   vcpuid - VCPU ID
- *   msr_index - Index of MSR
- *
- * Output Args: None
- *
- * Return: On success, value of the MSR. On failure a TEST_ASSERT is produced.
- *
- * Get value of MSR for VCPU.
- */
-uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index)
-{
-	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
-	struct {
-		struct kvm_msrs header;
-		struct kvm_msr_entry entry;
-	} buffer = {};
-	int r;
-
-	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
-	buffer.header.nmsrs = 1;
-	buffer.entry.index = msr_index;
-	r = ioctl(vcpu->fd, KVM_GET_MSRS, &buffer.header);
-	TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n"
-		"  rc: %i errno: %i", r, errno);
-
-	return buffer.entry.data;
-}
-
-/* VCPU Set MSR
- *
- * Input Args:
- *   vm - Virtual Machine
- *   vcpuid - VCPU ID
- *   msr_index - Index of MSR
- *   msr_value - New value of MSR
- *
- * Output Args: None
- *
- * Return: On success, nothing. On failure a TEST_ASSERT is produced.
- *
- * Set value of MSR for VCPU.
- */
-void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
-	uint64_t msr_value)
-{
-	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
-	struct {
-		struct kvm_msrs header;
-		struct kvm_msr_entry entry;
-	} buffer = {};
-	int r;
-
-	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
-	memset(&buffer, 0, sizeof(buffer));
-	buffer.header.nmsrs = 1;
-	buffer.entry.index = msr_index;
-	buffer.entry.data = msr_value;
-	r = ioctl(vcpu->fd, KVM_SET_MSRS, &buffer.header);
-	TEST_ASSERT(r == 1, "KVM_SET_MSRS IOCTL failed,\n"
-		"  rc: %i errno: %i", r, errno);
-}
-
-/* VM VCPU Args Set
- *
- * Input Args:
- *   vm - Virtual Machine
- *   vcpuid - VCPU ID
- *   num - number of arguments
- *   ... - arguments, each of type uint64_t
- *
- * Output Args: None
- *
- * Return: None
- *
- * Sets the first num function input arguments to the values
- * given as variable args.  Each of the variable args is expected to
- * be of type uint64_t.
- */
-void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
-{
-	va_list ap;
-	struct kvm_regs regs;
-
-	TEST_ASSERT(num >= 1 && num <= 6, "Unsupported number of args,\n"
-		    "  num: %u\n",
-		    num);
-
-	va_start(ap, num);
-	vcpu_regs_get(vm, vcpuid, &regs);
-
-	if (num >= 1)
-		regs.rdi = va_arg(ap, uint64_t);
-
-	if (num >= 2)
-		regs.rsi = va_arg(ap, uint64_t);
-
-	if (num >= 3)
-		regs.rdx = va_arg(ap, uint64_t);
-
-	if (num >= 4)
-		regs.rcx = va_arg(ap, uint64_t);
-
-	if (num >= 5)
-		regs.r8 = va_arg(ap, uint64_t);
-
-	if (num >= 6)
-		regs.r9 = va_arg(ap, uint64_t);
-
-	vcpu_regs_set(vm, vcpuid, &regs);
-	va_end(ap);
-}
-
-/* VM VCPU System Regs Get
+/*
+ * VM VCPU System Regs Get
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1374,22 +1181,20 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
  * Obtains the current system register state for the VCPU specified by
  * vcpuid and stores it at the location given by sregs.
  */
-void vcpu_sregs_get(struct kvm_vm *vm,
-	uint32_t vcpuid, struct kvm_sregs *sregs)
+void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	int ret;
 
 	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
 
-	/* Get the regs. */
-	/* Get the regs. */
 	ret = ioctl(vcpu->fd, KVM_GET_SREGS, sregs);
 	TEST_ASSERT(ret == 0, "KVM_GET_SREGS failed, rc: %i errno: %i",
 		ret, errno);
 }
 
-/* VM VCPU System Regs Set
+/*
+ * VM VCPU System Regs Set
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1403,27 +1208,25 @@ void vcpu_sregs_get(struct kvm_vm *vm,
  * Sets the system regs of the VCPU specified by vcpuid to the values
  * given by sregs.
  */
-void vcpu_sregs_set(struct kvm_vm *vm,
-	uint32_t vcpuid, struct kvm_sregs *sregs)
+void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs)
 {
 	int ret = _vcpu_sregs_set(vm, vcpuid, sregs);
 	TEST_ASSERT(ret == 0, "KVM_RUN IOCTL failed, "
 		"rc: %i errno: %i", ret, errno);
 }
 
-int _vcpu_sregs_set(struct kvm_vm *vm,
-	uint32_t vcpuid, struct kvm_sregs *sregs)
+int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	int ret;
 
 	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
 
-	/* Get the regs. */
 	return ioctl(vcpu->fd, KVM_SET_SREGS, sregs);
 }
 
-/* VCPU Ioctl
+/*
+ * VCPU Ioctl
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1435,8 +1238,8 @@ int _vcpu_sregs_set(struct kvm_vm *vm,
  *
  * Issues an arbitrary ioctl on a VCPU fd.
  */
-void vcpu_ioctl(struct kvm_vm *vm,
-	uint32_t vcpuid, unsigned long cmd, void *arg)
+void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid,
+		unsigned long cmd, void *arg)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	int ret;
@@ -1448,7 +1251,8 @@ void vcpu_ioctl(struct kvm_vm *vm,
 		cmd, ret, errno, strerror(errno));
 }
 
-/* VM Ioctl
+/*
+ * VM Ioctl
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1468,7 +1272,8 @@ void vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg)
 		cmd, ret, errno, strerror(errno));
 }
 
-/* VM Dump
+/*
+ * VM Dump
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1515,38 +1320,6 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 		vcpu_dump(stream, vm, vcpu->id, indent + 2);
 }
 
-/* VM VCPU Dump
- *
- * Input Args:
- *   vm - Virtual Machine
- *   vcpuid - VCPU ID
- *   indent - Left margin indent amount
- *
- * Output Args:
- *   stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps the current state of the VCPU specified by vcpuid, within the VM
- * given by vm, to the FILE stream given by stream.
- */
-void vcpu_dump(FILE *stream, struct kvm_vm *vm,
-	uint32_t vcpuid, uint8_t indent)
-{
-		struct kvm_regs regs;
-		struct kvm_sregs sregs;
-
-		fprintf(stream, "%*scpuid: %u\n", indent, "", vcpuid);
-
-		fprintf(stream, "%*sregs:\n", indent + 2, "");
-		vcpu_regs_get(vm, vcpuid, &regs);
-		regs_dump(stream, &regs, indent + 4);
-
-		fprintf(stream, "%*ssregs:\n", indent + 2, "");
-		vcpu_sregs_get(vm, vcpuid, &sregs);
-		sregs_dump(stream, &sregs, indent + 4);
-}
-
 /* Known KVM exit reasons */
 static struct exit_reason {
 	unsigned int reason;
@@ -1577,7 +1350,8 @@ static struct exit_reason {
 #endif
 };
 
-/* Exit Reason String
+/*
+ * Exit Reason String
  *
  * Input Args:
  *   exit_reason - Exit reason
@@ -1603,7 +1377,8 @@ const char *exit_reason_str(unsigned int exit_reason)
 	return "Unknown";
 }
 
-/* Physical Page Allocate
+/*
+ * Physical Page Allocate
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1620,8 +1395,8 @@ const char *exit_reason_str(unsigned int exit_reason)
  * and its address is returned.  A TEST_ASSERT failure occurs if no
  * page is available at or above paddr_min.
  */
-vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm,
-	vm_paddr_t paddr_min, uint32_t memslot)
+vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
+			     uint32_t memslot)
 {
 	struct userspace_mem_region *region;
 	sparsebit_idx_t pg;
@@ -1631,17 +1406,15 @@ vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm,
 		"  paddr_min: 0x%lx page_size: 0x%x",
 		paddr_min, vm->page_size);
 
-	/* Locate memory region. */
 	region = memslot2region(vm, memslot);
-
-	/* Locate next available physical page at or above paddr_min. */
 	pg = paddr_min >> vm->page_shift;
 
+	/* Locate next available physical page at or above paddr_min. */
 	if (!sparsebit_is_set(region->unused_phy_pages, pg)) {
 		pg = sparsebit_next_set(region->unused_phy_pages, pg);
 		if (pg == 0) {
 			fprintf(stderr, "No guest physical page available, "
-				"paddr_min: 0x%lx page_size: 0x%x memslot: %u",
+				"paddr_min: 0x%lx page_size: 0x%x memslot: %u\n",
 				paddr_min, vm->page_size, memslot);
 			fputs("---- vm dump ----\n", stderr);
 			vm_dump(stderr, vm, 2);
@@ -1655,7 +1428,8 @@ vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm,
 	return pg * vm->page_size;
 }
 
-/* Address Guest Virtual to Host Virtual
+/*
+ * Address Guest Virtual to Host Virtual
  *
  * Input Args:
  *   vm - Virtual Machine
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index 36367be0fe26..3702c560bbf2 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -11,18 +11,19 @@
 
 #include "sparsebit.h"
 
+#define KVM_DEV_PATH		"/dev/kvm"
+
 #ifndef BITS_PER_BYTE
-#define BITS_PER_BYTE           8
+#define BITS_PER_BYTE		8
 #endif
 
 #ifndef BITS_PER_LONG
-#define BITS_PER_LONG (BITS_PER_BYTE * sizeof(long))
+#define BITS_PER_LONG		(BITS_PER_BYTE * sizeof(long))
 #endif
 
 #define DIV_ROUND_UP(n, d)	(((n) + (d) - 1) / (d))
-#define BITS_TO_LONGS(nr)       DIV_ROUND_UP(nr, BITS_PER_LONG)
+#define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_LONG)
 
-/* Concrete definition of struct kvm_vm. */
 struct userspace_mem_region {
 	struct userspace_mem_region *next, *prev;
 	struct kvm_userspace_memory_region region;
@@ -53,7 +54,6 @@ struct kvm_vm {
 	struct userspace_mem_region *userspace_mem_region_head;
 	struct sparsebit *vpages_valid;
 	struct sparsebit *vpages_mapped;
-
 	bool has_irqchip;
 	bool pgd_created;
 	vm_paddr_t pgd;
@@ -61,13 +61,11 @@ struct kvm_vm {
 	vm_vaddr_t tss;
 };
 
-struct vcpu *vcpu_find(struct kvm_vm *vm,
-	uint32_t vcpuid);
-void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot);
+struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot,
+		int gdt_memslot);
 void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
-void regs_dump(FILE *stream, struct kvm_regs *regs,
-	uint8_t indent);
-void sregs_dump(FILE *stream, struct kvm_sregs *sregs,
-	uint8_t indent);
+void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent);
+void sregs_dump(FILE *stream, struct kvm_sregs *sregs, uint8_t indent);
 
 #endif /* SELFTEST_KVM_UTIL_INTERNAL_H */
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 79c2c5c203c0..67f84fbb0ca4 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -672,6 +672,102 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
 	vcpu_set_mp_state(vm, vcpuid, &mp_state);
 }
 
+/* Allocate an instance of struct kvm_cpuid2
+ *
+ * Input Args: None
+ *
+ * Output Args: None
+ *
+ * Return: A pointer to the allocated struct. The caller is responsible
+ * for freeing this struct.
+ *
+ * Since kvm_cpuid2 uses a 0-length array to allow a the size of the
+ * array to be decided at allocation time, allocation is slightly
+ * complicated. This function uses a reasonable default length for
+ * the array and performs the appropriate allocation.
+ */
+static struct kvm_cpuid2 *allocate_kvm_cpuid2(void)
+{
+	struct kvm_cpuid2 *cpuid;
+	int nent = 100;
+	size_t size;
+
+	size = sizeof(*cpuid);
+	size += nent * sizeof(struct kvm_cpuid_entry2);
+	cpuid = malloc(size);
+	if (!cpuid) {
+		perror("malloc");
+		abort();
+	}
+
+	cpuid->nent = nent;
+
+	return cpuid;
+}
+
+/* KVM Supported CPUID Get
+ *
+ * Input Args: None
+ *
+ * Output Args:
+ *
+ * Return: The supported KVM CPUID
+ *
+ * Get the guest CPUID supported by KVM.
+ */
+struct kvm_cpuid2 *kvm_get_supported_cpuid(void)
+{
+	static struct kvm_cpuid2 *cpuid;
+	int ret;
+	int kvm_fd;
+
+	if (cpuid)
+		return cpuid;
+
+	cpuid = allocate_kvm_cpuid2();
+	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
+	if (kvm_fd < 0)
+		exit(KSFT_SKIP);
+
+	ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid);
+	TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n",
+		    ret, errno);
+
+	close(kvm_fd);
+	return cpuid;
+}
+
+/* Locate a cpuid entry.
+ *
+ * Input Args:
+ *   cpuid: The cpuid.
+ *   function: The function of the cpuid entry to find.
+ *
+ * Output Args: None
+ *
+ * Return: A pointer to the cpuid entry. Never returns NULL.
+ */
+struct kvm_cpuid_entry2 *
+kvm_get_supported_cpuid_index(uint32_t function, uint32_t index)
+{
+	struct kvm_cpuid2 *cpuid;
+	struct kvm_cpuid_entry2 *entry = NULL;
+	int i;
+
+	cpuid = kvm_get_supported_cpuid();
+	for (i = 0; i < cpuid->nent; i++) {
+		if (cpuid->entries[i].function == function &&
+		    cpuid->entries[i].index == index) {
+			entry = &cpuid->entries[i];
+			break;
+		}
+	}
+
+	TEST_ASSERT(entry, "Guest CPUID entry not found: (EAX=%x, ECX=%x).",
+		    function, index);
+	return entry;
+}
+
 /* VM VCPU CPUID Set
  *
  * Input Args:
@@ -698,6 +794,7 @@ void vcpu_set_cpuid(struct kvm_vm *vm,
 		    rc, errno);
 
 }
+
 /* Create a VM with reasonable defaults
  *
  * Input Args:
@@ -742,6 +839,154 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
 	return vm;
 }
 
+/* VCPU Get MSR
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpuid - VCPU ID
+ *   msr_index - Index of MSR
+ *
+ * Output Args: None
+ *
+ * Return: On success, value of the MSR. On failure a TEST_ASSERT is produced.
+ *
+ * Get value of MSR for VCPU.
+ */
+uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+	struct {
+		struct kvm_msrs header;
+		struct kvm_msr_entry entry;
+	} buffer = {};
+	int r;
+
+	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+	buffer.header.nmsrs = 1;
+	buffer.entry.index = msr_index;
+	r = ioctl(vcpu->fd, KVM_GET_MSRS, &buffer.header);
+	TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n"
+		"  rc: %i errno: %i", r, errno);
+
+	return buffer.entry.data;
+}
+
+/* VCPU Set MSR
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpuid - VCPU ID
+ *   msr_index - Index of MSR
+ *   msr_value - New value of MSR
+ *
+ * Output Args: None
+ *
+ * Return: On success, nothing. On failure a TEST_ASSERT is produced.
+ *
+ * Set value of MSR for VCPU.
+ */
+void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
+	uint64_t msr_value)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+	struct {
+		struct kvm_msrs header;
+		struct kvm_msr_entry entry;
+	} buffer = {};
+	int r;
+
+	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+	memset(&buffer, 0, sizeof(buffer));
+	buffer.header.nmsrs = 1;
+	buffer.entry.index = msr_index;
+	buffer.entry.data = msr_value;
+	r = ioctl(vcpu->fd, KVM_SET_MSRS, &buffer.header);
+	TEST_ASSERT(r == 1, "KVM_SET_MSRS IOCTL failed,\n"
+		"  rc: %i errno: %i", r, errno);
+}
+
+/* VM VCPU Args Set
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpuid - VCPU ID
+ *   num - number of arguments
+ *   ... - arguments, each of type uint64_t
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Sets the first num function input arguments to the values
+ * given as variable args.  Each of the variable args is expected to
+ * be of type uint64_t.
+ */
+void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
+{
+	va_list ap;
+	struct kvm_regs regs;
+
+	TEST_ASSERT(num >= 1 && num <= 6, "Unsupported number of args,\n"
+		    "  num: %u\n",
+		    num);
+
+	va_start(ap, num);
+	vcpu_regs_get(vm, vcpuid, &regs);
+
+	if (num >= 1)
+		regs.rdi = va_arg(ap, uint64_t);
+
+	if (num >= 2)
+		regs.rsi = va_arg(ap, uint64_t);
+
+	if (num >= 3)
+		regs.rdx = va_arg(ap, uint64_t);
+
+	if (num >= 4)
+		regs.rcx = va_arg(ap, uint64_t);
+
+	if (num >= 5)
+		regs.r8 = va_arg(ap, uint64_t);
+
+	if (num >= 6)
+		regs.r9 = va_arg(ap, uint64_t);
+
+	vcpu_regs_set(vm, vcpuid, &regs);
+	va_end(ap);
+}
+
+/*
+ * VM VCPU Dump
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpuid - VCPU ID
+ *   indent - Left margin indent amount
+ *
+ * Output Args:
+ *   stream - Output FILE stream
+ *
+ * Return: None
+ *
+ * Dumps the current state of the VCPU specified by vcpuid, within the VM
+ * given by vm, to the FILE stream given by stream.
+ */
+void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
+{
+	struct kvm_regs regs;
+	struct kvm_sregs sregs;
+
+	fprintf(stream, "%*scpuid: %u\n", indent, "", vcpuid);
+
+	fprintf(stream, "%*sregs:\n", indent + 2, "");
+	vcpu_regs_get(vm, vcpuid, &regs);
+	regs_dump(stream, &regs, indent + 4);
+
+	fprintf(stream, "%*ssregs:\n", indent + 2, "");
+	vcpu_sregs_get(vm, vcpuid, &sregs);
+	sregs_dump(stream, &sregs, indent + 4);
+}
+
 struct kvm_x86_state {
 	struct kvm_vcpu_events events;
 	struct kvm_mp_state mp_state;
diff --git a/tools/testing/selftests/kvm/x86_64/dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/dirty_log_test.c
index 7cf3e4ae6046..395a6e07d37c 100644
--- a/tools/testing/selftests/kvm/x86_64/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/x86_64/dirty_log_test.c
@@ -15,6 +15,7 @@
 
 #include "test_util.h"
 #include "kvm_util.h"
+#include "processor.h"
 
 #define  DEBUG                 printf
 
-- 
cgit 


From d5106539cfef362e3870b6aa8b5ca587cd67e93d Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:29 +0200
Subject: kvm: selftests: add vm_phy_pages_alloc

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/kvm_util.h |  2 +
 tools/testing/selftests/kvm/lib/kvm_util.c     | 60 ++++++++++++++++----------
 2 files changed, 39 insertions(+), 23 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 4d5e405ff246..e0c9cf4d1c49 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -110,6 +110,8 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 		 uint32_t pgd_memslot);
 vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
 			     uint32_t memslot);
+vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
+			      vm_paddr_t paddr_min, uint32_t memslot);
 
 struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_size,
 				 void *guest_code);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 1a8f8f9e3635..26c3c4350a88 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1378,10 +1378,11 @@ const char *exit_reason_str(unsigned int exit_reason)
 }
 
 /*
- * Physical Page Allocate
+ * Physical Contiguous Page Allocator
  *
  * Input Args:
  *   vm - Virtual Machine
+ *   num - number of pages
  *   paddr_min - Physical address minimum
  *   memslot - Memory region to allocate page from
  *
@@ -1390,16 +1391,18 @@ const char *exit_reason_str(unsigned int exit_reason)
  * Return:
  *   Starting physical address
  *
- * Within the VM specified by vm, locates an available physical page
- * at or above paddr_min.  If found, the page is marked as in use
- * and its address is returned.  A TEST_ASSERT failure occurs if no
- * page is available at or above paddr_min.
+ * Within the VM specified by vm, locates a range of available physical
+ * pages at or above paddr_min. If found, the pages are marked as in use
+ * and thier base address is returned. A TEST_ASSERT failure occurs if
+ * not enough pages are available at or above paddr_min.
  */
-vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
-			     uint32_t memslot)
+vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
+			      vm_paddr_t paddr_min, uint32_t memslot)
 {
 	struct userspace_mem_region *region;
-	sparsebit_idx_t pg;
+	sparsebit_idx_t pg, base;
+
+	TEST_ASSERT(num > 0, "Must allocate at least one page");
 
 	TEST_ASSERT((paddr_min % vm->page_size) == 0, "Min physical address "
 		"not divisible by page size.\n"
@@ -1407,25 +1410,36 @@ vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
 		paddr_min, vm->page_size);
 
 	region = memslot2region(vm, memslot);
-	pg = paddr_min >> vm->page_shift;
-
-	/* Locate next available physical page at or above paddr_min. */
-	if (!sparsebit_is_set(region->unused_phy_pages, pg)) {
-		pg = sparsebit_next_set(region->unused_phy_pages, pg);
-		if (pg == 0) {
-			fprintf(stderr, "No guest physical page available, "
-				"paddr_min: 0x%lx page_size: 0x%x memslot: %u\n",
-				paddr_min, vm->page_size, memslot);
-			fputs("---- vm dump ----\n", stderr);
-			vm_dump(stderr, vm, 2);
-			abort();
+	base = pg = paddr_min >> vm->page_shift;
+
+	do {
+		for (; pg < base + num; ++pg) {
+			if (!sparsebit_is_set(region->unused_phy_pages, pg)) {
+				base = pg = sparsebit_next_set(region->unused_phy_pages, pg);
+				break;
+			}
 		}
+	} while (pg && pg != base + num);
+
+	if (pg == 0) {
+		fprintf(stderr, "No guest physical page available, "
+			"paddr_min: 0x%lx page_size: 0x%x memslot: %u\n",
+			paddr_min, vm->page_size, memslot);
+		fputs("---- vm dump ----\n", stderr);
+		vm_dump(stderr, vm, 2);
+		abort();
 	}
 
-	/* Specify page as in use and return its address. */
-	sparsebit_clear(region->unused_phy_pages, pg);
+	for (pg = base; pg < base + num; ++pg)
+		sparsebit_clear(region->unused_phy_pages, pg);
+
+	return base * vm->page_size;
+}
 
-	return pg * vm->page_size;
+vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
+			     uint32_t memslot)
+{
+	return vm_phy_pages_alloc(vm, 1, paddr_min, memslot);
 }
 
 /*
-- 
cgit 


From 7a6629ef746d1a50cc9247bd7c92ce6b38b8ed68 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:30 +0200
Subject: kvm: selftests: add virt mem support for aarch64

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../testing/selftests/kvm/lib/aarch64/processor.c  | 216 +++++++++++++++++++++
 tools/testing/selftests/kvm/lib/kvm_util.c         |   1 +
 .../testing/selftests/kvm/lib/kvm_util_internal.h  |   1 +
 3 files changed, 218 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/lib/aarch64/processor.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
new file mode 100644
index 000000000000..464d4d074249
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -0,0 +1,216 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * AArch64 code
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+
+#include "kvm_util.h"
+#include "../kvm_util_internal.h"
+
+#define KVM_GUEST_PAGE_TABLE_MIN_PADDR		0x180000
+
+static uint64_t page_align(struct kvm_vm *vm, uint64_t v)
+{
+	return (v + vm->page_size) & ~(vm->page_size - 1);
+}
+
+static uint64_t pgd_index(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+	unsigned int shift = (vm->pgtable_levels - 1) * (vm->page_shift - 3) + vm->page_shift;
+	uint64_t mask = (1UL << (vm->va_bits - shift)) - 1;
+
+	return (gva >> shift) & mask;
+}
+
+static uint64_t pud_index(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+	unsigned int shift = 2 * (vm->page_shift - 3) + vm->page_shift;
+	uint64_t mask = (1UL << (vm->page_shift - 3)) - 1;
+
+	TEST_ASSERT(vm->pgtable_levels == 4,
+		"Mode %d does not have 4 page table levels", vm->mode);
+
+	return (gva >> shift) & mask;
+}
+
+static uint64_t pmd_index(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+	unsigned int shift = (vm->page_shift - 3) + vm->page_shift;
+	uint64_t mask = (1UL << (vm->page_shift - 3)) - 1;
+
+	TEST_ASSERT(vm->pgtable_levels >= 3,
+		"Mode %d does not have >= 3 page table levels", vm->mode);
+
+	return (gva >> shift) & mask;
+}
+
+static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+	uint64_t mask = (1UL << (vm->page_shift - 3)) - 1;
+	return (gva >> vm->page_shift) & mask;
+}
+
+static uint64_t pte_addr(struct kvm_vm *vm, uint64_t entry)
+{
+	uint64_t mask = ((1UL << (vm->va_bits - vm->page_shift)) - 1) << vm->page_shift;
+	return entry & mask;
+}
+
+static uint64_t ptrs_per_pgd(struct kvm_vm *vm)
+{
+	unsigned int shift = (vm->pgtable_levels - 1) * (vm->page_shift - 3) + vm->page_shift;
+	return 1 << (vm->va_bits - shift);
+}
+
+static uint64_t ptrs_per_pte(struct kvm_vm *vm)
+{
+	return 1 << (vm->page_shift - 3);
+}
+
+void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot)
+{
+	int rc;
+
+	if (!vm->pgd_created) {
+		vm_paddr_t paddr = vm_phy_pages_alloc(vm,
+			page_align(vm, ptrs_per_pgd(vm) * 8) / vm->page_size,
+			KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
+		vm->pgd = paddr;
+		vm->pgd_created = true;
+	}
+}
+
+void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+		  uint32_t pgd_memslot, uint64_t flags)
+{
+	uint8_t attr_idx = flags & 7;
+	uint64_t *ptep;
+
+	TEST_ASSERT((vaddr % vm->page_size) == 0,
+		"Virtual address not on page boundary,\n"
+		"  vaddr: 0x%lx vm->page_size: 0x%x", vaddr, vm->page_size);
+	TEST_ASSERT(sparsebit_is_set(vm->vpages_valid,
+		(vaddr >> vm->page_shift)),
+		"Invalid virtual address, vaddr: 0x%lx", vaddr);
+	TEST_ASSERT((paddr % vm->page_size) == 0,
+		"Physical address not on page boundary,\n"
+		"  paddr: 0x%lx vm->page_size: 0x%x", paddr, vm->page_size);
+	TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn,
+		"Physical address beyond beyond maximum supported,\n"
+		"  paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
+		paddr, vm->max_gfn, vm->page_size);
+
+	ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, vaddr) * 8;
+	if (!*ptep) {
+		*ptep = vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
+		*ptep |= 3;
+	}
+
+	switch (vm->pgtable_levels) {
+	case 4:
+		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, vaddr) * 8;
+		if (!*ptep) {
+			*ptep = vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
+			*ptep |= 3;
+		}
+		/* fall through */
+	case 3:
+		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, vaddr) * 8;
+		if (!*ptep) {
+			*ptep = vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
+			*ptep |= 3;
+		}
+		/* fall through */
+	case 2:
+		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, vaddr) * 8;
+		break;
+	default:
+		TEST_ASSERT(false, "Page table levels must be 2, 3, or 4");
+	}
+
+	*ptep = paddr | 3;
+	*ptep |= (attr_idx << 2) | (1 << 10) /* Access Flag */;
+}
+
+void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+		 uint32_t pgd_memslot)
+{
+	uint64_t attr_idx = 4; /* NORMAL (See DEFAULT_MAIR_EL1) */
+
+	_virt_pg_map(vm, vaddr, paddr, pgd_memslot, attr_idx);
+}
+
+vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+	uint64_t *ptep;
+
+	if (!vm->pgd_created)
+		goto unmapped_gva;
+
+	ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, gva) * 8;
+	if (!ptep)
+		goto unmapped_gva;
+
+	switch (vm->pgtable_levels) {
+	case 4:
+		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, gva) * 8;
+		if (!ptep)
+			goto unmapped_gva;
+		/* fall through */
+	case 3:
+		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, gva) * 8;
+		if (!ptep)
+			goto unmapped_gva;
+		/* fall through */
+	case 2:
+		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, gva) * 8;
+		if (!ptep)
+			goto unmapped_gva;
+		break;
+	default:
+		TEST_ASSERT(false, "Page table levels must be 2, 3, or 4");
+	}
+
+	return pte_addr(vm, *ptep) + (gva & (vm->page_size - 1));
+
+unmapped_gva:
+	TEST_ASSERT(false, "No mapping for vm virtual address, "
+		    "gva: 0x%lx", gva);
+}
+
+static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, uint64_t page, int level)
+{
+#ifdef DEBUG_VM
+	static const char * const type[] = { "", "pud", "pmd", "pte" };
+	uint64_t pte, *ptep;
+
+	if (level == 4)
+		return;
+
+	for (pte = page; pte < page + ptrs_per_pte(vm) * 8; pte += 8) {
+		ptep = addr_gpa2hva(vm, pte);
+		if (!*ptep)
+			continue;
+		printf("%*s%s: %lx: %lx at %p\n", indent, "", type[level], pte, *ptep, ptep);
+		pte_dump(stream, vm, indent + 1, pte_addr(vm, *ptep), level + 1);
+	}
+#endif
+}
+
+void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
+{
+	int level = 4 - (vm->pgtable_levels - 1);
+	uint64_t pgd, *ptep;
+
+	if (!vm->pgd_created)
+		return;
+
+	for (pgd = vm->pgd; pgd < vm->pgd + ptrs_per_pgd(vm) * 8; pgd += 8) {
+		ptep = addr_gpa2hva(vm, pgd);
+		if (!*ptep)
+			continue;
+		printf("%*spgd: %lx: %lx at %p\n", indent, "", pgd, *ptep, ptep);
+		pte_dump(stream, vm, indent + 1, pte_addr(vm, *ptep), level);
+	}
+}
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 26c3c4350a88..fd346fb82e46 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -129,6 +129,7 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	/* Setup mode specific traits. */
 	switch (vm->mode) {
 	case VM_MODE_FLAT48PG:
+		vm->pgtable_levels = 4;
 		vm->page_size = 0x1000;
 		vm->page_shift = 12;
 		vm->va_bits = 48;
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index 3702c560bbf2..d048d7363d66 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -46,6 +46,7 @@ struct kvm_vm {
 	int mode;
 	int kvm_fd;
 	int fd;
+	unsigned int pgtable_levels;
 	unsigned int page_size;
 	unsigned int page_shift;
 	unsigned int va_bits;
-- 
cgit 


From 0bec140fb6c106a70aac183e5fa99de0ef1d161a Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:31 +0200
Subject: kvm: selftests: add vcpu support for aarch64

This code adds VM and VCPU setup code for the VM_MODE_FLAT48PG mode.
The VM_MODE_FLAT48PG isn't yet fully supportable, as it defines the
guest physical address limit as 52-bits, and KVM currently only
supports guests with up to 40-bit physical addresses (see
KVM_PHYS_SHIFT). VM_MODE_FLAT48PG will work fine, though, as long as
no >= 40-bit physical addresses are used.

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../selftests/kvm/include/aarch64/processor.h      | 55 ++++++++++++++
 .../testing/selftests/kvm/lib/aarch64/processor.c  | 83 ++++++++++++++++++++++
 2 files changed, 138 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/include/aarch64/processor.h

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
new file mode 100644
index 000000000000..9ef2ab1a0c08
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AArch64 processor specific defines
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+#ifndef SELFTEST_KVM_PROCESSOR_H
+#define SELFTEST_KVM_PROCESSOR_H
+
+#include "kvm_util.h"
+
+
+#define ARM64_CORE_REG(x) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
+			   KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(x))
+
+#define CPACR_EL1	3, 0,  1, 0, 2
+#define TCR_EL1		3, 0,  2, 0, 2
+#define MAIR_EL1	3, 0, 10, 2, 0
+#define TTBR0_EL1	3, 0,  2, 0, 0
+#define SCTLR_EL1	3, 0,  1, 0, 0
+
+/*
+ * Default MAIR
+ *                  index   attribute
+ * DEVICE_nGnRnE      0     0000:0000
+ * DEVICE_nGnRE       1     0000:0100
+ * DEVICE_GRE         2     0000:1100
+ * NORMAL_NC          3     0100:0100
+ * NORMAL             4     1111:1111
+ * NORMAL_WT          5     1011:1011
+ */
+#define DEFAULT_MAIR_EL1 ((0x00ul << (0 * 8)) | \
+			  (0x04ul << (1 * 8)) | \
+			  (0x0cul << (2 * 8)) | \
+			  (0x44ul << (3 * 8)) | \
+			  (0xfful << (4 * 8)) | \
+			  (0xbbul << (5 * 8)))
+
+static inline void get_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, uint64_t *addr)
+{
+	struct kvm_one_reg reg;
+	reg.id = id;
+	reg.addr = (uint64_t)addr;
+	vcpu_ioctl(vm, vcpuid, KVM_GET_ONE_REG, &reg);
+}
+
+static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, uint64_t val)
+{
+	struct kvm_one_reg reg;
+	reg.id = id;
+	reg.addr = (uint64_t)&val;
+	vcpu_ioctl(vm, vcpuid, KVM_SET_ONE_REG, &reg);
+}
+
+#endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 464d4d074249..871fe2173679 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -5,10 +5,14 @@
  * Copyright (C) 2018, Red Hat, Inc.
  */
 
+#define _GNU_SOURCE /* for program_invocation_name */
+
 #include "kvm_util.h"
 #include "../kvm_util_internal.h"
+#include "processor.h"
 
 #define KVM_GUEST_PAGE_TABLE_MIN_PADDR		0x180000
+#define DEFAULT_ARM64_GUEST_STACK_VADDR_MIN	0xac0000
 
 static uint64_t page_align(struct kvm_vm *vm, uint64_t v)
 {
@@ -214,3 +218,82 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 		pte_dump(stream, vm, indent + 1, pte_addr(vm, *ptep), level);
 	}
 }
+
+struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
+				 void *guest_code)
+{
+	uint64_t ptrs_per_4k_pte = 512;
+	uint64_t extra_pg_pages = (extra_mem_pages / ptrs_per_4k_pte) * 2;
+	struct kvm_vm *vm;
+
+	vm = vm_create(VM_MODE_FLAT48PG, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
+
+	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+	vm_vcpu_add_default(vm, vcpuid, guest_code);
+
+	return vm;
+}
+
+void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
+{
+	size_t stack_size = vm->page_size == 4096 ?
+					DEFAULT_STACK_PGS * vm->page_size :
+					vm->page_size;
+	uint64_t stack_vaddr = vm_vaddr_alloc(vm, stack_size,
+					DEFAULT_ARM64_GUEST_STACK_VADDR_MIN, 0, 0);
+
+	vm_vcpu_add(vm, vcpuid, 0, 0);
+
+	set_reg(vm, vcpuid, ARM64_CORE_REG(sp_el1), stack_vaddr + stack_size);
+	set_reg(vm, vcpuid, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code);
+}
+
+void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot)
+{
+	struct kvm_vcpu_init init;
+	uint64_t sctlr_el1, tcr_el1;
+
+	memset(&init, 0, sizeof(init));
+	init.target = KVM_ARM_TARGET_GENERIC_V8;
+	vcpu_ioctl(vm, vcpuid, KVM_ARM_VCPU_INIT, &init);
+
+	/*
+	 * Enable FP/ASIMD to avoid trapping when accessing Q0-Q15
+	 * registers, which the variable argument list macros do.
+	 */
+	set_reg(vm, vcpuid, ARM64_SYS_REG(CPACR_EL1), 3 << 20);
+
+	get_reg(vm, vcpuid, ARM64_SYS_REG(SCTLR_EL1), &sctlr_el1);
+	get_reg(vm, vcpuid, ARM64_SYS_REG(TCR_EL1), &tcr_el1);
+
+	switch (vm->mode) {
+	case VM_MODE_FLAT48PG:
+		tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
+		tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
+		break;
+	default:
+		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", vm->mode);
+	}
+
+	sctlr_el1 |= (1 << 0) | (1 << 2) | (1 << 12) /* M | C | I */;
+	/* TCR_EL1 |= IRGN0:WBWA | ORGN0:WBWA | SH0:Inner-Shareable */;
+	tcr_el1 |= (1 << 8) | (1 << 10) | (3 << 12);
+	tcr_el1 |= (64 - vm->va_bits) /* T0SZ */;
+
+	set_reg(vm, vcpuid, ARM64_SYS_REG(SCTLR_EL1), sctlr_el1);
+	set_reg(vm, vcpuid, ARM64_SYS_REG(TCR_EL1), tcr_el1);
+	set_reg(vm, vcpuid, ARM64_SYS_REG(MAIR_EL1), DEFAULT_MAIR_EL1);
+	set_reg(vm, vcpuid, ARM64_SYS_REG(TTBR0_EL1), vm->pgd);
+}
+
+void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
+{
+	uint64_t pstate, pc;
+
+	get_reg(vm, vcpuid, ARM64_CORE_REG(regs.pstate), &pstate);
+	get_reg(vm, vcpuid, ARM64_CORE_REG(regs.pc), &pc);
+
+        fprintf(stream, "%*spstate: 0x%.16llx pc: 0x%.16llx\n",
+                indent, "", pstate, pc);
+
+}
-- 
cgit 


From 81d1cca0c062a589953eef7e98f1e68b8222a918 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:33 +0200
Subject: kvm: selftests: introduce new VM mode for 64K pages

Rename VM_MODE_FLAT48PG to be more descriptive of its config and add a
new config that has the same parameters, except with 64K pages.

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/kvm_util.h     |  7 +++-
 .../testing/selftests/kvm/lib/aarch64/processor.c  |  8 +++-
 tools/testing/selftests/kvm/lib/kvm_util.c         | 46 ++++++++++++++--------
 .../testing/selftests/kvm/lib/kvm_util_internal.h  |  1 +
 tools/testing/selftests/kvm/lib/x86_64/processor.c | 10 ++---
 5 files changed, 47 insertions(+), 25 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index e0c9cf4d1c49..88df26c41845 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -34,9 +34,14 @@ typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
 #define DEFAULT_STACK_PGS		5
 
 enum vm_guest_mode {
-	VM_MODE_FLAT48PG,
+	VM_MODE_P52V48_4K,
+	VM_MODE_P52V48_64K,
+	NUM_VM_MODES,
 };
 
+#define vm_guest_mode_string(m) vm_guest_mode_string[m]
+extern const char * const vm_guest_mode_string[];
+
 enum vm_mem_backing_src_type {
 	VM_MEM_SRC_ANONYMOUS,
 	VM_MEM_SRC_ANONYMOUS_THP,
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 871fe2173679..b1dfc0d4b68e 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -226,7 +226,7 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
 	uint64_t extra_pg_pages = (extra_mem_pages / ptrs_per_4k_pte) * 2;
 	struct kvm_vm *vm;
 
-	vm = vm_create(VM_MODE_FLAT48PG, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
+	vm = vm_create(VM_MODE_P52V48_4K, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
 
 	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
 	vm_vcpu_add_default(vm, vcpuid, guest_code);
@@ -267,10 +267,14 @@ void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot)
 	get_reg(vm, vcpuid, ARM64_SYS_REG(TCR_EL1), &tcr_el1);
 
 	switch (vm->mode) {
-	case VM_MODE_FLAT48PG:
+	case VM_MODE_P52V48_4K:
 		tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
 		tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
 		break;
+	case VM_MODE_P52V48_64K:
+		tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
+		tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
+		break;
 	default:
 		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", vm->mode);
 	}
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index fd346fb82e46..b37e52f4daad 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -17,7 +17,7 @@
 #include <linux/kernel.h>
 
 #define KVM_UTIL_PGS_PER_HUGEPG 512
-#define KVM_UTIL_MIN_PADDR      0x2000
+#define KVM_UTIL_MIN_PFN	2
 
 /* Aligns x up to the next multiple of size. Size must be a power of 2. */
 static void *align(void *x, size_t size)
@@ -96,11 +96,16 @@ static void vm_open(struct kvm_vm *vm, int perm)
 		"rc: %i errno: %i", vm->fd, errno);
 }
 
+const char * const vm_guest_mode_string[] = {
+	"PA-bits:52, VA-bits:48, 4K pages",
+	"PA-bits:52, VA-bits:48, 64K pages",
+};
+
 /*
  * VM Create
  *
  * Input Args:
- *   mode - VM Mode (e.g. VM_MODE_FLAT48PG)
+ *   mode - VM Mode (e.g. VM_MODE_P52V48_4K)
  *   phy_pages - Physical memory pages
  *   perm - permission
  *
@@ -109,7 +114,7 @@ static void vm_open(struct kvm_vm *vm, int perm)
  * Return:
  *   Pointer to opaque structure that describes the created VM.
  *
- * Creates a VM with the mode specified by mode (e.g. VM_MODE_FLAT48PG).
+ * Creates a VM with the mode specified by mode (e.g. VM_MODE_P52V48_4K).
  * When phy_pages is non-zero, a memory region of phy_pages physical pages
  * is created and mapped starting at guest physical address 0.  The file
  * descriptor to control the created VM is created with the permissions
@@ -128,28 +133,34 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 
 	/* Setup mode specific traits. */
 	switch (vm->mode) {
-	case VM_MODE_FLAT48PG:
+	case VM_MODE_P52V48_4K:
 		vm->pgtable_levels = 4;
 		vm->page_size = 0x1000;
 		vm->page_shift = 12;
 		vm->va_bits = 48;
-
-		/* Limit to 48-bit canonical virtual addresses. */
-		vm->vpages_valid = sparsebit_alloc();
-		sparsebit_set_num(vm->vpages_valid,
-			0, (1ULL << (48 - 1)) >> vm->page_shift);
-		sparsebit_set_num(vm->vpages_valid,
-			(~((1ULL << (48 - 1)) - 1)) >> vm->page_shift,
-			(1ULL << (48 - 1)) >> vm->page_shift);
-
-		/* Limit physical addresses to 52-bits. */
-		vm->max_gfn = ((1ULL << 52) >> vm->page_shift) - 1;
 		break;
-
+	case VM_MODE_P52V48_64K:
+		vm->pgtable_levels = 3;
+		vm->pa_bits = 52;
+		vm->page_size = 0x10000;
+		vm->page_shift = 16;
+		vm->va_bits = 48;
+		break;
 	default:
 		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", mode);
 	}
 
+	/* Limit to VA-bit canonical virtual addresses. */
+	vm->vpages_valid = sparsebit_alloc();
+	sparsebit_set_num(vm->vpages_valid,
+		0, (1ULL << (vm->va_bits - 1)) >> vm->page_shift);
+	sparsebit_set_num(vm->vpages_valid,
+		(~((1ULL << (vm->va_bits - 1)) - 1)) >> vm->page_shift,
+		(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;
+
 	/* Allocate and setup memory for guest. */
 	vm->vpages_mapped = sparsebit_alloc();
 	if (phy_pages != 0)
@@ -868,7 +879,8 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
 		pages--, vaddr += vm->page_size) {
 		vm_paddr_t paddr;
 
-		paddr = vm_phy_page_alloc(vm, KVM_UTIL_MIN_PADDR, data_memslot);
+		paddr = vm_phy_page_alloc(vm,
+				KVM_UTIL_MIN_PFN * vm->page_size, data_memslot);
 
 		virt_pg_map(vm, vaddr, paddr, pgd_memslot);
 
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index d048d7363d66..52701db0f253 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -49,6 +49,7 @@ struct kvm_vm {
 	unsigned int pgtable_levels;
 	unsigned int page_size;
 	unsigned int page_shift;
+	unsigned int pa_bits;
 	unsigned int va_bits;
 	uint64_t max_gfn;
 	struct vcpu *vcpu_head;
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 67f84fbb0ca4..f28127f4a3af 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -231,7 +231,7 @@ void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot)
 {
 	int rc;
 
-	TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
+	TEST_ASSERT(vm->mode == VM_MODE_P52V48_4K, "Attempt to use "
 		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
 
 	/* If needed, create page map l4 table. */
@@ -264,7 +264,7 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 	uint16_t index[4];
 	struct pageMapL4Entry *pml4e;
 
-	TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
+	TEST_ASSERT(vm->mode == VM_MODE_P52V48_4K, "Attempt to use "
 		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
 
 	TEST_ASSERT((vaddr % vm->page_size) == 0,
@@ -551,7 +551,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 	struct pageTableEntry *pte;
 	void *hva;
 
-	TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
+	TEST_ASSERT(vm->mode == VM_MODE_P52V48_4K, "Attempt to use "
 		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
 
 	index[0] = (gva >> 12) & 0x1ffu;
@@ -624,7 +624,7 @@ void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot)
 	kvm_setup_gdt(vm, &sregs.gdt, gdt_memslot, pgd_memslot);
 
 	switch (vm->mode) {
-	case VM_MODE_FLAT48PG:
+	case VM_MODE_P52V48_4K:
 		sregs.cr0 = X86_CR0_PE | X86_CR0_NE | X86_CR0_PG;
 		sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR;
 		sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
@@ -823,7 +823,7 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
 	uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
 
 	/* Create VM */
-	vm = vm_create(VM_MODE_FLAT48PG,
+	vm = vm_create(VM_MODE_P52V48_4K,
 		       DEFAULT_GUEST_PHY_PAGES + extra_pg_pages,
 		       O_RDWR);
 
-- 
cgit 


From fff8dcd7b4a242e3752d6f316967b02f933031d0 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:32 +0200
Subject: kvm: selftests: port dirty_log_test to aarch64

While we're messing with the code for the port and to support guest
page sizes that are less than the host page size, we also make some
code formatting cleanups and apply sync_global_to_guest().

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/.gitignore             |   2 +-
 tools/testing/selftests/kvm/Makefile               |   5 +-
 tools/testing/selftests/kvm/dirty_log_test.c       | 315 +++++++++++++++++++++
 .../testing/selftests/kvm/x86_64/dirty_log_test.c  | 308 --------------------
 4 files changed, 320 insertions(+), 310 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/dirty_log_test.c
 delete mode 100644 tools/testing/selftests/kvm/x86_64/dirty_log_test.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index e0aa5411cf9b..552b0d9a49f4 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -4,4 +4,4 @@
 /x86_64/sync_regs_test
 /x86_64/vmx_tsc_adjust_test
 /x86_64/state_test
-/x86_64/dirty_log_test
+/dirty_log_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 959be146f789..5e23f97ec46f 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -5,6 +5,7 @@ UNAME_M := $(shell uname -m)
 
 LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/ucall.c lib/sparsebit.c
 LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c
+LIBKVM_aarch64 = lib/aarch64/processor.c
 
 TEST_GEN_PROGS_x86_64 = x86_64/platform_info_test
 TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
@@ -12,7 +13,9 @@ TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
 TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
 TEST_GEN_PROGS_x86_64 += x86_64/state_test
-TEST_GEN_PROGS_x86_64 += x86_64/dirty_log_test
+TEST_GEN_PROGS_x86_64 += dirty_log_test
+
+TEST_GEN_PROGS_aarch64 += dirty_log_test
 
 TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
 LIBKVM += $(LIBKVM_$(UNAME_M))
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
new file mode 100644
index 000000000000..d90f1091f687
--- /dev/null
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -0,0 +1,315 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM dirty page logging test
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <time.h>
+#include <pthread.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#define DEBUG printf
+
+#define VCPU_ID				1
+
+/* The memory slot index to track dirty pages */
+#define TEST_MEM_SLOT_INDEX		1
+
+/*
+ * GPA offset of the testing memory slot. Must be bigger than the
+ * default vm mem slot, which is DEFAULT_GUEST_PHY_PAGES.
+ */
+#define TEST_MEM_OFFSET			(1ul << 30) /* 1G */
+
+/* Size of the testing memory slot */
+#define TEST_MEM_PAGES			(1ul << 18) /* 1G for 4K pages */
+
+/* How many pages to dirty for each guest loop */
+#define TEST_PAGES_PER_LOOP		1024
+
+/* How many host loops to run (one KVM_GET_DIRTY_LOG for each loop) */
+#define TEST_HOST_LOOP_N		32
+
+/* Interval for each host loop (ms) */
+#define TEST_HOST_LOOP_INTERVAL		10
+
+/*
+ * Guest/Host shared variables. Ensure addr_gva2hva() and/or
+ * sync_global_to/from_guest() are used when accessing from
+ * the host. READ/WRITE_ONCE() should also be used with anything
+ * that may change.
+ */
+static uint64_t host_page_size;
+static uint64_t guest_page_size;
+static uint64_t random_array[TEST_PAGES_PER_LOOP];
+static uint64_t iteration;
+
+/*
+ * Continuously write to the first 8 bytes of a random pages within
+ * the testing memory region.
+ */
+static void guest_code(void)
+{
+	int i;
+
+	while (true) {
+		for (i = 0; i < TEST_PAGES_PER_LOOP; i++) {
+			uint64_t addr = TEST_MEM_OFFSET;
+			addr += (READ_ONCE(random_array[i]) % TEST_MEM_PAGES)
+				* guest_page_size;
+			addr &= ~(host_page_size - 1);
+			*(uint64_t *)addr = READ_ONCE(iteration);
+		}
+
+		/* Tell the host that we need more random numbers */
+		GUEST_SYNC(1);
+	}
+}
+
+/* Host variables */
+static bool host_quit;
+
+/* Points to the test VM memory region on which we track dirty logs */
+static void *host_test_mem;
+static uint64_t host_num_pages;
+
+/* For statistics only */
+static uint64_t host_dirty_count;
+static uint64_t host_clear_count;
+static uint64_t host_track_next_count;
+
+/*
+ * We use this bitmap to track some pages that should have its dirty
+ * bit set in the _next_ iteration.  For example, if we detected the
+ * page value changed to current iteration but at the same time the
+ * page bit is cleared in the latest bitmap, then the system must
+ * report that write in the next get dirty log call.
+ */
+static unsigned long *host_bmap_track;
+
+static void generate_random_array(uint64_t *guest_array, uint64_t size)
+{
+	uint64_t i;
+
+	for (i = 0; i < size; i++)
+		guest_array[i] = random();
+}
+
+static void *vcpu_worker(void *data)
+{
+	int ret;
+	struct kvm_vm *vm = data;
+	uint64_t *guest_array;
+	uint64_t pages_count = 0;
+	struct kvm_run *run;
+	struct ucall uc;
+
+	run = vcpu_state(vm, VCPU_ID);
+
+	guest_array = addr_gva2hva(vm, (vm_vaddr_t)random_array);
+	generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
+
+	while (!READ_ONCE(host_quit)) {
+		/* Let the guest dirty the random pages */
+		ret = _vcpu_run(vm, VCPU_ID);
+		if (get_ucall(vm, VCPU_ID, &uc) == UCALL_SYNC) {
+			pages_count += TEST_PAGES_PER_LOOP;
+			generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
+		} else {
+			TEST_ASSERT(false,
+				    "Invalid guest sync status: "
+				    "exit_reason=%s\n",
+				    exit_reason_str(run->exit_reason));
+		}
+	}
+
+	DEBUG("Dirtied %"PRIu64" pages\n", pages_count);
+
+	return NULL;
+}
+
+static void vm_dirty_log_verify(unsigned long *bmap)
+{
+	uint64_t page;
+	uint64_t *value_ptr;
+
+	for (page = 0; page < host_num_pages; page++) {
+		value_ptr = host_test_mem + page * host_page_size;
+
+		/* If this is a special page that we were tracking... */
+		if (test_and_clear_bit(page, host_bmap_track)) {
+			host_track_next_count++;
+			TEST_ASSERT(test_bit(page, bmap),
+				    "Page %"PRIu64" should have its dirty bit "
+				    "set in this iteration but it is missing",
+				    page);
+		}
+
+		if (test_bit(page, bmap)) {
+			host_dirty_count++;
+			/*
+			 * If the bit is set, the value written onto
+			 * the corresponding page should be either the
+			 * previous iteration number or the current one.
+			 */
+			TEST_ASSERT(*value_ptr == iteration ||
+				    *value_ptr == iteration - 1,
+				    "Set page %"PRIu64" value %"PRIu64
+				    " incorrect (iteration=%"PRIu64")",
+				    page, *value_ptr, iteration);
+		} else {
+			host_clear_count++;
+			/*
+			 * If cleared, the value written can be any
+			 * value smaller or equals to the iteration
+			 * number.  Note that the value can be exactly
+			 * (iteration-1) if that write can happen
+			 * like this:
+			 *
+			 * (1) increase loop count to "iteration-1"
+			 * (2) write to page P happens (with value
+			 *     "iteration-1")
+			 * (3) get dirty log for "iteration-1"; we'll
+			 *     see that page P bit is set (dirtied),
+			 *     and not set the bit in host_bmap_track
+			 * (4) increase loop count to "iteration"
+			 *     (which is current iteration)
+			 * (5) get dirty log for current iteration,
+			 *     we'll see that page P is cleared, with
+			 *     value "iteration-1".
+			 */
+			TEST_ASSERT(*value_ptr <= iteration,
+				    "Clear page %"PRIu64" value %"PRIu64
+				    " incorrect (iteration=%"PRIu64")",
+				    page, *value_ptr, iteration);
+			if (*value_ptr == iteration) {
+				/*
+				 * This page is _just_ modified; it
+				 * should report its dirtyness in the
+				 * next run
+				 */
+				set_bit(page, host_bmap_track);
+			}
+		}
+	}
+}
+
+static void help(char *name)
+{
+	puts("");
+	printf("usage: %s [-i iterations] [-I interval] [-h]\n", name);
+	puts("");
+	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
+	       TEST_HOST_LOOP_N);
+	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
+	       TEST_HOST_LOOP_INTERVAL);
+	puts("");
+	exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+	pthread_t vcpu_thread;
+	struct kvm_vm *vm;
+	unsigned long iterations = TEST_HOST_LOOP_N;
+	unsigned long interval = TEST_HOST_LOOP_INTERVAL;
+	unsigned long *bmap;
+	int opt;
+
+	while ((opt = getopt(argc, argv, "hi:I:")) != -1) {
+		switch (opt) {
+		case 'i':
+			iterations = strtol(optarg, NULL, 10);
+			break;
+		case 'I':
+			interval = strtol(optarg, NULL, 10);
+			break;
+		case 'h':
+		default:
+			help(argv[0]);
+			break;
+		}
+	}
+
+	TEST_ASSERT(iterations > 2, "Iterations must be greater than two");
+	TEST_ASSERT(interval > 0, "Interval must be greater than zero");
+
+	DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
+	      iterations, interval);
+
+	srandom(time(0));
+
+	guest_page_size = 4096;
+	host_page_size = getpagesize();
+	host_num_pages = (TEST_MEM_PAGES * guest_page_size) / host_page_size +
+			 !!((TEST_MEM_PAGES * guest_page_size) % host_page_size);
+
+	bmap = bitmap_alloc(host_num_pages);
+	host_bmap_track = bitmap_alloc(host_num_pages);
+
+	vm = vm_create_default(VCPU_ID, TEST_MEM_PAGES, guest_code);
+
+	/* Add an extra memory slot for testing dirty logging */
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+				    TEST_MEM_OFFSET,
+				    TEST_MEM_SLOT_INDEX,
+				    TEST_MEM_PAGES,
+				    KVM_MEM_LOG_DIRTY_PAGES);
+
+	/* Do 1:1 mapping for the dirty track memory slot */
+	virt_map(vm, TEST_MEM_OFFSET, TEST_MEM_OFFSET,
+		 TEST_MEM_PAGES * guest_page_size, 0);
+
+	/* Cache the HVA pointer of the region */
+	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)TEST_MEM_OFFSET);
+
+#ifdef __x86_64__
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+#endif
+#ifdef __aarch64__
+	ucall_init(vm, UCALL_MMIO, NULL);
+#endif
+
+	/* Tell the guest about the page sizes */
+	sync_global_to_guest(vm, host_page_size);
+	sync_global_to_guest(vm, guest_page_size);
+
+	/* Start the iterations */
+	iteration = 1;
+	sync_global_to_guest(vm, iteration);
+
+	pthread_create(&vcpu_thread, NULL, vcpu_worker, vm);
+
+	while (iteration < iterations) {
+		/* Give the vcpu thread some time to dirty some pages */
+		usleep(interval * 1000);
+		kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
+		vm_dirty_log_verify(bmap);
+		iteration++;
+		sync_global_to_guest(vm, iteration);
+	}
+
+	/* Tell the vcpu thread to quit */
+	host_quit = true;
+	pthread_join(vcpu_thread, NULL);
+
+	DEBUG("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), "
+	      "track_next (%"PRIu64")\n", host_dirty_count, host_clear_count,
+	      host_track_next_count);
+
+	free(bmap);
+	free(host_bmap_track);
+	ucall_uninit(vm);
+	kvm_vm_free(vm);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/dirty_log_test.c
deleted file mode 100644
index 395a6e07d37c..000000000000
--- a/tools/testing/selftests/kvm/x86_64/dirty_log_test.c
+++ /dev/null
@@ -1,308 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * KVM dirty page logging test
- *
- * Copyright (C) 2018, Red Hat, Inc.
- */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <time.h>
-#include <pthread.h>
-#include <linux/bitmap.h>
-#include <linux/bitops.h>
-
-#include "test_util.h"
-#include "kvm_util.h"
-#include "processor.h"
-
-#define  DEBUG                 printf
-
-#define  VCPU_ID                        1
-/* The memory slot index to track dirty pages */
-#define  TEST_MEM_SLOT_INDEX            1
-/*
- * GPA offset of the testing memory slot. Must be bigger than the
- * default vm mem slot, which is DEFAULT_GUEST_PHY_PAGES.
- */
-#define  TEST_MEM_OFFSET                (1ULL << 30) /* 1G */
-/* Size of the testing memory slot */
-#define  TEST_MEM_PAGES                 (1ULL << 18) /* 1G for 4K pages */
-/* How many pages to dirty for each guest loop */
-#define  TEST_PAGES_PER_LOOP            1024
-/* How many host loops to run (one KVM_GET_DIRTY_LOG for each loop) */
-#define  TEST_HOST_LOOP_N               32
-/* Interval for each host loop (ms) */
-#define  TEST_HOST_LOOP_INTERVAL        10
-
-/*
- * Guest variables.  We use these variables to share data between host
- * and guest.  There are two copies of the variables, one in host memory
- * (which is unused) and one in guest memory.  When the host wants to
- * access these variables, it needs to call addr_gva2hva() to access the
- * guest copy.
- */
-uint64_t guest_random_array[TEST_PAGES_PER_LOOP];
-uint64_t guest_iteration;
-uint64_t guest_page_size;
-
-/*
- * Writes to the first byte of a random page within the testing memory
- * region continuously.
- */
-void guest_code(void)
-{
-	int i = 0;
-	uint64_t volatile *array = guest_random_array;
-	uint64_t volatile *guest_addr;
-
-	while (true) {
-		for (i = 0; i < TEST_PAGES_PER_LOOP; i++) {
-			/*
-			 * Write to the first 8 bytes of a random page
-			 * on the testing memory region.
-			 */
-			guest_addr = (uint64_t *)
-			    (TEST_MEM_OFFSET +
-			     (array[i] % TEST_MEM_PAGES) * guest_page_size);
-			*guest_addr = guest_iteration;
-		}
-		/* Tell the host that we need more random numbers */
-		GUEST_SYNC(1);
-	}
-}
-
-/*
- * Host variables.  These variables should only be used by the host
- * rather than the guest.
- */
-bool host_quit;
-
-/* Points to the test VM memory region on which we track dirty logs */
-void *host_test_mem;
-
-/* For statistics only */
-uint64_t host_dirty_count;
-uint64_t host_clear_count;
-uint64_t host_track_next_count;
-
-/*
- * We use this bitmap to track some pages that should have its dirty
- * bit set in the _next_ iteration.  For example, if we detected the
- * page value changed to current iteration but at the same time the
- * page bit is cleared in the latest bitmap, then the system must
- * report that write in the next get dirty log call.
- */
-unsigned long *host_bmap_track;
-
-void generate_random_array(uint64_t *guest_array, uint64_t size)
-{
-	uint64_t i;
-
-	for (i = 0; i < size; i++) {
-		guest_array[i] = random();
-	}
-}
-
-void *vcpu_worker(void *data)
-{
-	int ret;
-	uint64_t loops, *guest_array, pages_count = 0;
-	struct kvm_vm *vm = data;
-	struct kvm_run *run;
-	struct ucall uc;
-
-	run = vcpu_state(vm, VCPU_ID);
-
-	/* Retrieve the guest random array pointer and cache it */
-	guest_array = addr_gva2hva(vm, (vm_vaddr_t)guest_random_array);
-
-	DEBUG("VCPU starts\n");
-
-	generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
-
-	while (!READ_ONCE(host_quit)) {
-		/* Let the guest to dirty these random pages */
-		ret = _vcpu_run(vm, VCPU_ID);
-		if (run->exit_reason == KVM_EXIT_IO &&
-		    get_ucall(vm, VCPU_ID, &uc) == UCALL_SYNC) {
-			pages_count += TEST_PAGES_PER_LOOP;
-			generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
-		} else {
-			TEST_ASSERT(false,
-				    "Invalid guest sync status: "
-				    "exit_reason=%s\n",
-				    exit_reason_str(run->exit_reason));
-		}
-	}
-
-	DEBUG("VCPU exits, dirtied %"PRIu64" pages\n", pages_count);
-
-	return NULL;
-}
-
-void vm_dirty_log_verify(unsigned long *bmap, uint64_t iteration)
-{
-	uint64_t page;
-	uint64_t volatile *value_ptr;
-
-	for (page = 0; page < TEST_MEM_PAGES; page++) {
-		value_ptr = host_test_mem + page * getpagesize();
-
-		/* If this is a special page that we were tracking... */
-		if (test_and_clear_bit(page, host_bmap_track)) {
-			host_track_next_count++;
-			TEST_ASSERT(test_bit(page, bmap),
-				    "Page %"PRIu64" should have its dirty bit "
-				    "set in this iteration but it is missing",
-				    page);
-		}
-
-		if (test_bit(page, bmap)) {
-			host_dirty_count++;
-			/*
-			 * If the bit is set, the value written onto
-			 * the corresponding page should be either the
-			 * previous iteration number or the current one.
-			 */
-			TEST_ASSERT(*value_ptr == iteration ||
-				    *value_ptr == iteration - 1,
-				    "Set page %"PRIu64" value %"PRIu64
-				    " incorrect (iteration=%"PRIu64")",
-				    page, *value_ptr, iteration);
-		} else {
-			host_clear_count++;
-			/*
-			 * If cleared, the value written can be any
-			 * value smaller or equals to the iteration
-			 * number.  Note that the value can be exactly
-			 * (iteration-1) if that write can happen
-			 * like this:
-			 *
-			 * (1) increase loop count to "iteration-1"
-			 * (2) write to page P happens (with value
-			 *     "iteration-1")
-			 * (3) get dirty log for "iteration-1"; we'll
-			 *     see that page P bit is set (dirtied),
-			 *     and not set the bit in host_bmap_track
-			 * (4) increase loop count to "iteration"
-			 *     (which is current iteration)
-			 * (5) get dirty log for current iteration,
-			 *     we'll see that page P is cleared, with
-			 *     value "iteration-1".
-			 */
-			TEST_ASSERT(*value_ptr <= iteration,
-				    "Clear page %"PRIu64" value %"PRIu64
-				    " incorrect (iteration=%"PRIu64")",
-				    page, *value_ptr, iteration);
-			if (*value_ptr == iteration) {
-				/*
-				 * This page is _just_ modified; it
-				 * should report its dirtyness in the
-				 * next run
-				 */
-				set_bit(page, host_bmap_track);
-			}
-		}
-	}
-}
-
-void help(char *name)
-{
-	puts("");
-	printf("usage: %s [-i iterations] [-I interval] [-h]\n", name);
-	puts("");
-	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
-	       TEST_HOST_LOOP_N);
-	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
-	       TEST_HOST_LOOP_INTERVAL);
-	puts("");
-	exit(0);
-}
-
-int main(int argc, char *argv[])
-{
-	pthread_t vcpu_thread;
-	struct kvm_vm *vm;
-	uint64_t volatile *psize, *iteration;
-	unsigned long *bmap, iterations = TEST_HOST_LOOP_N,
-	    interval = TEST_HOST_LOOP_INTERVAL;
-	int opt;
-
-	while ((opt = getopt(argc, argv, "hi:I:")) != -1) {
-		switch (opt) {
-		case 'i':
-			iterations = strtol(optarg, NULL, 10);
-			break;
-		case 'I':
-			interval = strtol(optarg, NULL, 10);
-			break;
-		case 'h':
-		default:
-			help(argv[0]);
-			break;
-		}
-	}
-
-	TEST_ASSERT(iterations > 2, "Iteration must be bigger than zero\n");
-	TEST_ASSERT(interval > 0, "Interval must be bigger than zero");
-
-	DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
-	      iterations, interval);
-
-	srandom(time(0));
-
-	bmap = bitmap_alloc(TEST_MEM_PAGES);
-	host_bmap_track = bitmap_alloc(TEST_MEM_PAGES);
-
-	vm = vm_create_default(VCPU_ID, TEST_MEM_PAGES, guest_code);
-
-	/* Add an extra memory slot for testing dirty logging */
-	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
-				    TEST_MEM_OFFSET,
-				    TEST_MEM_SLOT_INDEX,
-				    TEST_MEM_PAGES,
-				    KVM_MEM_LOG_DIRTY_PAGES);
-	/* Cache the HVA pointer of the region */
-	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)TEST_MEM_OFFSET);
-
-	/* Do 1:1 mapping for the dirty track memory slot */
-	virt_map(vm, TEST_MEM_OFFSET, TEST_MEM_OFFSET,
-		 TEST_MEM_PAGES * getpagesize(), 0);
-
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
-
-	/* Tell the guest about the page size on the system */
-	psize = addr_gva2hva(vm, (vm_vaddr_t)&guest_page_size);
-	*psize = getpagesize();
-
-	/* Start the iterations */
-	iteration = addr_gva2hva(vm, (vm_vaddr_t)&guest_iteration);
-	*iteration = 1;
-
-	/* Start dirtying pages */
-	pthread_create(&vcpu_thread, NULL, vcpu_worker, vm);
-
-	while (*iteration < iterations) {
-		/* Give the vcpu thread some time to dirty some pages */
-		usleep(interval * 1000);
-		kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
-		vm_dirty_log_verify(bmap, *iteration);
-		(*iteration)++;
-	}
-
-	/* Tell the vcpu thread to quit */
-	host_quit = true;
-	pthread_join(vcpu_thread, NULL);
-
-	DEBUG("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), "
-	      "track_next (%"PRIu64")\n", host_dirty_count, host_clear_count,
-	      host_track_next_count);
-
-	free(bmap);
-	free(host_bmap_track);
-	kvm_vm_free(vm);
-
-	return 0;
-}
-- 
cgit 


From e1b376f140ad9cbb1e1976f347377b8ef08a5bc9 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:34 +0200
Subject: kvm: selftests: dirty_log_test: also test 64K pages on aarch64

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/dirty_log_test.c | 183 ++++++++++++++++++++-------
 1 file changed, 137 insertions(+), 46 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index d90f1091f687..3afc7d607a2e 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -5,6 +5,8 @@
  * Copyright (C) 2018, Red Hat, Inc.
  */
 
+#define _GNU_SOURCE /* for program_invocation_name */
+
 #include <stdio.h>
 #include <stdlib.h>
 #include <unistd.h>
@@ -30,9 +32,6 @@
  */
 #define TEST_MEM_OFFSET			(1ul << 30) /* 1G */
 
-/* Size of the testing memory slot */
-#define TEST_MEM_PAGES			(1ul << 18) /* 1G for 4K pages */
-
 /* How many pages to dirty for each guest loop */
 #define TEST_PAGES_PER_LOOP		1024
 
@@ -50,6 +49,7 @@
  */
 static uint64_t host_page_size;
 static uint64_t guest_page_size;
+static uint64_t guest_num_pages;
 static uint64_t random_array[TEST_PAGES_PER_LOOP];
 static uint64_t iteration;
 
@@ -64,7 +64,7 @@ static void guest_code(void)
 	while (true) {
 		for (i = 0; i < TEST_PAGES_PER_LOOP; i++) {
 			uint64_t addr = TEST_MEM_OFFSET;
-			addr += (READ_ONCE(random_array[i]) % TEST_MEM_PAGES)
+			addr += (READ_ONCE(random_array[i]) % guest_num_pages)
 				* guest_page_size;
 			addr &= ~(host_page_size - 1);
 			*(uint64_t *)addr = READ_ONCE(iteration);
@@ -141,8 +141,10 @@ static void vm_dirty_log_verify(unsigned long *bmap)
 {
 	uint64_t page;
 	uint64_t *value_ptr;
+	uint64_t step = host_page_size >= guest_page_size ? 1 :
+				guest_page_size / host_page_size;
 
-	for (page = 0; page < host_num_pages; page++) {
+	for (page = 0; page < host_num_pages; page += step) {
 		value_ptr = host_test_mem + page * host_page_size;
 
 		/* If this is a special page that we were tracking... */
@@ -203,71 +205,64 @@ static void vm_dirty_log_verify(unsigned long *bmap)
 	}
 }
 
-static void help(char *name)
+static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
+				uint64_t extra_mem_pages, void *guest_code)
 {
-	puts("");
-	printf("usage: %s [-i iterations] [-I interval] [-h]\n", name);
-	puts("");
-	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
-	       TEST_HOST_LOOP_N);
-	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
-	       TEST_HOST_LOOP_INTERVAL);
-	puts("");
-	exit(0);
+	struct kvm_vm *vm;
+	uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
+
+	vm = vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
+	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+#ifdef __x86_64__
+	vm_create_irqchip(vm);
+#endif
+	vm_vcpu_add_default(vm, vcpuid, guest_code);
+	return vm;
 }
 
-int main(int argc, char *argv[])
+static void run_test(enum vm_guest_mode mode, unsigned long iterations,
+		     unsigned long interval)
 {
+	unsigned int guest_page_shift;
 	pthread_t vcpu_thread;
 	struct kvm_vm *vm;
-	unsigned long iterations = TEST_HOST_LOOP_N;
-	unsigned long interval = TEST_HOST_LOOP_INTERVAL;
 	unsigned long *bmap;
-	int opt;
 
-	while ((opt = getopt(argc, argv, "hi:I:")) != -1) {
-		switch (opt) {
-		case 'i':
-			iterations = strtol(optarg, NULL, 10);
-			break;
-		case 'I':
-			interval = strtol(optarg, NULL, 10);
-			break;
-		case 'h':
-		default:
-			help(argv[0]);
-			break;
-		}
+	switch (mode) {
+	case VM_MODE_P52V48_4K:
+		guest_page_shift = 12;
+		break;
+	case VM_MODE_P52V48_64K:
+		guest_page_shift = 16;
+		break;
+	default:
+		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", mode);
 	}
 
-	TEST_ASSERT(iterations > 2, "Iterations must be greater than two");
-	TEST_ASSERT(interval > 0, "Interval must be greater than zero");
-
-	DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
-	      iterations, interval);
-
-	srandom(time(0));
+	DEBUG("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
-	guest_page_size = 4096;
+	guest_page_size = (1ul << guest_page_shift);
+	/* 1G of guest page sized pages */
+	guest_num_pages = (1ul << (30 - guest_page_shift));
 	host_page_size = getpagesize();
-	host_num_pages = (TEST_MEM_PAGES * guest_page_size) / host_page_size +
-			 !!((TEST_MEM_PAGES * guest_page_size) % host_page_size);
+	host_num_pages = (guest_num_pages * guest_page_size) / host_page_size +
+			 !!((guest_num_pages * guest_page_size) % host_page_size);
 
 	bmap = bitmap_alloc(host_num_pages);
 	host_bmap_track = bitmap_alloc(host_num_pages);
 
-	vm = vm_create_default(VCPU_ID, TEST_MEM_PAGES, guest_code);
+	vm = create_vm(mode, VCPU_ID, guest_num_pages, guest_code);
 
 	/* Add an extra memory slot for testing dirty logging */
 	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
 				    TEST_MEM_OFFSET,
 				    TEST_MEM_SLOT_INDEX,
-				    TEST_MEM_PAGES,
+				    guest_num_pages,
 				    KVM_MEM_LOG_DIRTY_PAGES);
 
 	/* Do 1:1 mapping for the dirty track memory slot */
 	virt_map(vm, TEST_MEM_OFFSET, TEST_MEM_OFFSET,
-		 TEST_MEM_PAGES * guest_page_size, 0);
+		 guest_num_pages * guest_page_size, 0);
 
 	/* Cache the HVA pointer of the region */
 	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)TEST_MEM_OFFSET);
@@ -279,13 +274,18 @@ int main(int argc, char *argv[])
 	ucall_init(vm, UCALL_MMIO, NULL);
 #endif
 
-	/* Tell the guest about the page sizes */
+	/* Export the shared variables to the guest */
 	sync_global_to_guest(vm, host_page_size);
 	sync_global_to_guest(vm, guest_page_size);
+	sync_global_to_guest(vm, guest_num_pages);
 
 	/* Start the iterations */
 	iteration = 1;
 	sync_global_to_guest(vm, iteration);
+	host_quit = false;
+	host_dirty_count = 0;
+	host_clear_count = 0;
+	host_track_next_count = 0;
 
 	pthread_create(&vcpu_thread, NULL, vcpu_worker, vm);
 
@@ -310,6 +310,97 @@ int main(int argc, char *argv[])
 	free(host_bmap_track);
 	ucall_uninit(vm);
 	kvm_vm_free(vm);
+}
+
+static struct vm_guest_modes {
+	enum vm_guest_mode mode;
+	bool supported;
+	bool enabled;
+} vm_guest_modes[NUM_VM_MODES] = {
+	{ VM_MODE_P52V48_4K,	1, 1, },
+#ifdef __aarch64__
+	{ VM_MODE_P52V48_64K,	1, 1, },
+#else
+	{ VM_MODE_P52V48_64K,	0, 0, },
+#endif
+};
+
+static void help(char *name)
+{
+	int i;
+
+	puts("");
+	printf("usage: %s [-h] [-i iterations] [-I interval] [-m mode]\n", name);
+	puts("");
+	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
+	       TEST_HOST_LOOP_N);
+	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
+	       TEST_HOST_LOOP_INTERVAL);
+	printf(" -m: specify the guest mode ID to test "
+	       "(default: test all supported modes)\n"
+	       "     This option may be used multiple times.\n"
+	       "     Guest mode IDs:\n");
+	for (i = 0; i < NUM_VM_MODES; ++i) {
+		printf("         %d:    %s%s\n",
+		       vm_guest_modes[i].mode,
+		       vm_guest_mode_string(vm_guest_modes[i].mode),
+		       vm_guest_modes[i].supported ? " (supported)" : "");
+	}
+	puts("");
+	exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+	unsigned long iterations = TEST_HOST_LOOP_N;
+	unsigned long interval = TEST_HOST_LOOP_INTERVAL;
+	bool mode_selected = false;
+	unsigned int mode;
+	int opt, i;
+
+	while ((opt = getopt(argc, argv, "hi:I:m:")) != -1) {
+		switch (opt) {
+		case 'i':
+			iterations = strtol(optarg, NULL, 10);
+			break;
+		case 'I':
+			interval = strtol(optarg, NULL, 10);
+			break;
+		case 'm':
+			if (!mode_selected) {
+				for (i = 0; i < NUM_VM_MODES; ++i)
+					vm_guest_modes[i].enabled = 0;
+				mode_selected = true;
+			}
+			mode = strtoul(optarg, NULL, 10);
+			TEST_ASSERT(mode < NUM_VM_MODES,
+				    "Guest mode ID %d too big", mode);
+			vm_guest_modes[mode].enabled = 1;
+			break;
+		case 'h':
+		default:
+			help(argv[0]);
+			break;
+		}
+	}
+
+	TEST_ASSERT(iterations > 2, "Iterations must be greater than two");
+	TEST_ASSERT(interval > 0, "Interval must be greater than zero");
+
+	DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
+	      iterations, interval);
+
+	srandom(time(0));
+
+	for (i = 0; i < NUM_VM_MODES; ++i) {
+		if (!vm_guest_modes[i].enabled)
+			continue;
+		TEST_ASSERT(vm_guest_modes[i].supported,
+			    "Guest mode ID %d (%s) not supported.",
+			    vm_guest_modes[i].mode,
+			    vm_guest_mode_string(vm_guest_modes[i].mode));
+		run_test(vm_guest_modes[i].mode, iterations, interval);
+	}
 
 	return 0;
 }
-- 
cgit 


From e28934e661c1d9425f1cc41b405dcd8626507206 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:35 +0200
Subject: kvm: selftests: stop lying to aarch64 tests about PA-bits

Let's add the 40 PA-bit versions of the VM modes, that AArch64
should have been using, so we can extend the dirty log test without
breaking things.

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/dirty_log_test.c        | 13 ++++++++++---
 tools/testing/selftests/kvm/include/kvm_util.h      |  2 ++
 tools/testing/selftests/kvm/lib/aarch64/processor.c |  8 ++++++++
 tools/testing/selftests/kvm/lib/kvm_util.c          | 16 ++++++++++++++++
 4 files changed, 36 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 3afc7d607a2e..61396882ad4e 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -230,9 +230,11 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 
 	switch (mode) {
 	case VM_MODE_P52V48_4K:
+	case VM_MODE_P40V48_4K:
 		guest_page_shift = 12;
 		break;
 	case VM_MODE_P52V48_64K:
+	case VM_MODE_P40V48_64K:
 		guest_page_shift = 16;
 		break;
 	default:
@@ -317,11 +319,16 @@ static struct vm_guest_modes {
 	bool supported;
 	bool enabled;
 } vm_guest_modes[NUM_VM_MODES] = {
+#if defined(__x86_64__)
 	{ VM_MODE_P52V48_4K,	1, 1, },
-#ifdef __aarch64__
-	{ VM_MODE_P52V48_64K,	1, 1, },
-#else
 	{ VM_MODE_P52V48_64K,	0, 0, },
+	{ VM_MODE_P40V48_4K,	0, 0, },
+	{ VM_MODE_P40V48_64K,	0, 0, },
+#elif defined(__aarch64__)
+	{ VM_MODE_P52V48_4K,	0, 0, },
+	{ VM_MODE_P52V48_64K,	0, 0, },
+	{ VM_MODE_P40V48_4K,	1, 1, },
+	{ VM_MODE_P40V48_64K,	1, 1, },
 #endif
 };
 
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 88df26c41845..a4e59e3b4826 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -36,6 +36,8 @@ typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
 enum vm_guest_mode {
 	VM_MODE_P52V48_4K,
 	VM_MODE_P52V48_64K,
+	VM_MODE_P40V48_4K,
+	VM_MODE_P40V48_64K,
 	NUM_VM_MODES,
 };
 
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index b1dfc0d4b68e..b6022e2f116e 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -275,6 +275,14 @@ void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot)
 		tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
 		tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
 		break;
+	case VM_MODE_P40V48_4K:
+		tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
+		tcr_el1 |= 2ul << 32; /* IPS = 40 bits */
+		break;
+	case VM_MODE_P40V48_64K:
+		tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
+		tcr_el1 |= 2ul << 32; /* IPS = 40 bits */
+		break;
 	default:
 		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", vm->mode);
 	}
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index b37e52f4daad..8c06da4f03db 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -99,6 +99,8 @@ static void vm_open(struct kvm_vm *vm, int perm)
 const char * const vm_guest_mode_string[] = {
 	"PA-bits:52, VA-bits:48, 4K pages",
 	"PA-bits:52, VA-bits:48, 64K pages",
+	"PA-bits:40, VA-bits:48, 4K pages",
+	"PA-bits:40, VA-bits:48, 64K pages",
 };
 
 /*
@@ -146,6 +148,20 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 		vm->page_shift = 16;
 		vm->va_bits = 48;
 		break;
+	case VM_MODE_P40V48_4K:
+		vm->pgtable_levels = 4;
+		vm->pa_bits = 40;
+		vm->va_bits = 48;
+		vm->page_size = 0x1000;
+		vm->page_shift = 12;
+		break;
+	case VM_MODE_P40V48_64K:
+		vm->pgtable_levels = 3;
+		vm->pa_bits = 40;
+		vm->va_bits = 48;
+		vm->page_size = 0x10000;
+		vm->page_shift = 16;
+		break;
 	default:
 		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", mode);
 	}
-- 
cgit 


From 5b8ee8792f6bda46978e6e86fda4650bcbae07ab Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:36 +0200
Subject: kvm: selftests: support high GPAs in dirty_log_test

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/dirty_log_test.c | 65 +++++++++++++++++++++-------
 1 file changed, 50 insertions(+), 15 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 61396882ad4e..d59820cc2d39 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -26,11 +26,8 @@
 /* The memory slot index to track dirty pages */
 #define TEST_MEM_SLOT_INDEX		1
 
-/*
- * GPA offset of the testing memory slot. Must be bigger than the
- * default vm mem slot, which is DEFAULT_GUEST_PHY_PAGES.
- */
-#define TEST_MEM_OFFSET			(1ul << 30) /* 1G */
+/* Default guest test memory offset, 1G */
+#define DEFAULT_GUEST_TEST_MEM		0x40000000
 
 /* How many pages to dirty for each guest loop */
 #define TEST_PAGES_PER_LOOP		1024
@@ -53,6 +50,12 @@ static uint64_t guest_num_pages;
 static uint64_t random_array[TEST_PAGES_PER_LOOP];
 static uint64_t iteration;
 
+/*
+ * GPA offset of the testing memory slot. Must be bigger than
+ * DEFAULT_GUEST_PHY_PAGES.
+ */
+static uint64_t guest_test_mem = DEFAULT_GUEST_TEST_MEM;
+
 /*
  * Continuously write to the first 8 bytes of a random pages within
  * the testing memory region.
@@ -63,7 +66,7 @@ static void guest_code(void)
 
 	while (true) {
 		for (i = 0; i < TEST_PAGES_PER_LOOP; i++) {
-			uint64_t addr = TEST_MEM_OFFSET;
+			uint64_t addr = guest_test_mem;
 			addr += (READ_ONCE(random_array[i]) % guest_num_pages)
 				* guest_page_size;
 			addr &= ~(host_page_size - 1);
@@ -221,20 +224,29 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
 }
 
 static void run_test(enum vm_guest_mode mode, unsigned long iterations,
-		     unsigned long interval)
+		     unsigned long interval, bool top_offset)
 {
-	unsigned int guest_page_shift;
+	unsigned int guest_pa_bits, guest_page_shift;
 	pthread_t vcpu_thread;
 	struct kvm_vm *vm;
+	uint64_t max_gfn;
 	unsigned long *bmap;
 
 	switch (mode) {
 	case VM_MODE_P52V48_4K:
-	case VM_MODE_P40V48_4K:
+		guest_pa_bits = 52;
 		guest_page_shift = 12;
 		break;
 	case VM_MODE_P52V48_64K:
+		guest_pa_bits = 52;
+		guest_page_shift = 16;
+		break;
+	case VM_MODE_P40V48_4K:
+		guest_pa_bits = 40;
+		guest_page_shift = 12;
+		break;
 	case VM_MODE_P40V48_64K:
+		guest_pa_bits = 40;
 		guest_page_shift = 16;
 		break;
 	default:
@@ -243,6 +255,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 
 	DEBUG("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
+	max_gfn = (1ul << (guest_pa_bits - guest_page_shift)) - 1;
 	guest_page_size = (1ul << guest_page_shift);
 	/* 1G of guest page sized pages */
 	guest_num_pages = (1ul << (30 - guest_page_shift));
@@ -250,6 +263,13 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	host_num_pages = (guest_num_pages * guest_page_size) / host_page_size +
 			 !!((guest_num_pages * guest_page_size) % host_page_size);
 
+	if (top_offset) {
+		guest_test_mem = (max_gfn - guest_num_pages) * guest_page_size;
+		guest_test_mem &= ~(host_page_size - 1);
+	}
+
+	DEBUG("guest test mem offset: 0x%lx\n", guest_test_mem);
+
 	bmap = bitmap_alloc(host_num_pages);
 	host_bmap_track = bitmap_alloc(host_num_pages);
 
@@ -257,17 +277,17 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 
 	/* Add an extra memory slot for testing dirty logging */
 	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
-				    TEST_MEM_OFFSET,
+				    guest_test_mem,
 				    TEST_MEM_SLOT_INDEX,
 				    guest_num_pages,
 				    KVM_MEM_LOG_DIRTY_PAGES);
 
 	/* Do 1:1 mapping for the dirty track memory slot */
-	virt_map(vm, TEST_MEM_OFFSET, TEST_MEM_OFFSET,
+	virt_map(vm, guest_test_mem, guest_test_mem,
 		 guest_num_pages * guest_page_size, 0);
 
 	/* Cache the HVA pointer of the region */
-	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)TEST_MEM_OFFSET);
+	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_mem);
 
 #ifdef __x86_64__
 	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
@@ -279,6 +299,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	/* Export the shared variables to the guest */
 	sync_global_to_guest(vm, host_page_size);
 	sync_global_to_guest(vm, guest_page_size);
+	sync_global_to_guest(vm, guest_test_mem);
 	sync_global_to_guest(vm, guest_num_pages);
 
 	/* Start the iterations */
@@ -337,12 +358,17 @@ static void help(char *name)
 	int i;
 
 	puts("");
-	printf("usage: %s [-h] [-i iterations] [-I interval] [-m mode]\n", name);
+	printf("usage: %s [-h] [-i iterations] [-I interval] "
+	       "[-o offset] [-t] [-m mode]\n", name);
 	puts("");
 	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
 	       TEST_HOST_LOOP_N);
 	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
 	       TEST_HOST_LOOP_INTERVAL);
+	printf(" -o: guest test memory offset (default: 0x%lx)\n",
+	       DEFAULT_GUEST_TEST_MEM);
+	printf(" -t: map guest test memory at the top of the allowed "
+	       "physical address range\n");
 	printf(" -m: specify the guest mode ID to test "
 	       "(default: test all supported modes)\n"
 	       "     This option may be used multiple times.\n"
@@ -362,10 +388,11 @@ int main(int argc, char *argv[])
 	unsigned long iterations = TEST_HOST_LOOP_N;
 	unsigned long interval = TEST_HOST_LOOP_INTERVAL;
 	bool mode_selected = false;
+	bool top_offset = false;
 	unsigned int mode;
 	int opt, i;
 
-	while ((opt = getopt(argc, argv, "hi:I:m:")) != -1) {
+	while ((opt = getopt(argc, argv, "hi:I:o:tm:")) != -1) {
 		switch (opt) {
 		case 'i':
 			iterations = strtol(optarg, NULL, 10);
@@ -373,6 +400,12 @@ int main(int argc, char *argv[])
 		case 'I':
 			interval = strtol(optarg, NULL, 10);
 			break;
+		case 'o':
+			guest_test_mem = strtoull(optarg, NULL, 0);
+			break;
+		case 't':
+			top_offset = true;
+			break;
 		case 'm':
 			if (!mode_selected) {
 				for (i = 0; i < NUM_VM_MODES; ++i)
@@ -393,6 +426,8 @@ int main(int argc, char *argv[])
 
 	TEST_ASSERT(iterations > 2, "Iterations must be greater than two");
 	TEST_ASSERT(interval > 0, "Interval must be greater than zero");
+	TEST_ASSERT(!top_offset || guest_test_mem == DEFAULT_GUEST_TEST_MEM,
+		    "Cannot use both -o [offset] and -t at the same time");
 
 	DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
 	      iterations, interval);
@@ -406,7 +441,7 @@ int main(int argc, char *argv[])
 			    "Guest mode ID %d (%s) not supported.",
 			    vm_guest_modes[i].mode,
 			    vm_guest_mode_string(vm_guest_modes[i].mode));
-		run_test(vm_guest_modes[i].mode, iterations, interval);
+		run_test(vm_guest_modes[i].mode, iterations, interval, top_offset);
 	}
 
 	return 0;
-- 
cgit 


From 1e7ecd1b3d21a6302f3ee4a3720f682eb2467a3c Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 16 Oct 2018 18:50:08 +0200
Subject: KVM: selftests: state_test: test bare VMXON migration

Split prepare_for_vmx_operation() into prepare_for_vmx_operation() and
load_vmcs() so we can inject GUEST_SYNC() in between.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/x86_64/vmx.h   |  1 +
 tools/testing/selftests/kvm/lib/x86_64/vmx.c       |  5 +++++
 tools/testing/selftests/kvm/x86_64/state_test.c    | 22 ++++++++++++----------
 .../selftests/kvm/x86_64/vmx_tsc_adjust_test.c     |  1 +
 4 files changed, 19 insertions(+), 10 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index 12ebd836f7ef..4bbee8560292 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -548,5 +548,6 @@ struct vmx_pages {
 struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva);
 bool prepare_for_vmx_operation(struct vmx_pages *vmx);
 void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp);
+bool load_vmcs(struct vmx_pages *vmx);
 
 #endif /* SELFTEST_KVM_VMX_H */
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index d7c401472247..cc356da9b3d8 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -107,6 +107,11 @@ bool prepare_for_vmx_operation(struct vmx_pages *vmx)
 	if (vmxon(vmx->vmxon_gpa))
 		return false;
 
+	return true;
+}
+
+bool load_vmcs(struct vmx_pages *vmx)
+{
 	/* Load a VMCS. */
 	*(uint32_t *)(vmx->vmcs) = vmcs_revision();
 	if (vmclear(vmx->vmcs_gpa))
diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c
index 43df194a7c1e..03da41f0f736 100644
--- a/tools/testing/selftests/kvm/x86_64/state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/state_test.c
@@ -26,20 +26,20 @@ static bool have_nested_state;
 
 void l2_guest_code(void)
 {
-	GUEST_SYNC(5);
+	GUEST_SYNC(6);
 
         /* Exit to L1 */
 	vmcall();
 
 	/* L1 has now set up a shadow VMCS for us.  */
 	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
-	GUEST_SYNC(9);
+	GUEST_SYNC(10);
 	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
 	GUEST_ASSERT(!vmwrite(GUEST_RIP, 0xc0fffee));
-	GUEST_SYNC(10);
+	GUEST_SYNC(11);
 	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0fffee);
 	GUEST_ASSERT(!vmwrite(GUEST_RIP, 0xc0ffffee));
-	GUEST_SYNC(11);
+	GUEST_SYNC(12);
 
 	/* Done, exit to L1 and never come back.  */
 	vmcall();
@@ -52,15 +52,17 @@ void l1_guest_code(struct vmx_pages *vmx_pages)
 
 	GUEST_ASSERT(vmx_pages->vmcs_gpa);
 	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+	GUEST_SYNC(3);
+	GUEST_ASSERT(load_vmcs(vmx_pages));
 	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
 
-	GUEST_SYNC(3);
+	GUEST_SYNC(4);
 	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
 
 	prepare_vmcs(vmx_pages, l2_guest_code,
 		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
 
-	GUEST_SYNC(4);
+	GUEST_SYNC(5);
 	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
 	GUEST_ASSERT(!vmlaunch());
 	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
@@ -72,7 +74,7 @@ void l1_guest_code(struct vmx_pages *vmx_pages)
 	GUEST_ASSERT(!vmresume());
 	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
 
-	GUEST_SYNC(6);
+	GUEST_SYNC(7);
 	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
 
 	GUEST_ASSERT(!vmresume());
@@ -85,12 +87,12 @@ void l1_guest_code(struct vmx_pages *vmx_pages)
 
 	GUEST_ASSERT(!vmptrld(vmx_pages->shadow_vmcs_gpa));
 	GUEST_ASSERT(vmlaunch());
-	GUEST_SYNC(7);
+	GUEST_SYNC(8);
 	GUEST_ASSERT(vmlaunch());
 	GUEST_ASSERT(vmresume());
 
 	vmwrite(GUEST_RIP, 0xc0ffee);
-	GUEST_SYNC(8);
+	GUEST_SYNC(9);
 	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
 
 	GUEST_ASSERT(!vmptrld(vmx_pages->vmcs_gpa));
@@ -101,7 +103,7 @@ void l1_guest_code(struct vmx_pages *vmx_pages)
 	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffffee);
 	GUEST_ASSERT(vmlaunch());
 	GUEST_ASSERT(vmresume());
-	GUEST_SYNC(12);
+	GUEST_SYNC(13);
 	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffffee);
 	GUEST_ASSERT(vmlaunch());
 	GUEST_ASSERT(vmresume());
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
index 38a91a5f04ac..18fa64db0d7a 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
@@ -94,6 +94,7 @@ static void l1_guest_code(struct vmx_pages *vmx_pages)
 	check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
 
 	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+	GUEST_ASSERT(load_vmcs(vmx_pages));
 
 	/* Prepare the VMCS for L2 execution. */
 	prepare_vmcs(vmx_pages, l2_guest_code,
-- 
cgit 


From 18178ff862170ee4c9fd7450173c6fba9e3c4c3a Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 16 Oct 2018 18:50:11 +0200
Subject: KVM: selftests: add Enlightened VMCS test

Modify test library and add eVMCS test. This includes nVMX save/restore
testing.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/Makefile             |    1 +
 tools/testing/selftests/kvm/include/evmcs.h      | 1098 ++++++++++++++++++++++
 tools/testing/selftests/kvm/include/x86_64/vmx.h |   28 +
 tools/testing/selftests/kvm/lib/x86_64/vmx.c     |   48 +-
 tools/testing/selftests/kvm/x86_64/evmcs_test.c  |  160 ++++
 5 files changed, 1323 insertions(+), 12 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/include/evmcs.h
 create mode 100644 tools/testing/selftests/kvm/x86_64/evmcs_test.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 5e23f97ec46f..01a219229238 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -13,6 +13,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
 TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
 TEST_GEN_PROGS_x86_64 += x86_64/state_test
+TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
 
 TEST_GEN_PROGS_aarch64 += dirty_log_test
diff --git a/tools/testing/selftests/kvm/include/evmcs.h b/tools/testing/selftests/kvm/include/evmcs.h
new file mode 100644
index 000000000000..4059014d93ea
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/evmcs.h
@@ -0,0 +1,1098 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * tools/testing/selftests/kvm/include/vmx.h
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ *
+ */
+
+#ifndef SELFTEST_KVM_EVMCS_H
+#define SELFTEST_KVM_EVMCS_H
+
+#include <stdint.h>
+#include "vmx.h"
+
+#define u16 uint16_t
+#define u32 uint32_t
+#define u64 uint64_t
+
+extern bool enable_evmcs;
+
+struct hv_vp_assist_page {
+	__u32 apic_assist;
+	__u32 reserved;
+	__u64 vtl_control[2];
+	__u64 nested_enlightenments_control[2];
+	__u32 enlighten_vmentry;
+	__u64 current_nested_vmcs;
+};
+
+struct hv_enlightened_vmcs {
+	u32 revision_id;
+	u32 abort;
+
+	u16 host_es_selector;
+	u16 host_cs_selector;
+	u16 host_ss_selector;
+	u16 host_ds_selector;
+	u16 host_fs_selector;
+	u16 host_gs_selector;
+	u16 host_tr_selector;
+
+	u64 host_ia32_pat;
+	u64 host_ia32_efer;
+
+	u64 host_cr0;
+	u64 host_cr3;
+	u64 host_cr4;
+
+	u64 host_ia32_sysenter_esp;
+	u64 host_ia32_sysenter_eip;
+	u64 host_rip;
+	u32 host_ia32_sysenter_cs;
+
+	u32 pin_based_vm_exec_control;
+	u32 vm_exit_controls;
+	u32 secondary_vm_exec_control;
+
+	u64 io_bitmap_a;
+	u64 io_bitmap_b;
+	u64 msr_bitmap;
+
+	u16 guest_es_selector;
+	u16 guest_cs_selector;
+	u16 guest_ss_selector;
+	u16 guest_ds_selector;
+	u16 guest_fs_selector;
+	u16 guest_gs_selector;
+	u16 guest_ldtr_selector;
+	u16 guest_tr_selector;
+
+	u32 guest_es_limit;
+	u32 guest_cs_limit;
+	u32 guest_ss_limit;
+	u32 guest_ds_limit;
+	u32 guest_fs_limit;
+	u32 guest_gs_limit;
+	u32 guest_ldtr_limit;
+	u32 guest_tr_limit;
+	u32 guest_gdtr_limit;
+	u32 guest_idtr_limit;
+
+	u32 guest_es_ar_bytes;
+	u32 guest_cs_ar_bytes;
+	u32 guest_ss_ar_bytes;
+	u32 guest_ds_ar_bytes;
+	u32 guest_fs_ar_bytes;
+	u32 guest_gs_ar_bytes;
+	u32 guest_ldtr_ar_bytes;
+	u32 guest_tr_ar_bytes;
+
+	u64 guest_es_base;
+	u64 guest_cs_base;
+	u64 guest_ss_base;
+	u64 guest_ds_base;
+	u64 guest_fs_base;
+	u64 guest_gs_base;
+	u64 guest_ldtr_base;
+	u64 guest_tr_base;
+	u64 guest_gdtr_base;
+	u64 guest_idtr_base;
+
+	u64 padding64_1[3];
+
+	u64 vm_exit_msr_store_addr;
+	u64 vm_exit_msr_load_addr;
+	u64 vm_entry_msr_load_addr;
+
+	u64 cr3_target_value0;
+	u64 cr3_target_value1;
+	u64 cr3_target_value2;
+	u64 cr3_target_value3;
+
+	u32 page_fault_error_code_mask;
+	u32 page_fault_error_code_match;
+
+	u32 cr3_target_count;
+	u32 vm_exit_msr_store_count;
+	u32 vm_exit_msr_load_count;
+	u32 vm_entry_msr_load_count;
+
+	u64 tsc_offset;
+	u64 virtual_apic_page_addr;
+	u64 vmcs_link_pointer;
+
+	u64 guest_ia32_debugctl;
+	u64 guest_ia32_pat;
+	u64 guest_ia32_efer;
+
+	u64 guest_pdptr0;
+	u64 guest_pdptr1;
+	u64 guest_pdptr2;
+	u64 guest_pdptr3;
+
+	u64 guest_pending_dbg_exceptions;
+	u64 guest_sysenter_esp;
+	u64 guest_sysenter_eip;
+
+	u32 guest_activity_state;
+	u32 guest_sysenter_cs;
+
+	u64 cr0_guest_host_mask;
+	u64 cr4_guest_host_mask;
+	u64 cr0_read_shadow;
+	u64 cr4_read_shadow;
+	u64 guest_cr0;
+	u64 guest_cr3;
+	u64 guest_cr4;
+	u64 guest_dr7;
+
+	u64 host_fs_base;
+	u64 host_gs_base;
+	u64 host_tr_base;
+	u64 host_gdtr_base;
+	u64 host_idtr_base;
+	u64 host_rsp;
+
+	u64 ept_pointer;
+
+	u16 virtual_processor_id;
+	u16 padding16[3];
+
+	u64 padding64_2[5];
+	u64 guest_physical_address;
+
+	u32 vm_instruction_error;
+	u32 vm_exit_reason;
+	u32 vm_exit_intr_info;
+	u32 vm_exit_intr_error_code;
+	u32 idt_vectoring_info_field;
+	u32 idt_vectoring_error_code;
+	u32 vm_exit_instruction_len;
+	u32 vmx_instruction_info;
+
+	u64 exit_qualification;
+	u64 exit_io_instruction_ecx;
+	u64 exit_io_instruction_esi;
+	u64 exit_io_instruction_edi;
+	u64 exit_io_instruction_eip;
+
+	u64 guest_linear_address;
+	u64 guest_rsp;
+	u64 guest_rflags;
+
+	u32 guest_interruptibility_info;
+	u32 cpu_based_vm_exec_control;
+	u32 exception_bitmap;
+	u32 vm_entry_controls;
+	u32 vm_entry_intr_info_field;
+	u32 vm_entry_exception_error_code;
+	u32 vm_entry_instruction_len;
+	u32 tpr_threshold;
+
+	u64 guest_rip;
+
+	u32 hv_clean_fields;
+	u32 hv_padding_32;
+	u32 hv_synthetic_controls;
+	struct {
+		u32 nested_flush_hypercall:1;
+		u32 msr_bitmap:1;
+		u32 reserved:30;
+	} hv_enlightenments_control;
+	u32 hv_vp_id;
+
+	u64 hv_vm_id;
+	u64 partition_assist_page;
+	u64 padding64_4[4];
+	u64 guest_bndcfgs;
+	u64 padding64_5[7];
+	u64 xss_exit_bitmap;
+	u64 padding64_6[7];
+};
+
+#define HV_X64_MSR_VP_ASSIST_PAGE		0x40000073
+#define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE	0x00000001
+#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT	12
+#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK	\
+		(~((1ull << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) - 1))
+
+struct hv_enlightened_vmcs *current_evmcs;
+struct hv_vp_assist_page *current_vp_assist;
+
+static inline int enable_vp_assist(uint64_t vp_assist_pa, void *vp_assist)
+{
+	u64 val = (vp_assist_pa & HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK) |
+		HV_X64_MSR_VP_ASSIST_PAGE_ENABLE;
+
+	wrmsr(HV_X64_MSR_VP_ASSIST_PAGE, val);
+
+	current_vp_assist = vp_assist;
+
+	enable_evmcs = true;
+
+	return 0;
+}
+
+static inline int evmcs_vmptrld(uint64_t vmcs_pa, void *vmcs)
+{
+	current_vp_assist->current_nested_vmcs = vmcs_pa;
+	current_vp_assist->enlighten_vmentry = 1;
+
+	current_evmcs = vmcs;
+
+	return 0;
+}
+
+static inline int evmcs_vmptrst(uint64_t *value)
+{
+	*value = current_vp_assist->current_nested_vmcs &
+		~HV_X64_MSR_VP_ASSIST_PAGE_ENABLE;
+
+	return 0;
+}
+
+static inline int evmcs_vmread(uint64_t encoding, uint64_t *value)
+{
+	switch (encoding) {
+	case GUEST_RIP:
+		*value = current_evmcs->guest_rip;
+		break;
+	case GUEST_RSP:
+		*value = current_evmcs->guest_rsp;
+		break;
+	case GUEST_RFLAGS:
+		*value = current_evmcs->guest_rflags;
+		break;
+	case HOST_IA32_PAT:
+		*value = current_evmcs->host_ia32_pat;
+		break;
+	case HOST_IA32_EFER:
+		*value = current_evmcs->host_ia32_efer;
+		break;
+	case HOST_CR0:
+		*value = current_evmcs->host_cr0;
+		break;
+	case HOST_CR3:
+		*value = current_evmcs->host_cr3;
+		break;
+	case HOST_CR4:
+		*value = current_evmcs->host_cr4;
+		break;
+	case HOST_IA32_SYSENTER_ESP:
+		*value = current_evmcs->host_ia32_sysenter_esp;
+		break;
+	case HOST_IA32_SYSENTER_EIP:
+		*value = current_evmcs->host_ia32_sysenter_eip;
+		break;
+	case HOST_RIP:
+		*value = current_evmcs->host_rip;
+		break;
+	case IO_BITMAP_A:
+		*value = current_evmcs->io_bitmap_a;
+		break;
+	case IO_BITMAP_B:
+		*value = current_evmcs->io_bitmap_b;
+		break;
+	case MSR_BITMAP:
+		*value = current_evmcs->msr_bitmap;
+		break;
+	case GUEST_ES_BASE:
+		*value = current_evmcs->guest_es_base;
+		break;
+	case GUEST_CS_BASE:
+		*value = current_evmcs->guest_cs_base;
+		break;
+	case GUEST_SS_BASE:
+		*value = current_evmcs->guest_ss_base;
+		break;
+	case GUEST_DS_BASE:
+		*value = current_evmcs->guest_ds_base;
+		break;
+	case GUEST_FS_BASE:
+		*value = current_evmcs->guest_fs_base;
+		break;
+	case GUEST_GS_BASE:
+		*value = current_evmcs->guest_gs_base;
+		break;
+	case GUEST_LDTR_BASE:
+		*value = current_evmcs->guest_ldtr_base;
+		break;
+	case GUEST_TR_BASE:
+		*value = current_evmcs->guest_tr_base;
+		break;
+	case GUEST_GDTR_BASE:
+		*value = current_evmcs->guest_gdtr_base;
+		break;
+	case GUEST_IDTR_BASE:
+		*value = current_evmcs->guest_idtr_base;
+		break;
+	case TSC_OFFSET:
+		*value = current_evmcs->tsc_offset;
+		break;
+	case VIRTUAL_APIC_PAGE_ADDR:
+		*value = current_evmcs->virtual_apic_page_addr;
+		break;
+	case VMCS_LINK_POINTER:
+		*value = current_evmcs->vmcs_link_pointer;
+		break;
+	case GUEST_IA32_DEBUGCTL:
+		*value = current_evmcs->guest_ia32_debugctl;
+		break;
+	case GUEST_IA32_PAT:
+		*value = current_evmcs->guest_ia32_pat;
+		break;
+	case GUEST_IA32_EFER:
+		*value = current_evmcs->guest_ia32_efer;
+		break;
+	case GUEST_PDPTR0:
+		*value = current_evmcs->guest_pdptr0;
+		break;
+	case GUEST_PDPTR1:
+		*value = current_evmcs->guest_pdptr1;
+		break;
+	case GUEST_PDPTR2:
+		*value = current_evmcs->guest_pdptr2;
+		break;
+	case GUEST_PDPTR3:
+		*value = current_evmcs->guest_pdptr3;
+		break;
+	case GUEST_PENDING_DBG_EXCEPTIONS:
+		*value = current_evmcs->guest_pending_dbg_exceptions;
+		break;
+	case GUEST_SYSENTER_ESP:
+		*value = current_evmcs->guest_sysenter_esp;
+		break;
+	case GUEST_SYSENTER_EIP:
+		*value = current_evmcs->guest_sysenter_eip;
+		break;
+	case CR0_GUEST_HOST_MASK:
+		*value = current_evmcs->cr0_guest_host_mask;
+		break;
+	case CR4_GUEST_HOST_MASK:
+		*value = current_evmcs->cr4_guest_host_mask;
+		break;
+	case CR0_READ_SHADOW:
+		*value = current_evmcs->cr0_read_shadow;
+		break;
+	case CR4_READ_SHADOW:
+		*value = current_evmcs->cr4_read_shadow;
+		break;
+	case GUEST_CR0:
+		*value = current_evmcs->guest_cr0;
+		break;
+	case GUEST_CR3:
+		*value = current_evmcs->guest_cr3;
+		break;
+	case GUEST_CR4:
+		*value = current_evmcs->guest_cr4;
+		break;
+	case GUEST_DR7:
+		*value = current_evmcs->guest_dr7;
+		break;
+	case HOST_FS_BASE:
+		*value = current_evmcs->host_fs_base;
+		break;
+	case HOST_GS_BASE:
+		*value = current_evmcs->host_gs_base;
+		break;
+	case HOST_TR_BASE:
+		*value = current_evmcs->host_tr_base;
+		break;
+	case HOST_GDTR_BASE:
+		*value = current_evmcs->host_gdtr_base;
+		break;
+	case HOST_IDTR_BASE:
+		*value = current_evmcs->host_idtr_base;
+		break;
+	case HOST_RSP:
+		*value = current_evmcs->host_rsp;
+		break;
+	case EPT_POINTER:
+		*value = current_evmcs->ept_pointer;
+		break;
+	case GUEST_BNDCFGS:
+		*value = current_evmcs->guest_bndcfgs;
+		break;
+	case XSS_EXIT_BITMAP:
+		*value = current_evmcs->xss_exit_bitmap;
+		break;
+	case GUEST_PHYSICAL_ADDRESS:
+		*value = current_evmcs->guest_physical_address;
+		break;
+	case EXIT_QUALIFICATION:
+		*value = current_evmcs->exit_qualification;
+		break;
+	case GUEST_LINEAR_ADDRESS:
+		*value = current_evmcs->guest_linear_address;
+		break;
+	case VM_EXIT_MSR_STORE_ADDR:
+		*value = current_evmcs->vm_exit_msr_store_addr;
+		break;
+	case VM_EXIT_MSR_LOAD_ADDR:
+		*value = current_evmcs->vm_exit_msr_load_addr;
+		break;
+	case VM_ENTRY_MSR_LOAD_ADDR:
+		*value = current_evmcs->vm_entry_msr_load_addr;
+		break;
+	case CR3_TARGET_VALUE0:
+		*value = current_evmcs->cr3_target_value0;
+		break;
+	case CR3_TARGET_VALUE1:
+		*value = current_evmcs->cr3_target_value1;
+		break;
+	case CR3_TARGET_VALUE2:
+		*value = current_evmcs->cr3_target_value2;
+		break;
+	case CR3_TARGET_VALUE3:
+		*value = current_evmcs->cr3_target_value3;
+		break;
+	case TPR_THRESHOLD:
+		*value = current_evmcs->tpr_threshold;
+		break;
+	case GUEST_INTERRUPTIBILITY_INFO:
+		*value = current_evmcs->guest_interruptibility_info;
+		break;
+	case CPU_BASED_VM_EXEC_CONTROL:
+		*value = current_evmcs->cpu_based_vm_exec_control;
+		break;
+	case EXCEPTION_BITMAP:
+		*value = current_evmcs->exception_bitmap;
+		break;
+	case VM_ENTRY_CONTROLS:
+		*value = current_evmcs->vm_entry_controls;
+		break;
+	case VM_ENTRY_INTR_INFO_FIELD:
+		*value = current_evmcs->vm_entry_intr_info_field;
+		break;
+	case VM_ENTRY_EXCEPTION_ERROR_CODE:
+		*value = current_evmcs->vm_entry_exception_error_code;
+		break;
+	case VM_ENTRY_INSTRUCTION_LEN:
+		*value = current_evmcs->vm_entry_instruction_len;
+		break;
+	case HOST_IA32_SYSENTER_CS:
+		*value = current_evmcs->host_ia32_sysenter_cs;
+		break;
+	case PIN_BASED_VM_EXEC_CONTROL:
+		*value = current_evmcs->pin_based_vm_exec_control;
+		break;
+	case VM_EXIT_CONTROLS:
+		*value = current_evmcs->vm_exit_controls;
+		break;
+	case SECONDARY_VM_EXEC_CONTROL:
+		*value = current_evmcs->secondary_vm_exec_control;
+		break;
+	case GUEST_ES_LIMIT:
+		*value = current_evmcs->guest_es_limit;
+		break;
+	case GUEST_CS_LIMIT:
+		*value = current_evmcs->guest_cs_limit;
+		break;
+	case GUEST_SS_LIMIT:
+		*value = current_evmcs->guest_ss_limit;
+		break;
+	case GUEST_DS_LIMIT:
+		*value = current_evmcs->guest_ds_limit;
+		break;
+	case GUEST_FS_LIMIT:
+		*value = current_evmcs->guest_fs_limit;
+		break;
+	case GUEST_GS_LIMIT:
+		*value = current_evmcs->guest_gs_limit;
+		break;
+	case GUEST_LDTR_LIMIT:
+		*value = current_evmcs->guest_ldtr_limit;
+		break;
+	case GUEST_TR_LIMIT:
+		*value = current_evmcs->guest_tr_limit;
+		break;
+	case GUEST_GDTR_LIMIT:
+		*value = current_evmcs->guest_gdtr_limit;
+		break;
+	case GUEST_IDTR_LIMIT:
+		*value = current_evmcs->guest_idtr_limit;
+		break;
+	case GUEST_ES_AR_BYTES:
+		*value = current_evmcs->guest_es_ar_bytes;
+		break;
+	case GUEST_CS_AR_BYTES:
+		*value = current_evmcs->guest_cs_ar_bytes;
+		break;
+	case GUEST_SS_AR_BYTES:
+		*value = current_evmcs->guest_ss_ar_bytes;
+		break;
+	case GUEST_DS_AR_BYTES:
+		*value = current_evmcs->guest_ds_ar_bytes;
+		break;
+	case GUEST_FS_AR_BYTES:
+		*value = current_evmcs->guest_fs_ar_bytes;
+		break;
+	case GUEST_GS_AR_BYTES:
+		*value = current_evmcs->guest_gs_ar_bytes;
+		break;
+	case GUEST_LDTR_AR_BYTES:
+		*value = current_evmcs->guest_ldtr_ar_bytes;
+		break;
+	case GUEST_TR_AR_BYTES:
+		*value = current_evmcs->guest_tr_ar_bytes;
+		break;
+	case GUEST_ACTIVITY_STATE:
+		*value = current_evmcs->guest_activity_state;
+		break;
+	case GUEST_SYSENTER_CS:
+		*value = current_evmcs->guest_sysenter_cs;
+		break;
+	case VM_INSTRUCTION_ERROR:
+		*value = current_evmcs->vm_instruction_error;
+		break;
+	case VM_EXIT_REASON:
+		*value = current_evmcs->vm_exit_reason;
+		break;
+	case VM_EXIT_INTR_INFO:
+		*value = current_evmcs->vm_exit_intr_info;
+		break;
+	case VM_EXIT_INTR_ERROR_CODE:
+		*value = current_evmcs->vm_exit_intr_error_code;
+		break;
+	case IDT_VECTORING_INFO_FIELD:
+		*value = current_evmcs->idt_vectoring_info_field;
+		break;
+	case IDT_VECTORING_ERROR_CODE:
+		*value = current_evmcs->idt_vectoring_error_code;
+		break;
+	case VM_EXIT_INSTRUCTION_LEN:
+		*value = current_evmcs->vm_exit_instruction_len;
+		break;
+	case VMX_INSTRUCTION_INFO:
+		*value = current_evmcs->vmx_instruction_info;
+		break;
+	case PAGE_FAULT_ERROR_CODE_MASK:
+		*value = current_evmcs->page_fault_error_code_mask;
+		break;
+	case PAGE_FAULT_ERROR_CODE_MATCH:
+		*value = current_evmcs->page_fault_error_code_match;
+		break;
+	case CR3_TARGET_COUNT:
+		*value = current_evmcs->cr3_target_count;
+		break;
+	case VM_EXIT_MSR_STORE_COUNT:
+		*value = current_evmcs->vm_exit_msr_store_count;
+		break;
+	case VM_EXIT_MSR_LOAD_COUNT:
+		*value = current_evmcs->vm_exit_msr_load_count;
+		break;
+	case VM_ENTRY_MSR_LOAD_COUNT:
+		*value = current_evmcs->vm_entry_msr_load_count;
+		break;
+	case HOST_ES_SELECTOR:
+		*value = current_evmcs->host_es_selector;
+		break;
+	case HOST_CS_SELECTOR:
+		*value = current_evmcs->host_cs_selector;
+		break;
+	case HOST_SS_SELECTOR:
+		*value = current_evmcs->host_ss_selector;
+		break;
+	case HOST_DS_SELECTOR:
+		*value = current_evmcs->host_ds_selector;
+		break;
+	case HOST_FS_SELECTOR:
+		*value = current_evmcs->host_fs_selector;
+		break;
+	case HOST_GS_SELECTOR:
+		*value = current_evmcs->host_gs_selector;
+		break;
+	case HOST_TR_SELECTOR:
+		*value = current_evmcs->host_tr_selector;
+		break;
+	case GUEST_ES_SELECTOR:
+		*value = current_evmcs->guest_es_selector;
+		break;
+	case GUEST_CS_SELECTOR:
+		*value = current_evmcs->guest_cs_selector;
+		break;
+	case GUEST_SS_SELECTOR:
+		*value = current_evmcs->guest_ss_selector;
+		break;
+	case GUEST_DS_SELECTOR:
+		*value = current_evmcs->guest_ds_selector;
+		break;
+	case GUEST_FS_SELECTOR:
+		*value = current_evmcs->guest_fs_selector;
+		break;
+	case GUEST_GS_SELECTOR:
+		*value = current_evmcs->guest_gs_selector;
+		break;
+	case GUEST_LDTR_SELECTOR:
+		*value = current_evmcs->guest_ldtr_selector;
+		break;
+	case GUEST_TR_SELECTOR:
+		*value = current_evmcs->guest_tr_selector;
+		break;
+	case VIRTUAL_PROCESSOR_ID:
+		*value = current_evmcs->virtual_processor_id;
+		break;
+	default: return 1;
+	}
+
+	return 0;
+}
+
+static inline int evmcs_vmwrite(uint64_t encoding, uint64_t value)
+{
+	switch (encoding) {
+	case GUEST_RIP:
+		current_evmcs->guest_rip = value;
+		break;
+	case GUEST_RSP:
+		current_evmcs->guest_rsp = value;
+		break;
+	case GUEST_RFLAGS:
+		current_evmcs->guest_rflags = value;
+		break;
+	case HOST_IA32_PAT:
+		current_evmcs->host_ia32_pat = value;
+		break;
+	case HOST_IA32_EFER:
+		current_evmcs->host_ia32_efer = value;
+		break;
+	case HOST_CR0:
+		current_evmcs->host_cr0 = value;
+		break;
+	case HOST_CR3:
+		current_evmcs->host_cr3 = value;
+		break;
+	case HOST_CR4:
+		current_evmcs->host_cr4 = value;
+		break;
+	case HOST_IA32_SYSENTER_ESP:
+		current_evmcs->host_ia32_sysenter_esp = value;
+		break;
+	case HOST_IA32_SYSENTER_EIP:
+		current_evmcs->host_ia32_sysenter_eip = value;
+		break;
+	case HOST_RIP:
+		current_evmcs->host_rip = value;
+		break;
+	case IO_BITMAP_A:
+		current_evmcs->io_bitmap_a = value;
+		break;
+	case IO_BITMAP_B:
+		current_evmcs->io_bitmap_b = value;
+		break;
+	case MSR_BITMAP:
+		current_evmcs->msr_bitmap = value;
+		break;
+	case GUEST_ES_BASE:
+		current_evmcs->guest_es_base = value;
+		break;
+	case GUEST_CS_BASE:
+		current_evmcs->guest_cs_base = value;
+		break;
+	case GUEST_SS_BASE:
+		current_evmcs->guest_ss_base = value;
+		break;
+	case GUEST_DS_BASE:
+		current_evmcs->guest_ds_base = value;
+		break;
+	case GUEST_FS_BASE:
+		current_evmcs->guest_fs_base = value;
+		break;
+	case GUEST_GS_BASE:
+		current_evmcs->guest_gs_base = value;
+		break;
+	case GUEST_LDTR_BASE:
+		current_evmcs->guest_ldtr_base = value;
+		break;
+	case GUEST_TR_BASE:
+		current_evmcs->guest_tr_base = value;
+		break;
+	case GUEST_GDTR_BASE:
+		current_evmcs->guest_gdtr_base = value;
+		break;
+	case GUEST_IDTR_BASE:
+		current_evmcs->guest_idtr_base = value;
+		break;
+	case TSC_OFFSET:
+		current_evmcs->tsc_offset = value;
+		break;
+	case VIRTUAL_APIC_PAGE_ADDR:
+		current_evmcs->virtual_apic_page_addr = value;
+		break;
+	case VMCS_LINK_POINTER:
+		current_evmcs->vmcs_link_pointer = value;
+		break;
+	case GUEST_IA32_DEBUGCTL:
+		current_evmcs->guest_ia32_debugctl = value;
+		break;
+	case GUEST_IA32_PAT:
+		current_evmcs->guest_ia32_pat = value;
+		break;
+	case GUEST_IA32_EFER:
+		current_evmcs->guest_ia32_efer = value;
+		break;
+	case GUEST_PDPTR0:
+		current_evmcs->guest_pdptr0 = value;
+		break;
+	case GUEST_PDPTR1:
+		current_evmcs->guest_pdptr1 = value;
+		break;
+	case GUEST_PDPTR2:
+		current_evmcs->guest_pdptr2 = value;
+		break;
+	case GUEST_PDPTR3:
+		current_evmcs->guest_pdptr3 = value;
+		break;
+	case GUEST_PENDING_DBG_EXCEPTIONS:
+		current_evmcs->guest_pending_dbg_exceptions = value;
+		break;
+	case GUEST_SYSENTER_ESP:
+		current_evmcs->guest_sysenter_esp = value;
+		break;
+	case GUEST_SYSENTER_EIP:
+		current_evmcs->guest_sysenter_eip = value;
+		break;
+	case CR0_GUEST_HOST_MASK:
+		current_evmcs->cr0_guest_host_mask = value;
+		break;
+	case CR4_GUEST_HOST_MASK:
+		current_evmcs->cr4_guest_host_mask = value;
+		break;
+	case CR0_READ_SHADOW:
+		current_evmcs->cr0_read_shadow = value;
+		break;
+	case CR4_READ_SHADOW:
+		current_evmcs->cr4_read_shadow = value;
+		break;
+	case GUEST_CR0:
+		current_evmcs->guest_cr0 = value;
+		break;
+	case GUEST_CR3:
+		current_evmcs->guest_cr3 = value;
+		break;
+	case GUEST_CR4:
+		current_evmcs->guest_cr4 = value;
+		break;
+	case GUEST_DR7:
+		current_evmcs->guest_dr7 = value;
+		break;
+	case HOST_FS_BASE:
+		current_evmcs->host_fs_base = value;
+		break;
+	case HOST_GS_BASE:
+		current_evmcs->host_gs_base = value;
+		break;
+	case HOST_TR_BASE:
+		current_evmcs->host_tr_base = value;
+		break;
+	case HOST_GDTR_BASE:
+		current_evmcs->host_gdtr_base = value;
+		break;
+	case HOST_IDTR_BASE:
+		current_evmcs->host_idtr_base = value;
+		break;
+	case HOST_RSP:
+		current_evmcs->host_rsp = value;
+		break;
+	case EPT_POINTER:
+		current_evmcs->ept_pointer = value;
+		break;
+	case GUEST_BNDCFGS:
+		current_evmcs->guest_bndcfgs = value;
+		break;
+	case XSS_EXIT_BITMAP:
+		current_evmcs->xss_exit_bitmap = value;
+		break;
+	case GUEST_PHYSICAL_ADDRESS:
+		current_evmcs->guest_physical_address = value;
+		break;
+	case EXIT_QUALIFICATION:
+		current_evmcs->exit_qualification = value;
+		break;
+	case GUEST_LINEAR_ADDRESS:
+		current_evmcs->guest_linear_address = value;
+		break;
+	case VM_EXIT_MSR_STORE_ADDR:
+		current_evmcs->vm_exit_msr_store_addr = value;
+		break;
+	case VM_EXIT_MSR_LOAD_ADDR:
+		current_evmcs->vm_exit_msr_load_addr = value;
+		break;
+	case VM_ENTRY_MSR_LOAD_ADDR:
+		current_evmcs->vm_entry_msr_load_addr = value;
+		break;
+	case CR3_TARGET_VALUE0:
+		current_evmcs->cr3_target_value0 = value;
+		break;
+	case CR3_TARGET_VALUE1:
+		current_evmcs->cr3_target_value1 = value;
+		break;
+	case CR3_TARGET_VALUE2:
+		current_evmcs->cr3_target_value2 = value;
+		break;
+	case CR3_TARGET_VALUE3:
+		current_evmcs->cr3_target_value3 = value;
+		break;
+	case TPR_THRESHOLD:
+		current_evmcs->tpr_threshold = value;
+		break;
+	case GUEST_INTERRUPTIBILITY_INFO:
+		current_evmcs->guest_interruptibility_info = value;
+		break;
+	case CPU_BASED_VM_EXEC_CONTROL:
+		current_evmcs->cpu_based_vm_exec_control = value;
+		break;
+	case EXCEPTION_BITMAP:
+		current_evmcs->exception_bitmap = value;
+		break;
+	case VM_ENTRY_CONTROLS:
+		current_evmcs->vm_entry_controls = value;
+		break;
+	case VM_ENTRY_INTR_INFO_FIELD:
+		current_evmcs->vm_entry_intr_info_field = value;
+		break;
+	case VM_ENTRY_EXCEPTION_ERROR_CODE:
+		current_evmcs->vm_entry_exception_error_code = value;
+		break;
+	case VM_ENTRY_INSTRUCTION_LEN:
+		current_evmcs->vm_entry_instruction_len = value;
+		break;
+	case HOST_IA32_SYSENTER_CS:
+		current_evmcs->host_ia32_sysenter_cs = value;
+		break;
+	case PIN_BASED_VM_EXEC_CONTROL:
+		current_evmcs->pin_based_vm_exec_control = value;
+		break;
+	case VM_EXIT_CONTROLS:
+		current_evmcs->vm_exit_controls = value;
+		break;
+	case SECONDARY_VM_EXEC_CONTROL:
+		current_evmcs->secondary_vm_exec_control = value;
+		break;
+	case GUEST_ES_LIMIT:
+		current_evmcs->guest_es_limit = value;
+		break;
+	case GUEST_CS_LIMIT:
+		current_evmcs->guest_cs_limit = value;
+		break;
+	case GUEST_SS_LIMIT:
+		current_evmcs->guest_ss_limit = value;
+		break;
+	case GUEST_DS_LIMIT:
+		current_evmcs->guest_ds_limit = value;
+		break;
+	case GUEST_FS_LIMIT:
+		current_evmcs->guest_fs_limit = value;
+		break;
+	case GUEST_GS_LIMIT:
+		current_evmcs->guest_gs_limit = value;
+		break;
+	case GUEST_LDTR_LIMIT:
+		current_evmcs->guest_ldtr_limit = value;
+		break;
+	case GUEST_TR_LIMIT:
+		current_evmcs->guest_tr_limit = value;
+		break;
+	case GUEST_GDTR_LIMIT:
+		current_evmcs->guest_gdtr_limit = value;
+		break;
+	case GUEST_IDTR_LIMIT:
+		current_evmcs->guest_idtr_limit = value;
+		break;
+	case GUEST_ES_AR_BYTES:
+		current_evmcs->guest_es_ar_bytes = value;
+		break;
+	case GUEST_CS_AR_BYTES:
+		current_evmcs->guest_cs_ar_bytes = value;
+		break;
+	case GUEST_SS_AR_BYTES:
+		current_evmcs->guest_ss_ar_bytes = value;
+		break;
+	case GUEST_DS_AR_BYTES:
+		current_evmcs->guest_ds_ar_bytes = value;
+		break;
+	case GUEST_FS_AR_BYTES:
+		current_evmcs->guest_fs_ar_bytes = value;
+		break;
+	case GUEST_GS_AR_BYTES:
+		current_evmcs->guest_gs_ar_bytes = value;
+		break;
+	case GUEST_LDTR_AR_BYTES:
+		current_evmcs->guest_ldtr_ar_bytes = value;
+		break;
+	case GUEST_TR_AR_BYTES:
+		current_evmcs->guest_tr_ar_bytes = value;
+		break;
+	case GUEST_ACTIVITY_STATE:
+		current_evmcs->guest_activity_state = value;
+		break;
+	case GUEST_SYSENTER_CS:
+		current_evmcs->guest_sysenter_cs = value;
+		break;
+	case VM_INSTRUCTION_ERROR:
+		current_evmcs->vm_instruction_error = value;
+		break;
+	case VM_EXIT_REASON:
+		current_evmcs->vm_exit_reason = value;
+		break;
+	case VM_EXIT_INTR_INFO:
+		current_evmcs->vm_exit_intr_info = value;
+		break;
+	case VM_EXIT_INTR_ERROR_CODE:
+		current_evmcs->vm_exit_intr_error_code = value;
+		break;
+	case IDT_VECTORING_INFO_FIELD:
+		current_evmcs->idt_vectoring_info_field = value;
+		break;
+	case IDT_VECTORING_ERROR_CODE:
+		current_evmcs->idt_vectoring_error_code = value;
+		break;
+	case VM_EXIT_INSTRUCTION_LEN:
+		current_evmcs->vm_exit_instruction_len = value;
+		break;
+	case VMX_INSTRUCTION_INFO:
+		current_evmcs->vmx_instruction_info = value;
+		break;
+	case PAGE_FAULT_ERROR_CODE_MASK:
+		current_evmcs->page_fault_error_code_mask = value;
+		break;
+	case PAGE_FAULT_ERROR_CODE_MATCH:
+		current_evmcs->page_fault_error_code_match = value;
+		break;
+	case CR3_TARGET_COUNT:
+		current_evmcs->cr3_target_count = value;
+		break;
+	case VM_EXIT_MSR_STORE_COUNT:
+		current_evmcs->vm_exit_msr_store_count = value;
+		break;
+	case VM_EXIT_MSR_LOAD_COUNT:
+		current_evmcs->vm_exit_msr_load_count = value;
+		break;
+	case VM_ENTRY_MSR_LOAD_COUNT:
+		current_evmcs->vm_entry_msr_load_count = value;
+		break;
+	case HOST_ES_SELECTOR:
+		current_evmcs->host_es_selector = value;
+		break;
+	case HOST_CS_SELECTOR:
+		current_evmcs->host_cs_selector = value;
+		break;
+	case HOST_SS_SELECTOR:
+		current_evmcs->host_ss_selector = value;
+		break;
+	case HOST_DS_SELECTOR:
+		current_evmcs->host_ds_selector = value;
+		break;
+	case HOST_FS_SELECTOR:
+		current_evmcs->host_fs_selector = value;
+		break;
+	case HOST_GS_SELECTOR:
+		current_evmcs->host_gs_selector = value;
+		break;
+	case HOST_TR_SELECTOR:
+		current_evmcs->host_tr_selector = value;
+		break;
+	case GUEST_ES_SELECTOR:
+		current_evmcs->guest_es_selector = value;
+		break;
+	case GUEST_CS_SELECTOR:
+		current_evmcs->guest_cs_selector = value;
+		break;
+	case GUEST_SS_SELECTOR:
+		current_evmcs->guest_ss_selector = value;
+		break;
+	case GUEST_DS_SELECTOR:
+		current_evmcs->guest_ds_selector = value;
+		break;
+	case GUEST_FS_SELECTOR:
+		current_evmcs->guest_fs_selector = value;
+		break;
+	case GUEST_GS_SELECTOR:
+		current_evmcs->guest_gs_selector = value;
+		break;
+	case GUEST_LDTR_SELECTOR:
+		current_evmcs->guest_ldtr_selector = value;
+		break;
+	case GUEST_TR_SELECTOR:
+		current_evmcs->guest_tr_selector = value;
+		break;
+	case VIRTUAL_PROCESSOR_ID:
+		current_evmcs->virtual_processor_id = value;
+		break;
+	default: return 1;
+	}
+
+	return 0;
+}
+
+static inline int evmcs_vmlaunch(void)
+{
+	int ret;
+
+	current_evmcs->hv_clean_fields = 0;
+
+	__asm__ __volatile__("push %%rbp;"
+			     "push %%rcx;"
+			     "push %%rdx;"
+			     "push %%rsi;"
+			     "push %%rdi;"
+			     "push $0;"
+			     "mov %%rsp, (%[host_rsp]);"
+			     "lea 1f(%%rip), %%rax;"
+			     "mov %%rax, (%[host_rip]);"
+			     "vmlaunch;"
+			     "incq (%%rsp);"
+			     "1: pop %%rax;"
+			     "pop %%rdi;"
+			     "pop %%rsi;"
+			     "pop %%rdx;"
+			     "pop %%rcx;"
+			     "pop %%rbp;"
+			     : [ret]"=&a"(ret)
+			     : [host_rsp]"r"
+			       ((uint64_t)&current_evmcs->host_rsp),
+			       [host_rip]"r"
+			       ((uint64_t)&current_evmcs->host_rip)
+			     : "memory", "cc", "rbx", "r8", "r9", "r10",
+			       "r11", "r12", "r13", "r14", "r15");
+	return ret;
+}
+
+/*
+ * No guest state (e.g. GPRs) is established by this vmresume.
+ */
+static inline int evmcs_vmresume(void)
+{
+	int ret;
+
+	current_evmcs->hv_clean_fields = 0;
+
+	__asm__ __volatile__("push %%rbp;"
+			     "push %%rcx;"
+			     "push %%rdx;"
+			     "push %%rsi;"
+			     "push %%rdi;"
+			     "push $0;"
+			     "mov %%rsp, (%[host_rsp]);"
+			     "lea 1f(%%rip), %%rax;"
+			     "mov %%rax, (%[host_rip]);"
+			     "vmresume;"
+			     "incq (%%rsp);"
+			     "1: pop %%rax;"
+			     "pop %%rdi;"
+			     "pop %%rsi;"
+			     "pop %%rdx;"
+			     "pop %%rcx;"
+			     "pop %%rbp;"
+			     : [ret]"=&a"(ret)
+			     : [host_rsp]"r"
+			       ((uint64_t)&current_evmcs->host_rsp),
+			       [host_rip]"r"
+			       ((uint64_t)&current_evmcs->host_rip)
+			     : "memory", "cc", "rbx", "r8", "r9", "r10",
+			       "r11", "r12", "r13", "r14", "r15");
+	return ret;
+}
+
+#endif /* !SELFTEST_KVM_EVMCS_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index 4bbee8560292..c9bd935b939c 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -339,6 +339,8 @@ struct vmx_msr_entry {
 	uint64_t value;
 } __attribute__ ((aligned(16)));
 
+#include "evmcs.h"
+
 static inline int vmxon(uint64_t phys)
 {
 	uint8_t ret;
@@ -372,6 +374,9 @@ static inline int vmptrld(uint64_t vmcs_pa)
 {
 	uint8_t ret;
 
+	if (enable_evmcs)
+		return -1;
+
 	__asm__ __volatile__ ("vmptrld %[pa]; setna %[ret]"
 		: [ret]"=rm"(ret)
 		: [pa]"m"(vmcs_pa)
@@ -385,6 +390,9 @@ static inline int vmptrst(uint64_t *value)
 	uint64_t tmp;
 	uint8_t ret;
 
+	if (enable_evmcs)
+		return evmcs_vmptrst(value);
+
 	__asm__ __volatile__("vmptrst %[value]; setna %[ret]"
 		: [value]"=m"(tmp), [ret]"=rm"(ret)
 		: : "cc", "memory");
@@ -411,6 +419,9 @@ static inline int vmlaunch(void)
 {
 	int ret;
 
+	if (enable_evmcs)
+		return evmcs_vmlaunch();
+
 	__asm__ __volatile__("push %%rbp;"
 			     "push %%rcx;"
 			     "push %%rdx;"
@@ -443,6 +454,9 @@ static inline int vmresume(void)
 {
 	int ret;
 
+	if (enable_evmcs)
+		return evmcs_vmresume();
+
 	__asm__ __volatile__("push %%rbp;"
 			     "push %%rcx;"
 			     "push %%rdx;"
@@ -482,6 +496,9 @@ static inline int vmread(uint64_t encoding, uint64_t *value)
 	uint64_t tmp;
 	uint8_t ret;
 
+	if (enable_evmcs)
+		return evmcs_vmread(encoding, value);
+
 	__asm__ __volatile__("vmread %[encoding], %[value]; setna %[ret]"
 		: [value]"=rm"(tmp), [ret]"=rm"(ret)
 		: [encoding]"r"(encoding)
@@ -506,6 +523,9 @@ static inline int vmwrite(uint64_t encoding, uint64_t value)
 {
 	uint8_t ret;
 
+	if (enable_evmcs)
+		return evmcs_vmwrite(encoding, value);
+
 	__asm__ __volatile__ ("vmwrite %[value], %[encoding]; setna %[ret]"
 		: [ret]"=rm"(ret)
 		: [value]"rm"(value), [encoding]"r"(encoding)
@@ -543,6 +563,14 @@ struct vmx_pages {
 	void *vmwrite_hva;
 	uint64_t vmwrite_gpa;
 	void *vmwrite;
+
+	void *vp_assist_hva;
+	uint64_t vp_assist_gpa;
+	void *vp_assist;
+
+	void *enlightened_vmcs_hva;
+	uint64_t enlightened_vmcs_gpa;
+	void *enlightened_vmcs;
 };
 
 struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva);
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index cc356da9b3d8..771ba6bf751c 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -13,6 +13,8 @@
 #include "processor.h"
 #include "vmx.h"
 
+bool enable_evmcs;
+
 /* Allocate memory regions for nested VMX tests.
  *
  * Input Args:
@@ -62,6 +64,20 @@ vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva)
 	vmx->vmwrite_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmwrite);
 	memset(vmx->vmwrite_hva, 0, getpagesize());
 
+	/* Setup of a region of guest memory for the VP Assist page. */
+	vmx->vp_assist = (void *)vm_vaddr_alloc(vm, getpagesize(),
+						0x10000, 0, 0);
+	vmx->vp_assist_hva = addr_gva2hva(vm, (uintptr_t)vmx->vp_assist);
+	vmx->vp_assist_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vp_assist);
+
+	/* Setup of a region of guest memory for the enlightened VMCS. */
+	vmx->enlightened_vmcs = (void *)vm_vaddr_alloc(vm, getpagesize(),
+						       0x10000, 0, 0);
+	vmx->enlightened_vmcs_hva =
+		addr_gva2hva(vm, (uintptr_t)vmx->enlightened_vmcs);
+	vmx->enlightened_vmcs_gpa =
+		addr_gva2gpa(vm, (uintptr_t)vmx->enlightened_vmcs);
+
 	*p_vmx_gva = vmx_gva;
 	return vmx;
 }
@@ -112,18 +128,26 @@ bool prepare_for_vmx_operation(struct vmx_pages *vmx)
 
 bool load_vmcs(struct vmx_pages *vmx)
 {
-	/* Load a VMCS. */
-	*(uint32_t *)(vmx->vmcs) = vmcs_revision();
-	if (vmclear(vmx->vmcs_gpa))
-		return false;
-
-	if (vmptrld(vmx->vmcs_gpa))
-		return false;
-
-	/* Setup shadow VMCS, do not load it yet. */
-	*(uint32_t *)(vmx->shadow_vmcs) = vmcs_revision() | 0x80000000ul;
-	if (vmclear(vmx->shadow_vmcs_gpa))
-		return false;
+	if (!enable_evmcs) {
+		/* Load a VMCS. */
+		*(uint32_t *)(vmx->vmcs) = vmcs_revision();
+		if (vmclear(vmx->vmcs_gpa))
+			return false;
+
+		if (vmptrld(vmx->vmcs_gpa))
+			return false;
+
+		/* Setup shadow VMCS, do not load it yet. */
+		*(uint32_t *)(vmx->shadow_vmcs) =
+			vmcs_revision() | 0x80000000ul;
+		if (vmclear(vmx->shadow_vmcs_gpa))
+			return false;
+	} else {
+		if (evmcs_vmptrld(vmx->enlightened_vmcs_gpa,
+				  vmx->enlightened_vmcs))
+			return false;
+		current_evmcs->revision_id = vmcs_revision();
+	}
 
 	return true;
 }
diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
new file mode 100644
index 000000000000..92c2cfd1b182
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018, Red Hat, Inc.
+ *
+ * Tests for Enlightened VMCS, including nested guest state.
+ */
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#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 "vmx.h"
+
+#define VCPU_ID		5
+
+static bool have_nested_state;
+
+void l2_guest_code(void)
+{
+	GUEST_SYNC(6);
+
+	GUEST_SYNC(7);
+
+	/* Done, exit to L1 and never come back.  */
+	vmcall();
+}
+
+void l1_guest_code(struct vmx_pages *vmx_pages)
+{
+#define L2_GUEST_STACK_SIZE 64
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+
+	enable_vp_assist(vmx_pages->vp_assist_gpa, vmx_pages->vp_assist);
+
+	GUEST_ASSERT(vmx_pages->vmcs_gpa);
+	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+	GUEST_SYNC(3);
+	GUEST_ASSERT(load_vmcs(vmx_pages));
+	GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
+
+	GUEST_SYNC(4);
+	GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
+
+	prepare_vmcs(vmx_pages, l2_guest_code,
+		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	GUEST_SYNC(5);
+	GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
+	GUEST_ASSERT(!vmlaunch());
+	GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
+	GUEST_SYNC(8);
+	GUEST_ASSERT(!vmresume());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+	GUEST_SYNC(9);
+}
+
+void guest_code(struct vmx_pages *vmx_pages)
+{
+	GUEST_SYNC(1);
+	GUEST_SYNC(2);
+
+	if (vmx_pages)
+		l1_guest_code(vmx_pages);
+
+	GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+	struct vmx_pages *vmx_pages = NULL;
+	vm_vaddr_t vmx_pages_gva = 0;
+
+	struct kvm_regs regs1, regs2;
+	struct kvm_vm *vm;
+	struct kvm_run *run;
+	struct kvm_x86_state *state;
+	struct ucall uc;
+	int stage;
+	uint16_t evmcs_ver;
+	struct kvm_enable_cap enable_evmcs_cap = {
+		.cap = KVM_CAP_HYPERV_ENLIGHTENED_VMCS,
+		 .args[0] = (unsigned long)&evmcs_ver
+	};
+
+	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
+
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+	if (!kvm_check_cap(KVM_CAP_NESTED_STATE) ||
+	    !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) {
+		printf("capabilities not available, skipping test\n");
+		exit(KSFT_SKIP);
+	}
+
+	vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap);
+
+	run = vcpu_state(vm, VCPU_ID);
+
+	vcpu_regs_get(vm, VCPU_ID, &regs1);
+
+	vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva);
+	vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
+
+	for (stage = 1;; stage++) {
+		_vcpu_run(vm, VCPU_ID);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Unexpected exit reason: %u (%s),\n",
+			    run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		memset(&regs1, 0, sizeof(regs1));
+		vcpu_regs_get(vm, VCPU_ID, &regs1);
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_ABORT:
+			TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
+				    __FILE__, uc.args[1]);
+			/* NOT REACHED */
+		case UCALL_SYNC:
+			break;
+		case UCALL_DONE:
+			goto done;
+		default:
+			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+		}
+
+		/* UCALL_SYNC is handled here.  */
+		TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
+			    uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx",
+			    stage, (ulong)uc.args[1]);
+
+		state = vcpu_save_state(vm, VCPU_ID);
+		kvm_vm_release(vm);
+
+		/* Restore state in a new VM.  */
+		kvm_vm_restart(vm, O_RDWR);
+		vm_vcpu_add(vm, VCPU_ID, 0, 0);
+		vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+		vcpu_load_state(vm, VCPU_ID, state);
+		run = vcpu_state(vm, VCPU_ID);
+		free(state);
+
+		memset(&regs2, 0, sizeof(regs2));
+		vcpu_regs_get(vm, VCPU_ID, &regs2);
+		TEST_ASSERT(!memcmp(&regs1, &regs2, sizeof(regs2)),
+			    "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx",
+			    (ulong) regs2.rdi, (ulong) regs2.rsi);
+	}
+
+done:
+	kvm_vm_free(vm);
+}
-- 
cgit 


From 753fb2ee09345e0730e610b2ee3a01964fe22a63 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Tue, 16 Oct 2018 11:08:09 -0700
Subject: bpf: sockmap, add msg_peek tests to test_sockmap

Add tests that do a MSG_PEEK recv followed by a regular receive to
test flag support.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_sockmap.c | 167 ++++++++++++++++++++---------
 1 file changed, 115 insertions(+), 52 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 7cb69ce6dfa2..cbd1c0be8680 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -80,6 +80,7 @@ int txmsg_end;
 int txmsg_ingress;
 int txmsg_skb;
 int ktls;
+int peek_flag;
 
 static const struct option long_options[] = {
 	{"help",	no_argument,		NULL, 'h' },
@@ -102,6 +103,7 @@ static const struct option long_options[] = {
 	{"txmsg_ingress", no_argument,		&txmsg_ingress, 1 },
 	{"txmsg_skb", no_argument,		&txmsg_skb, 1 },
 	{"ktls", no_argument,			&ktls, 1 },
+	{"peek", no_argument,			&peek_flag, 1 },
 	{0, 0, NULL, 0 }
 };
 
@@ -352,33 +354,40 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt,
 	return 0;
 }
 
-static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
-		    struct msg_stats *s, bool tx,
-		    struct sockmap_options *opt)
+static void msg_free_iov(struct msghdr *msg)
 {
-	struct msghdr msg = {0};
-	int err, i, flags = MSG_NOSIGNAL;
+	int i;
+
+	for (i = 0; i < msg->msg_iovlen; i++)
+		free(msg->msg_iov[i].iov_base);
+	free(msg->msg_iov);
+	msg->msg_iov = NULL;
+	msg->msg_iovlen = 0;
+}
+
+static int msg_alloc_iov(struct msghdr *msg,
+			 int iov_count, int iov_length,
+			 bool data, bool xmit)
+{
+	unsigned char k = 0;
 	struct iovec *iov;
-	unsigned char k;
-	bool data_test = opt->data_test;
-	bool drop = opt->drop_expected;
+	int i;
 
 	iov = calloc(iov_count, sizeof(struct iovec));
 	if (!iov)
 		return errno;
 
-	k = 0;
 	for (i = 0; i < iov_count; i++) {
 		unsigned char *d = calloc(iov_length, sizeof(char));
 
 		if (!d) {
 			fprintf(stderr, "iov_count %i/%i OOM\n", i, iov_count);
-			goto out_errno;
+			goto unwind_iov;
 		}
 		iov[i].iov_base = d;
 		iov[i].iov_len = iov_length;
 
-		if (data_test && tx) {
+		if (data && xmit) {
 			int j;
 
 			for (j = 0; j < iov_length; j++)
@@ -386,9 +395,60 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		}
 	}
 
-	msg.msg_iov = iov;
-	msg.msg_iovlen = iov_count;
-	k = 0;
+	msg->msg_iov = iov;
+	msg->msg_iovlen = iov_count;
+
+	return 0;
+unwind_iov:
+	for (i--; i >= 0 ; i--)
+		free(msg->msg_iov[i].iov_base);
+	return -ENOMEM;
+}
+
+static int msg_verify_data(struct msghdr *msg, int size, int chunk_sz)
+{
+	int i, j, bytes_cnt = 0;
+	unsigned char k = 0;
+
+	for (i = 0; i < msg->msg_iovlen; i++) {
+		unsigned char *d = msg->msg_iov[i].iov_base;
+
+		for (j = 0;
+		     j < msg->msg_iov[i].iov_len && size; j++) {
+			if (d[j] != k++) {
+				fprintf(stderr,
+					"detected data corruption @iov[%i]:%i %02x != %02x, %02x ?= %02x\n",
+					i, j, d[j], k - 1, d[j+1], k);
+				return -EIO;
+			}
+			bytes_cnt++;
+			if (bytes_cnt == chunk_sz) {
+				k = 0;
+				bytes_cnt = 0;
+			}
+			size--;
+		}
+	}
+	return 0;
+}
+
+static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
+		    struct msg_stats *s, bool tx,
+		    struct sockmap_options *opt)
+{
+	struct msghdr msg = {0}, msg_peek = {0};
+	int err, i, flags = MSG_NOSIGNAL;
+	bool drop = opt->drop_expected;
+	bool data = opt->data_test;
+
+	err = msg_alloc_iov(&msg, iov_count, iov_length, data, tx);
+	if (err)
+		goto out_errno;
+	if (peek_flag) {
+		err = msg_alloc_iov(&msg_peek, iov_count, iov_length, data, tx);
+		if (err)
+			goto out_errno;
+	}
 
 	if (tx) {
 		clock_gettime(CLOCK_MONOTONIC, &s->start);
@@ -408,19 +468,12 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		}
 		clock_gettime(CLOCK_MONOTONIC, &s->end);
 	} else {
-		int slct, recv, max_fd = fd;
+		int slct, recvp = 0, recv, max_fd = fd;
 		int fd_flags = O_NONBLOCK;
 		struct timeval timeout;
 		float total_bytes;
-		int bytes_cnt = 0;
-		int chunk_sz;
 		fd_set w;
 
-		if (opt->sendpage)
-			chunk_sz = iov_length * cnt;
-		else
-			chunk_sz = iov_length * iov_count;
-
 		fcntl(fd, fd_flags);
 		total_bytes = (float)iov_count * (float)iov_length * (float)cnt;
 		err = clock_gettime(CLOCK_MONOTONIC, &s->start);
@@ -452,6 +505,19 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 				goto out_errno;
 			}
 
+			errno = 0;
+			if (peek_flag) {
+				flags |= MSG_PEEK;
+				recvp = recvmsg(fd, &msg_peek, flags);
+				if (recvp < 0) {
+					if (errno != EWOULDBLOCK) {
+						clock_gettime(CLOCK_MONOTONIC, &s->end);
+						goto out_errno;
+					}
+				}
+				flags = 0;
+			}
+
 			recv = recvmsg(fd, &msg, flags);
 			if (recv < 0) {
 				if (errno != EWOULDBLOCK) {
@@ -463,27 +529,23 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 
 			s->bytes_recvd += recv;
 
-			if (data_test) {
-				int j;
-
-				for (i = 0; i < msg.msg_iovlen; i++) {
-					unsigned char *d = iov[i].iov_base;
-
-					for (j = 0;
-					     j < iov[i].iov_len && recv; j++) {
-						if (d[j] != k++) {
-							errno = -EIO;
-							fprintf(stderr,
-								"detected data corruption @iov[%i]:%i %02x != %02x, %02x ?= %02x\n",
-								i, j, d[j], k - 1, d[j+1], k);
-							goto out_errno;
-						}
-						bytes_cnt++;
-						if (bytes_cnt == chunk_sz) {
-							k = 0;
-							bytes_cnt = 0;
-						}
-						recv--;
+			if (data) {
+				int chunk_sz = opt->sendpage ?
+						iov_length * cnt :
+						iov_length * iov_count;
+
+				errno = msg_verify_data(&msg, recv, chunk_sz);
+				if (errno) {
+					perror("data verify msg failed\n");
+					goto out_errno;
+				}
+				if (recvp) {
+					errno = msg_verify_data(&msg_peek,
+								recvp,
+								chunk_sz);
+					if (errno) {
+						perror("data verify msg_peek failed\n");
+						goto out_errno;
 					}
 				}
 			}
@@ -491,14 +553,12 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		clock_gettime(CLOCK_MONOTONIC, &s->end);
 	}
 
-	for (i = 0; i < iov_count; i++)
-		free(iov[i].iov_base);
-	free(iov);
-	return 0;
+	msg_free_iov(&msg);
+	msg_free_iov(&msg_peek);
+	return err;
 out_errno:
-	for (i = 0; i < iov_count; i++)
-		free(iov[i].iov_base);
-	free(iov);
+	msg_free_iov(&msg);
+	msg_free_iov(&msg_peek);
 	return errno;
 }
 
@@ -565,9 +625,10 @@ static int sendmsg_test(struct sockmap_options *opt)
 		}
 		if (opt->verbose)
 			fprintf(stdout,
-				"rx_sendmsg: TX: %zuB %fB/s %fGB/s RX: %zuB %fB/s %fGB/s\n",
+				"rx_sendmsg: TX: %zuB %fB/s %fGB/s RX: %zuB %fB/s %fGB/s %s\n",
 				s.bytes_sent, sent_Bps, sent_Bps/giga,
-				s.bytes_recvd, recvd_Bps, recvd_Bps/giga);
+				s.bytes_recvd, recvd_Bps, recvd_Bps/giga,
+				peek_flag ? "(peek_msg)" : "");
 		if (err && txmsg_cork)
 			err = 0;
 		exit(err ? 1 : 0);
@@ -999,6 +1060,8 @@ static void test_options(char *options)
 		strncat(options, "skb,", OPTSTRING);
 	if (ktls)
 		strncat(options, "ktls,", OPTSTRING);
+	if (peek_flag)
+		strncat(options, "peek,", OPTSTRING);
 }
 
 static int __test_exec(int cgrp, int test, struct sockmap_options *opt)
-- 
cgit 


From 0ead11181fe0c9538b185e46a494df21dc7de23a Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Wed, 26 Sep 2018 10:47:15 -0700
Subject: acpi, nfit: Collect shutdown status

Some NVDIMMs, in addition to providing an indication of whether the
previous shutdown was clean, also provide a running count of lifetime
dirty-shutdown events for the device. In anticipation of this
functionality appearing on more devices arrange for the nfit driver to
retrieve / cache this data at DIMM discovery time, and export it via
sysfs.

Reviewed-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/nfit/core.c              | 77 ++++++++++++++++++++++++++++++++++-
 drivers/acpi/nfit/intel.h             | 38 +++++++++++++++++
 drivers/acpi/nfit/nfit.h              |  3 ++
 tools/testing/nvdimm/test/nfit.c      |  1 +
 tools/testing/nvdimm/test/nfit_test.h | 24 -----------
 5 files changed, 118 insertions(+), 25 deletions(-)
 create mode 100644 drivers/acpi/nfit/intel.h

(limited to 'tools/testing')

diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 308a77b6c837..bf7021bb276c 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -25,6 +25,7 @@
 #include <asm/cacheflush.h>
 #include <acpi/nfit.h>
 #include "nfit.h"
+#include "intel.h"
 
 /*
  * For readq() and writeq() on 32-bit builds, the hi-lo, lo-hi order is
@@ -1551,7 +1552,12 @@ static DEVICE_ATTR_RO(dsm_mask);
 static ssize_t flags_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	u16 flags = to_nfit_memdev(dev)->flags;
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+	u16 flags = __to_nfit_memdev(nfit_mem)->flags;
+
+	if (test_bit(NFIT_MEM_DIRTY, &nfit_mem->flags))
+		flags |= ACPI_NFIT_MEM_FLUSH_FAILED;
 
 	return sprintf(buf, "%s%s%s%s%s%s%s\n",
 		flags & ACPI_NFIT_MEM_SAVE_FAILED ? "save_fail " : "",
@@ -1582,6 +1588,16 @@ static ssize_t id_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(id);
 
+static ssize_t dirty_shutdown_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+
+	return sprintf(buf, "%d\n", nfit_mem->dirty_shutdown);
+}
+static DEVICE_ATTR_RO(dirty_shutdown);
+
 static struct attribute *acpi_nfit_dimm_attributes[] = {
 	&dev_attr_handle.attr,
 	&dev_attr_phys_id.attr,
@@ -1599,6 +1615,7 @@ static struct attribute *acpi_nfit_dimm_attributes[] = {
 	&dev_attr_id.attr,
 	&dev_attr_family.attr,
 	&dev_attr_dsm_mask.attr,
+	&dev_attr_dirty_shutdown.attr,
 	NULL,
 };
 
@@ -1607,6 +1624,7 @@ static umode_t acpi_nfit_dimm_attr_visible(struct kobject *kobj,
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
 	struct nvdimm *nvdimm = to_nvdimm(dev);
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
 
 	if (!to_nfit_dcr(dev)) {
 		/* Without a dcr only the memdev attributes can be surfaced */
@@ -1620,6 +1638,11 @@ static umode_t acpi_nfit_dimm_attr_visible(struct kobject *kobj,
 
 	if (a == &dev_attr_format1.attr && num_nvdimm_formats(nvdimm) <= 1)
 		return 0;
+
+	if (!test_bit(NFIT_MEM_DIRTY_COUNT, &nfit_mem->flags)
+			&& a == &dev_attr_dirty_shutdown.attr)
+		return 0;
+
 	return a->mode;
 }
 
@@ -1698,6 +1721,56 @@ static bool acpi_nvdimm_has_method(struct acpi_device *adev, char *method)
 	return false;
 }
 
+static void nfit_intel_shutdown_status(struct nfit_mem *nfit_mem)
+{
+	struct nd_intel_smart smart = { 0 };
+	union acpi_object in_buf = {
+		.type = ACPI_TYPE_BUFFER,
+		.buffer.pointer = (char *) &smart,
+		.buffer.length = sizeof(smart),
+	};
+	union acpi_object in_obj = {
+		.type = ACPI_TYPE_PACKAGE,
+		.package.count = 1,
+		.package.elements = &in_buf,
+	};
+	const u8 func = ND_INTEL_SMART;
+	const guid_t *guid = to_nfit_uuid(nfit_mem->family);
+	u8 revid = nfit_dsm_revid(nfit_mem->family, func);
+	struct acpi_device *adev = nfit_mem->adev;
+	acpi_handle handle = adev->handle;
+	union acpi_object *out_obj;
+
+	if ((nfit_mem->dsm_mask & (1 << func)) == 0)
+		return;
+
+	out_obj = acpi_evaluate_dsm(handle, guid, revid, func, &in_obj);
+	if (!out_obj)
+		return;
+
+	if (smart.flags & ND_INTEL_SMART_SHUTDOWN_VALID) {
+		if (smart.shutdown_state)
+			set_bit(NFIT_MEM_DIRTY, &nfit_mem->flags);
+	}
+
+	if (smart.flags & ND_INTEL_SMART_SHUTDOWN_COUNT_VALID) {
+		set_bit(NFIT_MEM_DIRTY_COUNT, &nfit_mem->flags);
+		nfit_mem->dirty_shutdown = smart.shutdown_count;
+	}
+	ACPI_FREE(out_obj);
+}
+
+static void populate_shutdown_status(struct nfit_mem *nfit_mem)
+{
+	/*
+	 * For DIMMs that provide a dynamic facility to retrieve a
+	 * dirty-shutdown status and/or a dirty-shutdown count, cache
+	 * these values in nfit_mem.
+	 */
+	if (nfit_mem->family == NVDIMM_FAMILY_INTEL)
+		nfit_intel_shutdown_status(nfit_mem);
+}
+
 static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_mem *nfit_mem, u32 device_handle)
 {
@@ -1797,6 +1870,8 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 		set_bit(NFIT_MEM_LSW, &nfit_mem->flags);
 	}
 
+	populate_shutdown_status(nfit_mem);
+
 	return 0;
 }
 
diff --git a/drivers/acpi/nfit/intel.h b/drivers/acpi/nfit/intel.h
new file mode 100644
index 000000000000..86746312381f
--- /dev/null
+++ b/drivers/acpi/nfit/intel.h
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright(c) 2018 Intel Corporation. All rights reserved.
+ * Intel specific definitions for NVDIMM Firmware Interface Table - NFIT
+ */
+#ifndef _NFIT_INTEL_H_
+#define _NFIT_INTEL_H_
+
+#define ND_INTEL_SMART 1
+
+#define ND_INTEL_SMART_SHUTDOWN_COUNT_VALID     (1 << 5)
+#define ND_INTEL_SMART_SHUTDOWN_VALID           (1 << 10)
+
+struct nd_intel_smart {
+	u32 status;
+	union {
+		struct {
+			u32 flags;
+			u8 reserved0[4];
+			u8 health;
+			u8 spares;
+			u8 life_used;
+			u8 alarm_flags;
+			u16 media_temperature;
+			u16 ctrl_temperature;
+			u32 shutdown_count;
+			u8 ait_status;
+			u16 pmic_temperature;
+			u8 reserved1[8];
+			u8 shutdown_state;
+			u32 vendor_size;
+			u8 vendor_data[92];
+		} __packed;
+		u8 data[128];
+	};
+} __packed;
+
+#endif
diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h
index 111c3c437c80..af73aec547f2 100644
--- a/drivers/acpi/nfit/nfit.h
+++ b/drivers/acpi/nfit/nfit.h
@@ -162,6 +162,8 @@ struct nfit_memdev {
 enum nfit_mem_flags {
 	NFIT_MEM_LSR,
 	NFIT_MEM_LSW,
+	NFIT_MEM_DIRTY,
+	NFIT_MEM_DIRTY_COUNT,
 };
 
 /* assembled tables for a given dimm/memory-device */
@@ -184,6 +186,7 @@ struct nfit_mem {
 	struct resource *flush_wpq;
 	unsigned long dsm_mask;
 	unsigned long flags;
+	u32 dirty_shutdown;
 	int family;
 };
 
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index cffc2c5a778d..f1a2a1a7bb1b 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -24,6 +24,7 @@
 #include <linux/list.h>
 #include <linux/slab.h>
 #include <nd-core.h>
+#include <intel.h>
 #include <nfit.h>
 #include <nd.h>
 #include "nfit_test.h"
diff --git a/tools/testing/nvdimm/test/nfit_test.h b/tools/testing/nvdimm/test/nfit_test.h
index 33752e06ff8d..ade14fe3837e 100644
--- a/tools/testing/nvdimm/test/nfit_test.h
+++ b/tools/testing/nvdimm/test/nfit_test.h
@@ -117,30 +117,6 @@ struct nd_cmd_ars_err_inj_stat {
 #define ND_INTEL_SMART_INJECT_FATAL		(1 << 2)
 #define ND_INTEL_SMART_INJECT_SHUTDOWN		(1 << 3)
 
-struct nd_intel_smart {
-	__u32 status;
-	union {
-		struct {
-			__u32 flags;
-			__u8 reserved0[4];
-			__u8 health;
-			__u8 spares;
-			__u8 life_used;
-			__u8 alarm_flags;
-			__u16 media_temperature;
-			__u16 ctrl_temperature;
-			__u32 shutdown_count;
-			__u8 ait_status;
-			__u16 pmic_temperature;
-			__u8 reserved1[8];
-			__u8 shutdown_state;
-			__u32 vendor_size;
-			__u8 vendor_data[92];
-		} __packed;
-		__u8 data[128];
-	};
-} __packed;
-
 struct nd_intel_smart_threshold {
 	__u32 status;
 	union {
-- 
cgit 


From f110176633d74bbac1f80ab9b9c6b83ea3e1cc23 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Wed, 17 Oct 2018 10:47:19 -0700
Subject: tools/testing/nvdimm: Populate dirty shutdown data

Allow the unit tests to verify the retrieval of the dirty shutdown
count via smart commands, and allow the driver-load-time retrieval of
the smart health payload to be simulated by nfit_test.

Reviewed-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/nfit/core.c              | 7 +++++--
 tools/testing/nvdimm/Kbuild           | 1 +
 tools/testing/nvdimm/acpi_nfit_test.c | 8 ++++++++
 tools/testing/nvdimm/test/nfit.c      | 3 ++-
 4 files changed, 16 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index bf7021bb276c..ec8fb578fa36 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -1721,7 +1721,7 @@ static bool acpi_nvdimm_has_method(struct acpi_device *adev, char *method)
 	return false;
 }
 
-static void nfit_intel_shutdown_status(struct nfit_mem *nfit_mem)
+__weak void nfit_intel_shutdown_status(struct nfit_mem *nfit_mem)
 {
 	struct nd_intel_smart smart = { 0 };
 	union acpi_object in_buf = {
@@ -1785,8 +1785,11 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 	nfit_mem->dsm_mask = acpi_desc->dimm_cmd_force_en;
 	nfit_mem->family = NVDIMM_FAMILY_INTEL;
 	adev = to_acpi_dev(acpi_desc);
-	if (!adev)
+	if (!adev) {
+		/* unit test case */
+		populate_shutdown_status(nfit_mem);
 		return 0;
+	}
 
 	adev_dimm = acpi_find_child_device(adev, device_handle, false);
 	nfit_mem->adev = adev_dimm;
diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild
index 0392153a0009..778ceb651000 100644
--- a/tools/testing/nvdimm/Kbuild
+++ b/tools/testing/nvdimm/Kbuild
@@ -22,6 +22,7 @@ NVDIMM_SRC := $(DRIVERS)/nvdimm
 ACPI_SRC := $(DRIVERS)/acpi/nfit
 DAX_SRC := $(DRIVERS)/dax
 ccflags-y := -I$(src)/$(NVDIMM_SRC)/
+ccflags-y += -I$(src)/$(ACPI_SRC)/
 
 obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o
 obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o
diff --git a/tools/testing/nvdimm/acpi_nfit_test.c b/tools/testing/nvdimm/acpi_nfit_test.c
index 43521512e577..fec8fb1b7715 100644
--- a/tools/testing/nvdimm/acpi_nfit_test.c
+++ b/tools/testing/nvdimm/acpi_nfit_test.c
@@ -4,5 +4,13 @@
 #include <linux/module.h>
 #include <linux/printk.h>
 #include "watermark.h"
+#include <nfit.h>
 
 nfit_test_watermark(acpi_nfit);
+
+/* strong / override definition of nfit_intel_shutdown_status */
+void nfit_intel_shutdown_status(struct nfit_mem *nfit_mem)
+{
+	set_bit(NFIT_MEM_DIRTY_COUNT, &nfit_mem->flags);
+	nfit_mem->dirty_shutdown = 42;
+}
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index f1a2a1a7bb1b..9527d47a1070 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -149,6 +149,7 @@ static const struct nd_intel_smart smart_def = {
 		| ND_INTEL_SMART_ALARM_VALID
 		| ND_INTEL_SMART_USED_VALID
 		| ND_INTEL_SMART_SHUTDOWN_VALID
+		| ND_INTEL_SMART_SHUTDOWN_COUNT_VALID
 		| ND_INTEL_SMART_MTEMP_VALID
 		| ND_INTEL_SMART_CTEMP_VALID,
 	.health = ND_INTEL_SMART_NON_CRITICAL_HEALTH,
@@ -161,8 +162,8 @@ static const struct nd_intel_smart smart_def = {
 	.ait_status = 1,
 	.life_used = 5,
 	.shutdown_state = 0,
+	.shutdown_count = 42,
 	.vendor_size = 0,
-	.shutdown_count = 100,
 };
 
 struct nfit_test_fw {
-- 
cgit 


From 1bd70d2eba9d90eb787634361f0f6fa2c86b3f6d Mon Sep 17 00:00:00 2001
From: Peng Hao <peng.hao2@zte.com.cn>
Date: Thu, 18 Oct 2018 23:18:36 +0800
Subject: selftests/bpf: fix file resource leak in load_kallsyms

FILE pointer variable f is opened but never closed.

Signed-off-by: Peng Hao <peng.hao2@zte.com.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/trace_helpers.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index cabe2a3a3b30..a3d1dace4a75 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -41,6 +41,7 @@ int load_kallsyms(void)
 		syms[i].name = strdup(func);
 		i++;
 	}
+	fclose(f);
 	sym_cnt = i;
 	qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp);
 	return 0;
-- 
cgit 


From f15ac811e80b857a443476de60ce70d3e6049ae5 Mon Sep 17 00:00:00 2001
From: Anders Roxell <anders.roxell@linaro.org>
Date: Fri, 19 Oct 2018 16:38:16 +0200
Subject: selftests/kvm: add missing executables to .gitignore

Fixes: 18178ff86217 ("KVM: selftests: add Enlightened VMCS test")
Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/.gitignore | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 552b0d9a49f4..6210ba41c29e 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,4 +1,5 @@
 /x86_64/cr4_cpuid_sync_test
+/x86_64/evmcs_test
 /x86_64/platform_info_test
 /x86_64/set_sregs_test
 /x86_64/sync_regs_test
-- 
cgit 


From 43b987d23d6bd08db41a9c4a85aacfb3f0b2a94c Mon Sep 17 00:00:00 2001
From: Mauricio Vasquez B <mauricio.vasquez@polito.it>
Date: Thu, 18 Oct 2018 15:16:41 +0200
Subject: selftests/bpf: add test cases for queue and stack maps

test_maps:
Tests that queue/stack maps are behaving correctly even in corner cases

test_progs:
Tests new ebpf helpers

Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c                                |  12 ++
 tools/lib/bpf/bpf.h                                |   2 +
 tools/testing/selftests/bpf/Makefile               |   5 +-
 tools/testing/selftests/bpf/bpf_helpers.h          |   7 ++
 tools/testing/selftests/bpf/test_maps.c            | 122 +++++++++++++++++++++
 tools/testing/selftests/bpf/test_progs.c           |  99 +++++++++++++++++
 tools/testing/selftests/bpf/test_queue_map.c       |   4 +
 tools/testing/selftests/bpf/test_queue_stack_map.h |  59 ++++++++++
 tools/testing/selftests/bpf/test_stack_map.c       |   4 +
 9 files changed, 313 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/test_queue_map.c
 create mode 100644 tools/testing/selftests/bpf/test_queue_stack_map.h
 create mode 100644 tools/testing/selftests/bpf/test_stack_map.c

(limited to 'tools/testing')

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index d70a255cb05e..03f9bcc4ef50 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -278,6 +278,18 @@ int bpf_map_lookup_elem(int fd, const void *key, void *value)
 	return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
 }
 
+int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.map_fd = fd;
+	attr.key = ptr_to_u64(key);
+	attr.value = ptr_to_u64(value);
+
+	return sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr));
+}
+
 int bpf_map_delete_elem(int fd, const void *key)
 {
 	union bpf_attr attr;
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 258c3c178333..26a51538213c 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -99,6 +99,8 @@ LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value,
 				   __u64 flags);
 
 LIBBPF_API int bpf_map_lookup_elem(int fd, const void *key, void *value);
+LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key,
+					      void *value);
 LIBBPF_API int bpf_map_delete_elem(int fd, const void *key);
 LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key);
 LIBBPF_API int bpf_obj_pin(int fd, const char *pathname);
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index d99dd6fc3fbe..e39dfb4e7970 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -37,7 +37,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
 	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
 	test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o \
-	test_sk_lookup_kern.o test_xdp_vlan.o
+	test_sk_lookup_kern.o test_xdp_vlan.o test_queue_map.o test_stack_map.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
@@ -118,6 +118,9 @@ CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \
 $(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline
 $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline
 
+$(OUTPUT)/test_queue_map.o: test_queue_stack_map.h
+$(OUTPUT)/test_stack_map.o: test_queue_stack_map.h
+
 BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
 BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
 BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm')
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index fda8c162d0df..6407a3df0f3b 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -16,6 +16,13 @@ static int (*bpf_map_update_elem)(void *map, void *key, void *value,
 	(void *) BPF_FUNC_map_update_elem;
 static int (*bpf_map_delete_elem)(void *map, void *key) =
 	(void *) BPF_FUNC_map_delete_elem;
+static int (*bpf_map_push_elem)(void *map, void *value,
+				unsigned long long flags) =
+	(void *) BPF_FUNC_map_push_elem;
+static int (*bpf_map_pop_elem)(void *map, void *value) =
+	(void *) BPF_FUNC_map_pop_elem;
+static int (*bpf_map_peek_elem)(void *map, void *value) =
+	(void *) BPF_FUNC_map_peek_elem;
 static int (*bpf_probe_read)(void *dst, int size, void *unsafe_ptr) =
 	(void *) BPF_FUNC_probe_read;
 static unsigned long long (*bpf_ktime_get_ns)(void) =
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 9b552c0fc47d..4db2116e52be 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -15,6 +15,7 @@
 #include <string.h>
 #include <assert.h>
 #include <stdlib.h>
+#include <time.h>
 
 #include <sys/wait.h>
 #include <sys/socket.h>
@@ -471,6 +472,122 @@ static void test_devmap(int task, void *data)
 	close(fd);
 }
 
+static void test_queuemap(int task, void *data)
+{
+	const int MAP_SIZE = 32;
+	__u32 vals[MAP_SIZE + MAP_SIZE/2], val;
+	int fd, i;
+
+	/* Fill test values to be used */
+	for (i = 0; i < MAP_SIZE + MAP_SIZE/2; i++)
+		vals[i] = rand();
+
+	/* Invalid key size */
+	fd = bpf_create_map(BPF_MAP_TYPE_QUEUE, 4, sizeof(val), MAP_SIZE,
+			    map_flags);
+	assert(fd < 0 && errno == EINVAL);
+
+	fd = bpf_create_map(BPF_MAP_TYPE_QUEUE, 0, sizeof(val), MAP_SIZE,
+			    map_flags);
+	/* Queue map does not support BPF_F_NO_PREALLOC */
+	if (map_flags & BPF_F_NO_PREALLOC) {
+		assert(fd < 0 && errno == EINVAL);
+		return;
+	}
+	if (fd < 0) {
+		printf("Failed to create queuemap '%s'!\n", strerror(errno));
+		exit(1);
+	}
+
+	/* Push MAP_SIZE elements */
+	for (i = 0; i < MAP_SIZE; i++)
+		assert(bpf_map_update_elem(fd, NULL, &vals[i], 0) == 0);
+
+	/* Check that element cannot be pushed due to max_entries limit */
+	assert(bpf_map_update_elem(fd, NULL, &val, 0) == -1 &&
+	       errno == E2BIG);
+
+	/* Peek element */
+	assert(bpf_map_lookup_elem(fd, NULL, &val) == 0 && val == vals[0]);
+
+	/* Replace half elements */
+	for (i = MAP_SIZE; i < MAP_SIZE + MAP_SIZE/2; i++)
+		assert(bpf_map_update_elem(fd, NULL, &vals[i], BPF_EXIST) == 0);
+
+	/* Pop all elements */
+	for (i = MAP_SIZE/2; i < MAP_SIZE + MAP_SIZE/2; i++)
+		assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) == 0 &&
+		       val == vals[i]);
+
+	/* Check that there are not elements left */
+	assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) == -1 &&
+	       errno == ENOENT);
+
+	/* Check that non supported functions set errno to EINVAL */
+	assert(bpf_map_delete_elem(fd, NULL) == -1 && errno == EINVAL);
+	assert(bpf_map_get_next_key(fd, NULL, NULL) == -1 && errno == EINVAL);
+
+	close(fd);
+}
+
+static void test_stackmap(int task, void *data)
+{
+	const int MAP_SIZE = 32;
+	__u32 vals[MAP_SIZE + MAP_SIZE/2], val;
+	int fd, i;
+
+	/* Fill test values to be used */
+	for (i = 0; i < MAP_SIZE + MAP_SIZE/2; i++)
+		vals[i] = rand();
+
+	/* Invalid key size */
+	fd = bpf_create_map(BPF_MAP_TYPE_STACK, 4, sizeof(val), MAP_SIZE,
+			    map_flags);
+	assert(fd < 0 && errno == EINVAL);
+
+	fd = bpf_create_map(BPF_MAP_TYPE_STACK, 0, sizeof(val), MAP_SIZE,
+			    map_flags);
+	/* Stack map does not support BPF_F_NO_PREALLOC */
+	if (map_flags & BPF_F_NO_PREALLOC) {
+		assert(fd < 0 && errno == EINVAL);
+		return;
+	}
+	if (fd < 0) {
+		printf("Failed to create stackmap '%s'!\n", strerror(errno));
+		exit(1);
+	}
+
+	/* Push MAP_SIZE elements */
+	for (i = 0; i < MAP_SIZE; i++)
+		assert(bpf_map_update_elem(fd, NULL, &vals[i], 0) == 0);
+
+	/* Check that element cannot be pushed due to max_entries limit */
+	assert(bpf_map_update_elem(fd, NULL, &val, 0) == -1 &&
+	       errno == E2BIG);
+
+	/* Peek element */
+	assert(bpf_map_lookup_elem(fd, NULL, &val) == 0 && val == vals[i - 1]);
+
+	/* Replace half elements */
+	for (i = MAP_SIZE; i < MAP_SIZE + MAP_SIZE/2; i++)
+		assert(bpf_map_update_elem(fd, NULL, &vals[i], BPF_EXIST) == 0);
+
+	/* Pop all elements */
+	for (i = MAP_SIZE + MAP_SIZE/2 - 1; i >= MAP_SIZE/2; i--)
+		assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) == 0 &&
+		       val == vals[i]);
+
+	/* Check that there are not elements left */
+	assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) == -1 &&
+	       errno == ENOENT);
+
+	/* Check that non supported functions set errno to EINVAL */
+	assert(bpf_map_delete_elem(fd, NULL) == -1 && errno == EINVAL);
+	assert(bpf_map_get_next_key(fd, NULL, NULL) == -1 && errno == EINVAL);
+
+	close(fd);
+}
+
 #include <sys/socket.h>
 #include <sys/ioctl.h>
 #include <arpa/inet.h>
@@ -1434,10 +1551,15 @@ static void run_all_tests(void)
 	test_map_wronly();
 
 	test_reuseport_array();
+
+	test_queuemap(0, NULL);
+	test_stackmap(0, NULL);
 }
 
 int main(void)
 {
+	srand(time(NULL));
+
 	map_flags = 0;
 	run_all_tests();
 
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index e8becca9c521..2d3c04f45530 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -1735,8 +1735,105 @@ static void test_reference_tracking()
 	bpf_object__close(obj);
 }
 
+enum {
+	QUEUE,
+	STACK,
+};
+
+static void test_queue_stack_map(int type)
+{
+	const int MAP_SIZE = 32;
+	__u32 vals[MAP_SIZE], duration, retval, size, val;
+	int i, err, prog_fd, map_in_fd, map_out_fd;
+	char file[32], buf[128];
+	struct bpf_object *obj;
+	struct iphdr *iph = (void *)buf + sizeof(struct ethhdr);
+
+	/* Fill test values to be used */
+	for (i = 0; i < MAP_SIZE; i++)
+		vals[i] = rand();
+
+	if (type == QUEUE)
+		strncpy(file, "./test_queue_map.o", sizeof(file));
+	else if (type == STACK)
+		strncpy(file, "./test_stack_map.o", sizeof(file));
+	else
+		return;
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd);
+	if (err) {
+		error_cnt++;
+		return;
+	}
+
+	map_in_fd = bpf_find_map(__func__, obj, "map_in");
+	if (map_in_fd < 0)
+		goto out;
+
+	map_out_fd = bpf_find_map(__func__, obj, "map_out");
+	if (map_out_fd < 0)
+		goto out;
+
+	/* Push 32 elements to the input map */
+	for (i = 0; i < MAP_SIZE; i++) {
+		err = bpf_map_update_elem(map_in_fd, NULL, &vals[i], 0);
+		if (err) {
+			error_cnt++;
+			goto out;
+		}
+	}
+
+	/* The eBPF program pushes iph.saddr in the output map,
+	 * pops the input map and saves this value in iph.daddr
+	 */
+	for (i = 0; i < MAP_SIZE; i++) {
+		if (type == QUEUE) {
+			val = vals[i];
+			pkt_v4.iph.saddr = vals[i] * 5;
+		} else if (type == STACK) {
+			val = vals[MAP_SIZE - 1 - i];
+			pkt_v4.iph.saddr = vals[MAP_SIZE - 1 - i] * 5;
+		}
+
+		err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+					buf, &size, &retval, &duration);
+		if (err || retval || size != sizeof(pkt_v4) ||
+		    iph->daddr != val)
+			break;
+	}
+
+	CHECK(err || retval || size != sizeof(pkt_v4) || iph->daddr != val,
+	      "bpf_map_pop_elem",
+	      "err %d errno %d retval %d size %d iph->daddr %u\n",
+	      err, errno, retval, size, iph->daddr);
+
+	/* Queue is empty, program should return TC_ACT_SHOT */
+	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+				buf, &size, &retval, &duration);
+	CHECK(err || retval != 2 /* TC_ACT_SHOT */|| size != sizeof(pkt_v4),
+	      "check-queue-stack-map-empty",
+	      "err %d errno %d retval %d size %d\n",
+	      err, errno, retval, size);
+
+	/* Check that the program pushed elements correctly */
+	for (i = 0; i < MAP_SIZE; i++) {
+		err = bpf_map_lookup_and_delete_elem(map_out_fd, NULL, &val);
+		if (err || val != vals[i] * 5)
+			break;
+	}
+
+	CHECK(i != MAP_SIZE && (err || val != vals[i] * 5),
+	      "bpf_map_push_elem", "err %d value %u\n", err, val);
+
+out:
+	pkt_v4.iph.saddr = 0;
+	bpf_object__close(obj);
+}
+
 int main(void)
 {
+	srand(time(NULL));
+
 	jit_enabled = is_jit_enabled();
 
 	test_pkt_access();
@@ -1757,6 +1854,8 @@ int main(void)
 	test_task_fd_query_rawtp();
 	test_task_fd_query_tp();
 	test_reference_tracking();
+	test_queue_stack_map(QUEUE);
+	test_queue_stack_map(STACK);
 
 	printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
 	return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS;
diff --git a/tools/testing/selftests/bpf/test_queue_map.c b/tools/testing/selftests/bpf/test_queue_map.c
new file mode 100644
index 000000000000..87db1f9da33d
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_queue_map.c
@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Politecnico di Torino
+#define MAP_TYPE BPF_MAP_TYPE_QUEUE
+#include "test_queue_stack_map.h"
diff --git a/tools/testing/selftests/bpf/test_queue_stack_map.h b/tools/testing/selftests/bpf/test_queue_stack_map.h
new file mode 100644
index 000000000000..295b9b3bc5c7
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_queue_stack_map.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (c) 2018 Politecnico di Torino
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/pkt_cls.h>
+#include "bpf_helpers.h"
+
+int _version SEC("version") = 1;
+
+struct bpf_map_def __attribute__ ((section("maps"), used)) map_in = {
+	.type = MAP_TYPE,
+	.key_size = 0,
+	.value_size = sizeof(__u32),
+	.max_entries = 32,
+	.map_flags = 0,
+};
+
+struct bpf_map_def __attribute__ ((section("maps"), used)) map_out = {
+	.type = MAP_TYPE,
+	.key_size = 0,
+	.value_size = sizeof(__u32),
+	.max_entries = 32,
+	.map_flags = 0,
+};
+
+SEC("test")
+int _test(struct __sk_buff *skb)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *data = (void *)(long)skb->data;
+	struct ethhdr *eth = (struct ethhdr *)(data);
+	__u32 value;
+	int err;
+
+	if (eth + 1 > data_end)
+		return TC_ACT_SHOT;
+
+	struct iphdr *iph = (struct iphdr *)(eth + 1);
+
+	if (iph + 1 > data_end)
+		return TC_ACT_SHOT;
+
+	err = bpf_map_pop_elem(&map_in, &value);
+	if (err)
+		return TC_ACT_SHOT;
+
+	iph->daddr = value;
+
+	err = bpf_map_push_elem(&map_out, &iph->saddr, 0);
+	if (err)
+		return TC_ACT_SHOT;
+
+	return TC_ACT_OK;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_stack_map.c b/tools/testing/selftests/bpf/test_stack_map.c
new file mode 100644
index 000000000000..31c3880e6da0
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_stack_map.c
@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Politecnico di Torino
+#define MAP_TYPE BPF_MAP_TYPE_STACK
+#include "test_queue_stack_map.h"
-- 
cgit 


From 78de35460a5cc206d42a239cb215c966a83ac283 Mon Sep 17 00:00:00 2001
From: Anders Roxell <anders.roxell@linaro.org>
Date: Fri, 19 Oct 2018 16:24:36 +0200
Subject: selftests/bpf: add missing executables to .gitignore

Fixes: 371e4fcc9d96 ("selftests/bpf: cgroup local storage-based network counters")
Fixes: 370920c47b26 ("selftests/bpf: Test libbpf_{prog,attach}_type_by_name")
Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/.gitignore | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 8a60c9b9892d..1b799e30c06d 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -25,3 +25,5 @@ test_cgroup_storage
 test_select_reuseport
 test_flow_dissector
 flow_dissector_load
+test_netcnt
+test_section_names
-- 
cgit 


From 2cb494a36c98279c5c6ce8e99cf9776f15449ade Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Fri, 19 Oct 2018 09:57:58 -0700
Subject: bpf: add tests for direct packet access from CGROUP_SKB

Tests are added to make sure CGROUP_SKB cannot access:
  tc_classid, data_meta, flow_keys

and can read and write:
  mark, prority, and cb[0-4]

and can read other fields.

To make selftest with skb->sk work, a dummy sk is added in
bpf_prog_test_run_skb().

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/bpf/test_run.c                          |  15 +++
 tools/testing/selftests/bpf/test_verifier.c | 171 ++++++++++++++++++++++++++++
 2 files changed, 186 insertions(+)

(limited to 'tools/testing')

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 0c423b8cd75c..c89c22c49015 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -10,6 +10,8 @@
 #include <linux/etherdevice.h>
 #include <linux/filter.h>
 #include <linux/sched/signal.h>
+#include <net/sock.h>
+#include <net/tcp.h>
 
 static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx,
 		struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE])
@@ -115,6 +117,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	u32 retval, duration;
 	int hh_len = ETH_HLEN;
 	struct sk_buff *skb;
+	struct sock *sk;
 	void *data;
 	int ret;
 
@@ -137,11 +140,21 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 		break;
 	}
 
+	sk = kzalloc(sizeof(struct sock), GFP_USER);
+	if (!sk) {
+		kfree(data);
+		return -ENOMEM;
+	}
+	sock_net_set(sk, current->nsproxy->net_ns);
+	sock_init_data(NULL, sk);
+
 	skb = build_skb(data, 0);
 	if (!skb) {
 		kfree(data);
+		kfree(sk);
 		return -ENOMEM;
 	}
+	skb->sk = sk;
 
 	skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
 	__skb_put(skb, size);
@@ -159,6 +172,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 
 			if (pskb_expand_head(skb, nhead, 0, GFP_USER)) {
 				kfree_skb(skb);
+				kfree(sk);
 				return -ENOMEM;
 			}
 		}
@@ -171,6 +185,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 		size = skb_headlen(skb);
 	ret = bpf_test_finish(kattr, uattr, skb->data, size, retval, duration);
 	kfree_skb(skb);
+	kfree(sk);
 	return ret;
 }
 
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index cf4cd32b6772..f1ae8d09770f 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -4862,6 +4862,177 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
+	{
+		"direct packet read test#1 for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct __sk_buff, len)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, pkt_type)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct __sk_buff, queue_mapping)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+				    offsetof(struct __sk_buff, protocol)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
+				    offsetof(struct __sk_buff, vlan_present)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"direct packet read test#2 for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct __sk_buff, vlan_tci)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, vlan_proto)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, priority)),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				    offsetof(struct __sk_buff, priority)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct __sk_buff,
+					     ingress_ifindex)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+				    offsetof(struct __sk_buff, tc_index)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
+				    offsetof(struct __sk_buff, hash)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"direct packet read test#3 for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[0])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[1])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[2])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[3])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[4])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
+				    offsetof(struct __sk_buff, napi_id)),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_4,
+				    offsetof(struct __sk_buff, cb[0])),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_5,
+				    offsetof(struct __sk_buff, cb[1])),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				    offsetof(struct __sk_buff, cb[2])),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_7,
+				    offsetof(struct __sk_buff, cb[3])),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_8,
+				    offsetof(struct __sk_buff, cb[4])),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"direct packet read test#4 for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, family)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_ip4)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_ip4)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_ip6[0])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_ip6[1])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_ip6[2])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_ip6[3])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_ip6[0])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_ip6[1])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_ip6[2])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_ip6[3])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_port)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_port)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid access of tc_classid for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, tc_classid)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid bpf_context access",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid access of data_meta for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_meta)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid bpf_context access",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid access of flow_keys for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, flow_keys)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid bpf_context access",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid write access to napi_id for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
+				    offsetof(struct __sk_buff, napi_id)),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_9,
+				    offsetof(struct __sk_buff, napi_id)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid bpf_context access",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
 	{
 		"valid cgroup storage access",
 		.insns = {
-- 
cgit 


From ba0e41ca81b935b958006c7120466e2217357827 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 18 Oct 2018 22:13:02 +0900
Subject: selftests: ftrace: Add synthetic event syntax testcase

Add a testcase to check the syntax and field types for
synthetic_events interface.

Link: http://lkml.kernel.org/r/153986838264.18251.16627517536956299922.stgit@devbox

Acked-by: Shuah Khan <shuah@kernel.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 .../inter-event/trigger-synthetic-event-syntax.tc  | 80 ++++++++++++++++++++++
 1 file changed, 80 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-syntax.tc

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-syntax.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-syntax.tc
new file mode 100644
index 000000000000..88e6c3f43006
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-syntax.tc
@@ -0,0 +1,80 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: event trigger - test synthetic_events syntax parser
+
+do_reset() {
+    reset_trigger
+    echo > set_event
+    clear_trace
+}
+
+fail() { #msg
+    do_reset
+    echo $1
+    exit_fail
+}
+
+if [ ! -f set_event ]; then
+    echo "event tracing is not supported"
+    exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+    echo "synthetic event is not supported"
+    exit_unsupported
+fi
+
+reset_tracer
+do_reset
+
+echo "Test synthetic_events syntax parser"
+
+echo > synthetic_events
+
+# synthetic event must have a field
+! echo "myevent" >> synthetic_events
+echo "myevent u64 var1" >> synthetic_events
+
+# synthetic event must be found in synthetic_events
+grep "myevent[[:space:]]u64 var1" synthetic_events
+
+# it is not possible to add same name event
+! echo "myevent u64 var2" >> synthetic_events
+
+# Non-append open will cleanup all events and add new one
+echo "myevent u64 var2" > synthetic_events
+
+# multiple fields with different spaces
+echo "myevent u64 var1; u64 var2;" > synthetic_events
+grep "myevent[[:space:]]u64 var1; u64 var2" synthetic_events
+echo "myevent u64 var1 ; u64 var2 ;" > synthetic_events
+grep "myevent[[:space:]]u64 var1; u64 var2" synthetic_events
+echo "myevent u64 var1 ;u64 var2" > synthetic_events
+grep "myevent[[:space:]]u64 var1; u64 var2" synthetic_events
+
+# test field types
+echo "myevent u32 var" > synthetic_events
+echo "myevent u16 var" > synthetic_events
+echo "myevent u8 var" > synthetic_events
+echo "myevent s64 var" > synthetic_events
+echo "myevent s32 var" > synthetic_events
+echo "myevent s16 var" > synthetic_events
+echo "myevent s8 var" > synthetic_events
+
+echo "myevent char var" > synthetic_events
+echo "myevent int var" > synthetic_events
+echo "myevent long var" > synthetic_events
+echo "myevent pid_t var" > synthetic_events
+
+echo "myevent unsigned char var" > synthetic_events
+echo "myevent unsigned int var" > synthetic_events
+echo "myevent unsigned long var" > synthetic_events
+grep "myevent[[:space:]]unsigned long var" synthetic_events
+
+# test string type
+echo "myevent char var[10]" > synthetic_events
+grep "myevent[[:space:]]char\[10\] var" synthetic_events
+
+do_reset
+
+exit 0
-- 
cgit 


From db3848515aff369404c31ef5a63699799913518f Mon Sep 17 00:00:00 2001
From: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
Date: Mon, 21 May 2018 20:43:56 +0530
Subject: selftests/powerpc: Move UCONTEXT_NIA() into utils.h

... so that it can be used by others.

Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/include/utils.h                   | 8 ++++++++
 .../testing/selftests/powerpc/primitives/load_unaligned_zeropad.c | 8 --------
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h
index c58c370828b4..da1b963cdb32 100644
--- a/tools/testing/selftests/powerpc/include/utils.h
+++ b/tools/testing/selftests/powerpc/include/utils.h
@@ -80,4 +80,12 @@ do {								\
 #define PPC_FEATURE2_ARCH_3_00 0x00800000
 #endif
 
+#if defined(__powerpc64__)
+#define UCONTEXT_NIA(UC)	(UC)->uc_mcontext.gp_regs[PT_NIP]
+#elif defined(__powerpc__)
+#define UCONTEXT_NIA(UC)	(UC)->uc_mcontext.uc_regs->gregs[PT_NIP]
+#else
+#error implement UCONTEXT_NIA
+#endif
+
 #endif /* _SELFTESTS_POWERPC_UTILS_H */
diff --git a/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c b/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c
index ed3239bbfae2..ee1e9ca22f0d 100644
--- a/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c
+++ b/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c
@@ -65,14 +65,6 @@ static int unprotect_region(void)
 extern char __start___ex_table[];
 extern char __stop___ex_table[];
 
-#if defined(__powerpc64__)
-#define UCONTEXT_NIA(UC)	(UC)->uc_mcontext.gp_regs[PT_NIP]
-#elif defined(__powerpc__)
-#define UCONTEXT_NIA(UC)	(UC)->uc_mcontext.uc_regs->gregs[PT_NIP]
-#else
-#error implement UCONTEXT_NIA
-#endif
-
 struct extbl_entry {
 	int insn;
 	int fixup;
-- 
cgit 


From d2bf793237b3aa9c4275a466eef3893eef593691 Mon Sep 17 00:00:00 2001
From: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
Date: Mon, 21 May 2018 20:43:57 +0530
Subject: selftests/powerpc: Add test to verify rfi flush across a system call

This adds a test to verify proper functioning of the rfi flush
capability implemented to mitigate meltdown. The test works by
measuring the number of L1d cache misses encountered while loading
data from memory. Across a system call, since the L1d cache is flushed
when rfi_flush is enabled, the number of cache misses is expected to
be relative to the number of cachelines corresponding to the data
being loaded.

The current system setting is reflected via powerpc/rfi_flush under
debugfs (assumed to be /sys/kernel/debug/). This test verifies the
expected result with rfi_flush enabled as well as when it is disabled.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
[mpe: Add SPDX tags, clang format, skip if the debugfs is missing, use
 __u64 and SANE_USERSPACE_TYPES to avoid printf() build errors.]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/Makefile           |   3 +-
 tools/testing/selftests/powerpc/include/utils.h    |  10 ++
 tools/testing/selftests/powerpc/security/Makefile  |   9 ++
 .../testing/selftests/powerpc/security/rfi_flush.c | 132 ++++++++++++++++++
 tools/testing/selftests/powerpc/utils.c            | 152 +++++++++++++++++++++
 5 files changed, 305 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/powerpc/security/Makefile
 create mode 100644 tools/testing/selftests/powerpc/security/rfi_flush.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile
index 201b598558b9..b3ad909aefbc 100644
--- a/tools/testing/selftests/powerpc/Makefile
+++ b/tools/testing/selftests/powerpc/Makefile
@@ -28,7 +28,8 @@ SUB_DIRS = alignment		\
 	   tm			\
 	   vphn         \
 	   math		\
-	   ptrace
+	   ptrace	\
+	   security
 
 endif
 
diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h
index da1b963cdb32..49621822d7c3 100644
--- a/tools/testing/selftests/powerpc/include/utils.h
+++ b/tools/testing/selftests/powerpc/include/utils.h
@@ -11,6 +11,7 @@
 #include <stdint.h>
 #include <stdbool.h>
 #include <linux/auxvec.h>
+#include <linux/perf_event.h>
 #include "reg.h"
 
 /* Avoid headaches with PRI?64 - just use %ll? always */
@@ -31,6 +32,15 @@ void *get_auxv_entry(int type);
 
 int pick_online_cpu(void);
 
+int read_debugfs_file(char *debugfs_file, int *result);
+int write_debugfs_file(char *debugfs_file, int result);
+void set_dscr(unsigned long val);
+int perf_event_open_counter(unsigned int type,
+			    unsigned long config, int group_fd);
+int perf_event_enable(int fd);
+int perf_event_disable(int fd);
+int perf_event_reset(int fd);
+
 static inline bool have_hwcap(unsigned long ftr)
 {
 	return ((unsigned long)get_auxv_entry(AT_HWCAP) & ftr) == ftr;
diff --git a/tools/testing/selftests/powerpc/security/Makefile b/tools/testing/selftests/powerpc/security/Makefile
new file mode 100644
index 000000000000..44690f1bb26a
--- /dev/null
+++ b/tools/testing/selftests/powerpc/security/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0+
+
+TEST_GEN_PROGS := rfi_flush
+
+CFLAGS += -I../../../../../usr/include
+
+include ../../lib.mk
+
+$(TEST_GEN_PROGS): ../harness.c ../utils.c
diff --git a/tools/testing/selftests/powerpc/security/rfi_flush.c b/tools/testing/selftests/powerpc/security/rfi_flush.c
new file mode 100644
index 000000000000..564ed45bbf73
--- /dev/null
+++ b/tools/testing/selftests/powerpc/security/rfi_flush.c
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+/*
+ * Copyright 2018 IBM Corporation.
+ */
+
+#define __SANE_USERSPACE_TYPES__
+
+#include <sys/types.h>
+#include <stdint.h>
+#include <malloc.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdio.h>
+#include "utils.h"
+
+#define CACHELINE_SIZE 128
+
+struct perf_event_read {
+	__u64 nr;
+	__u64 l1d_misses;
+};
+
+static inline __u64 load(void *addr)
+{
+	__u64 tmp;
+
+	asm volatile("ld %0,0(%1)" : "=r"(tmp) : "b"(addr));
+
+	return tmp;
+}
+
+static void syscall_loop(char *p, unsigned long iterations,
+			 unsigned long zero_size)
+{
+	for (unsigned long i = 0; i < iterations; i++) {
+		for (unsigned long j = 0; j < zero_size; j += CACHELINE_SIZE)
+			load(p + j);
+		getppid();
+	}
+}
+
+int rfi_flush_test(void)
+{
+	char *p;
+	int repetitions = 10;
+	int fd, passes = 0, iter, rc = 0;
+	struct perf_event_read v;
+	__u64 l1d_misses_total = 0;
+	unsigned long iterations = 100000, zero_size = 24 * 1024;
+	int rfi_flush_org, rfi_flush;
+
+	SKIP_IF(geteuid() != 0);
+
+	if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_org)) {
+		perror("Unable to read powerpc/rfi_flush debugfs file");
+		SKIP_IF(1);
+	}
+
+	rfi_flush = rfi_flush_org;
+
+	fd = perf_event_open_counter(PERF_TYPE_RAW, /* L1d miss */ 0x400f0, -1);
+	FAIL_IF(fd < 0);
+
+	p = (char *)memalign(zero_size, CACHELINE_SIZE);
+
+	FAIL_IF(perf_event_enable(fd));
+
+	set_dscr(1);
+
+	iter = repetitions;
+
+again:
+	FAIL_IF(perf_event_reset(fd));
+
+	syscall_loop(p, iterations, zero_size);
+
+	FAIL_IF(read(fd, &v, sizeof(v)) != sizeof(v));
+
+	/* Expect at least zero_size/CACHELINE_SIZE misses per iteration */
+	if (v.l1d_misses >= (iterations * zero_size / CACHELINE_SIZE) && rfi_flush)
+		passes++;
+	else if (v.l1d_misses < iterations && !rfi_flush)
+		passes++;
+
+	l1d_misses_total += v.l1d_misses;
+
+	while (--iter)
+		goto again;
+
+	if (passes < repetitions) {
+		printf("FAIL (L1D misses with rfi_flush=%d: %llu %c %lu) [%d/%d failures]\n",
+		       rfi_flush, l1d_misses_total, rfi_flush ? '<' : '>',
+		       rfi_flush ? (repetitions * iterations * zero_size / CACHELINE_SIZE) : iterations,
+		       repetitions - passes, repetitions);
+		rc = 1;
+	} else
+		printf("PASS (L1D misses with rfi_flush=%d: %llu %c %lu) [%d/%d pass]\n",
+		       rfi_flush, l1d_misses_total, rfi_flush ? '>' : '<',
+		       rfi_flush ? (repetitions * iterations * zero_size / CACHELINE_SIZE) : iterations,
+		       passes, repetitions);
+
+	if (rfi_flush == rfi_flush_org) {
+		rfi_flush = !rfi_flush_org;
+		if (write_debugfs_file("powerpc/rfi_flush", rfi_flush) < 0) {
+			perror("error writing to powerpc/rfi_flush debugfs file");
+			return 1;
+		}
+		iter = repetitions;
+		l1d_misses_total = 0;
+		passes = 0;
+		goto again;
+	}
+
+	perf_event_disable(fd);
+	close(fd);
+
+	set_dscr(0);
+
+	if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_org) < 0) {
+		perror("unable to restore original value of powerpc/rfi_flush debugfs file");
+		return 1;
+	}
+
+	return rc;
+}
+
+int main(int argc, char *argv[])
+{
+	return test_harness(rfi_flush_test, "rfi_flush_test");
+}
diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c
index aa8fc1e6365b..43c342845be0 100644
--- a/tools/testing/selftests/powerpc/utils.c
+++ b/tools/testing/selftests/powerpc/utils.c
@@ -10,16 +10,22 @@
 #include <fcntl.h>
 #include <link.h>
 #include <sched.h>
+#include <signal.h>
 #include <stdio.h>
+#include <stdlib.h>
 #include <string.h>
+#include <sys/ioctl.h>
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <sys/utsname.h>
 #include <unistd.h>
+#include <asm/unistd.h>
+#include <linux/limits.h>
 
 #include "utils.h"
 
 static char auxv[4096];
+extern unsigned int dscr_insn[];
 
 int read_auxv(char *buf, ssize_t buf_size)
 {
@@ -121,3 +127,149 @@ bool is_ppc64le(void)
 
 	return strcmp(uts.machine, "ppc64le") == 0;
 }
+
+int read_debugfs_file(char *debugfs_file, int *result)
+{
+	int rc = -1, fd;
+	char path[PATH_MAX];
+	char value[16];
+
+	strcpy(path, "/sys/kernel/debug/");
+	strncat(path, debugfs_file, PATH_MAX - strlen(path) - 1);
+
+	if ((fd = open(path, O_RDONLY)) < 0)
+		return rc;
+
+	if ((rc = read(fd, value, sizeof(value))) < 0)
+		return rc;
+
+	value[15] = 0;
+	*result = atoi(value);
+	close(fd);
+
+	return 0;
+}
+
+int write_debugfs_file(char *debugfs_file, int result)
+{
+	int rc = -1, fd;
+	char path[PATH_MAX];
+	char value[16];
+
+	strcpy(path, "/sys/kernel/debug/");
+	strncat(path, debugfs_file, PATH_MAX - strlen(path) - 1);
+
+	if ((fd = open(path, O_WRONLY)) < 0)
+		return rc;
+
+	snprintf(value, 16, "%d", result);
+
+	if ((rc = write(fd, value, strlen(value))) < 0)
+		return rc;
+
+	close(fd);
+
+	return 0;
+}
+
+static long perf_event_open(struct perf_event_attr *hw_event, pid_t pid,
+		int cpu, int group_fd, unsigned long flags)
+{
+	return syscall(__NR_perf_event_open, hw_event, pid, cpu,
+		      group_fd, flags);
+}
+
+static void perf_event_attr_init(struct perf_event_attr *event_attr,
+					unsigned int type,
+					unsigned long config)
+{
+	memset(event_attr, 0, sizeof(*event_attr));
+
+	event_attr->type = type;
+	event_attr->size = sizeof(struct perf_event_attr);
+	event_attr->config = config;
+	event_attr->read_format = PERF_FORMAT_GROUP;
+	event_attr->disabled = 1;
+	event_attr->exclude_kernel = 1;
+	event_attr->exclude_hv = 1;
+	event_attr->exclude_guest = 1;
+}
+
+int perf_event_open_counter(unsigned int type,
+			    unsigned long config, int group_fd)
+{
+	int fd;
+	struct perf_event_attr event_attr;
+
+	perf_event_attr_init(&event_attr, type, config);
+
+	fd = perf_event_open(&event_attr, 0, -1, group_fd, 0);
+
+	if (fd < 0)
+		perror("perf_event_open() failed");
+
+	return fd;
+}
+
+int perf_event_enable(int fd)
+{
+	if (ioctl(fd, PERF_EVENT_IOC_ENABLE, PERF_IOC_FLAG_GROUP) == -1) {
+		perror("error while enabling perf events");
+		return -1;
+	}
+
+	return 0;
+}
+
+int perf_event_disable(int fd)
+{
+	if (ioctl(fd, PERF_EVENT_IOC_DISABLE, PERF_IOC_FLAG_GROUP) == -1) {
+		perror("error disabling perf events");
+		return -1;
+	}
+
+	return 0;
+}
+
+int perf_event_reset(int fd)
+{
+	if (ioctl(fd, PERF_EVENT_IOC_RESET, PERF_IOC_FLAG_GROUP) == -1) {
+		perror("error resetting perf events");
+		return -1;
+	}
+
+	return 0;
+}
+
+static void sigill_handler(int signr, siginfo_t *info, void *unused)
+{
+	static int warned = 0;
+	ucontext_t *ctx = (ucontext_t *)unused;
+	unsigned long *pc = &UCONTEXT_NIA(ctx);
+
+	if (*pc == (unsigned long)&dscr_insn) {
+		if (!warned++)
+			printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n");
+		*pc += 4;
+	} else {
+		printf("SIGILL at %p\n", pc);
+		abort();
+	}
+}
+
+void set_dscr(unsigned long val)
+{
+	static int init = 0;
+	struct sigaction sa;
+
+	if (!init) {
+		memset(&sa, 0, sizeof(sa));
+		sa.sa_sigaction = sigill_handler;
+		sa.sa_flags = SA_SIGINFO;
+		if (sigaction(SIGILL, &sa, NULL))
+			perror("sigill_handler");
+		init = 1;
+	}
+
+	asm volatile("dscr_insn: mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR));
+}
-- 
cgit 


From d8a2fe29d3c97038c8efcc328d5e7940c5310565 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Fri, 19 Oct 2018 00:11:33 +1100
Subject: selftests/powerpc: Fix out-of-tree build errors

Some of our Makefiles don't do the right thing when building the
selftests with O=, fix them up.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/cache_shape/Makefile   | 2 --
 tools/testing/selftests/powerpc/ptrace/Makefile        | 2 --
 tools/testing/selftests/powerpc/signal/Makefile        | 2 --
 tools/testing/selftests/powerpc/switch_endian/Makefile | 1 +
 4 files changed, 1 insertion(+), 6 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/powerpc/cache_shape/Makefile b/tools/testing/selftests/powerpc/cache_shape/Makefile
index ede4d3dae750..62e947ca9921 100644
--- a/tools/testing/selftests/powerpc/cache_shape/Makefile
+++ b/tools/testing/selftests/powerpc/cache_shape/Makefile
@@ -1,8 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 TEST_PROGS := cache_shape
 
-all: $(TEST_PROGS)
-
 $(TEST_PROGS): ../harness.c ../utils.c
 
 top_srcdir = ../../../../..
diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile
index 9b35ca8e8f13..6ac71b629276 100644
--- a/tools/testing/selftests/powerpc/ptrace/Makefile
+++ b/tools/testing/selftests/powerpc/ptrace/Makefile
@@ -7,8 +7,6 @@ TEST_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \
 top_srcdir = ../../../../..
 include ../../lib.mk
 
-all: $(TEST_PROGS)
-
 CFLAGS += -m64 -I../../../../../usr/include -I../tm -mhtm -fno-pie
 
 ptrace-pkey core-pkey: child.h
diff --git a/tools/testing/selftests/powerpc/signal/Makefile b/tools/testing/selftests/powerpc/signal/Makefile
index 1fca25c6ace0..d34a7c7710db 100644
--- a/tools/testing/selftests/powerpc/signal/Makefile
+++ b/tools/testing/selftests/powerpc/signal/Makefile
@@ -1,8 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 TEST_PROGS := signal signal_tm
 
-all: $(TEST_PROGS)
-
 $(TEST_PROGS): ../harness.c ../utils.c signal.S
 
 CFLAGS += -maltivec
diff --git a/tools/testing/selftests/powerpc/switch_endian/Makefile b/tools/testing/selftests/powerpc/switch_endian/Makefile
index fcd2dcb8972b..bdc081afedb0 100644
--- a/tools/testing/selftests/powerpc/switch_endian/Makefile
+++ b/tools/testing/selftests/powerpc/switch_endian/Makefile
@@ -8,6 +8,7 @@ EXTRA_CLEAN = $(OUTPUT)/*.o $(OUTPUT)/check-reversed.S
 top_srcdir = ../../../../..
 include ../../lib.mk
 
+$(OUTPUT)/switch_endian_test: ASFLAGS += -I $(OUTPUT)
 $(OUTPUT)/switch_endian_test: $(OUTPUT)/check-reversed.S
 
 $(OUTPUT)/check-reversed.o: $(OUTPUT)/check.o
-- 
cgit 


From b7683fc66eba91674e52c30f4d8e596bfb5cbcf4 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Tue, 24 Jul 2018 15:53:22 +1000
Subject: selftests/powerpc: Add a test of wild bctr

This tests that a bctr (Branch to counter and link), ie. a function
call, to a wildly out-of-bounds address is handled correctly.

Some old kernel versions didn't handle it correctly, see eg:

  "powerpc/slb: Force a full SLB flush when we insert for a bad EA"
  https://lists.ozlabs.org/pipermail/linuxppc-dev/2017-April/157397.html

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/include/reg.h  |   1 +
 tools/testing/selftests/powerpc/mm/.gitignore  |   3 +-
 tools/testing/selftests/powerpc/mm/Makefile    |   4 +-
 tools/testing/selftests/powerpc/mm/wild_bctr.c | 155 +++++++++++++++++++++++++
 4 files changed, 161 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/powerpc/mm/wild_bctr.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/powerpc/include/reg.h b/tools/testing/selftests/powerpc/include/reg.h
index 7f348c059bc2..52b4710469d2 100644
--- a/tools/testing/selftests/powerpc/include/reg.h
+++ b/tools/testing/selftests/powerpc/include/reg.h
@@ -17,6 +17,7 @@
 				    : "memory")
 
 #define mb()		asm volatile("sync" : : : "memory");
+#define barrier()	asm volatile("" : : : "memory");
 
 #define SPRN_MMCR2     769
 #define SPRN_MMCRA     770
diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore
index 7d7c42ed6de9..ba919308fe30 100644
--- a/tools/testing/selftests/powerpc/mm/.gitignore
+++ b/tools/testing/selftests/powerpc/mm/.gitignore
@@ -2,4 +2,5 @@ hugetlb_vs_thp_test
 subpage_prot
 tempfile
 prot_sao
-segv_errors
\ No newline at end of file
+segv_errors
+wild_bctr
\ No newline at end of file
diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile
index 33ced6e0ad25..43d68420e363 100644
--- a/tools/testing/selftests/powerpc/mm/Makefile
+++ b/tools/testing/selftests/powerpc/mm/Makefile
@@ -2,7 +2,7 @@
 noarg:
 	$(MAKE) -C ../
 
-TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors
+TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors wild_bctr
 TEST_GEN_FILES := tempfile
 
 top_srcdir = ../../../../..
@@ -12,6 +12,8 @@ $(TEST_GEN_PROGS): ../harness.c
 
 $(OUTPUT)/prot_sao: ../utils.c
 
+$(OUTPUT)/wild_bctr: CFLAGS += -m64
+
 $(OUTPUT)/tempfile:
 	dd if=/dev/zero of=$@ bs=64k count=1
 
diff --git a/tools/testing/selftests/powerpc/mm/wild_bctr.c b/tools/testing/selftests/powerpc/mm/wild_bctr.c
new file mode 100644
index 000000000000..1b0e9e9a2ddc
--- /dev/null
+++ b/tools/testing/selftests/powerpc/mm/wild_bctr.c
@@ -0,0 +1,155 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright 2018, Michael Ellerman, IBM Corp.
+ *
+ * Test that an out-of-bounds branch to counter behaves as expected.
+ */
+
+#include <setjmp.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <ucontext.h>
+#include <unistd.h>
+
+#include "utils.h"
+
+
+#define BAD_NIP	0x788c545a18000000ull
+
+static struct pt_regs signal_regs;
+static jmp_buf setjmp_env;
+
+static void save_regs(ucontext_t *ctxt)
+{
+	struct pt_regs *regs = ctxt->uc_mcontext.regs;
+
+	memcpy(&signal_regs, regs, sizeof(signal_regs));
+}
+
+static void segv_handler(int signum, siginfo_t *info, void *ctxt_v)
+{
+	save_regs(ctxt_v);
+	longjmp(setjmp_env, 1);
+}
+
+static void usr2_handler(int signum, siginfo_t *info, void *ctxt_v)
+{
+	save_regs(ctxt_v);
+}
+
+static int ok(void)
+{
+	printf("Everything is OK in here.\n");
+	return 0;
+}
+
+#define REG_POISON	0x5a5aUL
+#define POISONED_REG(n)	((REG_POISON << 48) | ((n) << 32) | (REG_POISON << 16) | (n))
+
+static inline void poison_regs(void)
+{
+	#define POISON_REG(n)	\
+	  "lis  " __stringify(n) "," __stringify(REG_POISON) ";" \
+	  "addi " __stringify(n) "," __stringify(n) "," __stringify(n) ";" \
+	  "sldi " __stringify(n) "," __stringify(n) ", 32 ;" \
+	  "oris " __stringify(n) "," __stringify(n) "," __stringify(REG_POISON) ";" \
+	  "addi " __stringify(n) "," __stringify(n) "," __stringify(n) ";"
+
+	asm (POISON_REG(15)
+	     POISON_REG(16)
+	     POISON_REG(17)
+	     POISON_REG(18)
+	     POISON_REG(19)
+	     POISON_REG(20)
+	     POISON_REG(21)
+	     POISON_REG(22)
+	     POISON_REG(23)
+	     POISON_REG(24)
+	     POISON_REG(25)
+	     POISON_REG(26)
+	     POISON_REG(27)
+	     POISON_REG(28)
+	     POISON_REG(29)
+	     : // inputs
+	     : // outputs
+	     : "15", "16", "17", "18", "19", "20", "21", "22", "23", "24", "25",
+	       "26", "27", "28", "29"
+	);
+	#undef POISON_REG
+}
+
+static int check_regs(void)
+{
+	unsigned long i;
+
+	for (i = 15; i <= 29; i++)
+		FAIL_IF(signal_regs.gpr[i] != POISONED_REG(i));
+
+	printf("Regs OK\n");
+	return 0;
+}
+
+static void dump_regs(void)
+{
+	for (int i = 0; i < 32; i += 4) {
+		printf("r%02d 0x%016lx  r%02d 0x%016lx  " \
+		       "r%02d 0x%016lx  r%02d 0x%016lx\n",
+		       i, signal_regs.gpr[i],
+		       i+1, signal_regs.gpr[i+1],
+		       i+2, signal_regs.gpr[i+2],
+		       i+3, signal_regs.gpr[i+3]);
+	}
+}
+
+int test_wild_bctr(void)
+{
+	int (*func_ptr)(void);
+	struct sigaction segv = {
+		.sa_sigaction = segv_handler,
+		.sa_flags = SA_SIGINFO
+	};
+	struct sigaction usr2 = {
+		.sa_sigaction = usr2_handler,
+		.sa_flags = SA_SIGINFO
+	};
+
+	FAIL_IF(sigaction(SIGSEGV, &segv, NULL));
+	FAIL_IF(sigaction(SIGUSR2, &usr2, NULL));
+
+	bzero(&signal_regs, sizeof(signal_regs));
+
+	if (setjmp(setjmp_env) == 0) {
+		func_ptr = ok;
+		func_ptr();
+
+		kill(getpid(), SIGUSR2);
+		printf("Regs before:\n");
+		dump_regs();
+		bzero(&signal_regs, sizeof(signal_regs));
+
+		poison_regs();
+
+		func_ptr = (int (*)(void))BAD_NIP;
+		func_ptr();
+
+		FAIL_IF(1); /* we didn't segv? */
+	}
+
+	FAIL_IF(signal_regs.nip != BAD_NIP);
+
+	printf("All good - took SEGV as expected branching to 0x%llx\n", BAD_NIP);
+
+	dump_regs();
+	FAIL_IF(check_regs());
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(test_wild_bctr, "wild_bctr");
+}
-- 
cgit 


From f908d26b2c41d9a924371099c4979e4b5d385165 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Fri, 19 Oct 2018 19:56:50 -0700
Subject: bpf: libbpf support for msg_push_data

Add support for new bpf_msg_push_data in libbpf.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/include/uapi/linux/bpf.h            | 20 +++++++++++++++++++-
 tools/testing/selftests/bpf/bpf_helpers.h |  2 ++
 2 files changed, 21 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index a2fb333290dc..852dc17ab47a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2240,6 +2240,23 @@ union bpf_attr {
  *		pointer that was returned from bpf_sk_lookup_xxx\ ().
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_msg_push_data(struct sk_buff *skb, u32 start, u32 len, u64 flags)
+ *	Description
+ *		For socket policies, insert *len* bytes into msg at offset
+ *		*start*.
+ *
+ *		If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a
+ *		*msg* it may want to insert metadata or options into the msg.
+ *		This can later be read and used by any of the lower layer BPF
+ *		hooks.
+ *
+ *		This helper may fail if under memory pressure (a malloc
+ *		fails) in these cases BPF programs will get an appropriate
+ *		error and BPF programs will need to handle them.
+ *
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2331,7 +2348,8 @@ union bpf_attr {
 	FN(sk_release),			\
 	FN(map_push_elem),		\
 	FN(map_pop_elem),		\
-	FN(map_peek_elem),
+	FN(map_peek_elem),		\
+	FN(msg_push_data),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 6407a3df0f3b..686e57ce40f4 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -111,6 +111,8 @@ static int (*bpf_msg_cork_bytes)(void *ctx, int len) =
 	(void *) BPF_FUNC_msg_cork_bytes;
 static int (*bpf_msg_pull_data)(void *ctx, int start, int end, int flags) =
 	(void *) BPF_FUNC_msg_pull_data;
+static int (*bpf_msg_push_data)(void *ctx, int start, int end, int flags) =
+	(void *) BPF_FUNC_msg_push_data;
 static int (*bpf_bind)(void *ctx, void *addr, int addr_len) =
 	(void *) BPF_FUNC_bind;
 static int (*bpf_xdp_adjust_tail)(void *ctx, int offset) =
-- 
cgit 


From 84fbfe026acaa6d91e2f71f1635992bf472e2496 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Fri, 19 Oct 2018 19:56:51 -0700
Subject: bpf: test_sockmap add options to use msg_push_data

Add options to run msg_push_data, this patch creates two more flags
in test_sockmap that can be used to specify the offset and length
of bytes to be added. The new options are --txmsg_start_push to
specify where bytes should be inserted and --txmsg_end_push to
specify how many bytes. This is analagous to the options that are
used to pull data, --txmsg_start and --txmsg_end.

In addition to adding the options tests are added to the test
suit to run the tests similar to what was done for msg_pull_data.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_sockmap.c      | 58 ++++++++++++++-
 tools/testing/selftests/bpf/test_sockmap_kern.h | 97 +++++++++++++++++++------
 2 files changed, 129 insertions(+), 26 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index cbd1c0be8680..622ade0a0957 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -77,6 +77,8 @@ int txmsg_apply;
 int txmsg_cork;
 int txmsg_start;
 int txmsg_end;
+int txmsg_start_push;
+int txmsg_end_push;
 int txmsg_ingress;
 int txmsg_skb;
 int ktls;
@@ -100,6 +102,8 @@ static const struct option long_options[] = {
 	{"txmsg_cork",	required_argument,	NULL, 'k'},
 	{"txmsg_start", required_argument,	NULL, 's'},
 	{"txmsg_end",	required_argument,	NULL, 'e'},
+	{"txmsg_start_push", required_argument,	NULL, 'p'},
+	{"txmsg_end_push",   required_argument,	NULL, 'q'},
 	{"txmsg_ingress", no_argument,		&txmsg_ingress, 1 },
 	{"txmsg_skb", no_argument,		&txmsg_skb, 1 },
 	{"ktls", no_argument,			&ktls, 1 },
@@ -903,6 +907,30 @@ run:
 			}
 		}
 
+		if (txmsg_start_push) {
+			i = 2;
+			err = bpf_map_update_elem(map_fd[5],
+						  &i, &txmsg_start_push, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem (txmsg_start_push):  %d (%s)\n",
+					err, strerror(errno));
+				goto out;
+			}
+		}
+
+		if (txmsg_end_push) {
+			i = 3;
+			err = bpf_map_update_elem(map_fd[5],
+						  &i, &txmsg_end_push, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem %i@%i (txmsg_end_push):  %d (%s)\n",
+					txmsg_end_push, i, err, strerror(errno));
+				goto out;
+			}
+		}
+
 		if (txmsg_ingress) {
 			int in = BPF_F_INGRESS;
 
@@ -1235,6 +1263,8 @@ static int test_mixed(int cgrp)
 	txmsg_pass = txmsg_noisy = txmsg_redir_noisy = txmsg_drop = 0;
 	txmsg_apply = txmsg_cork = 0;
 	txmsg_start = txmsg_end = 0;
+	txmsg_start_push = txmsg_end_push = 0;
+
 	/* Test small and large iov_count values with pass/redir/apply/cork */
 	txmsg_pass = 1;
 	txmsg_redir = 0;
@@ -1351,6 +1381,8 @@ static int test_start_end(int cgrp)
 	/* Test basic start/end with lots of iov_count and iov_lengths */
 	txmsg_start = 1;
 	txmsg_end = 2;
+	txmsg_start_push = 1;
+	txmsg_end_push = 2;
 	err = test_txmsg(cgrp);
 	if (err)
 		goto out;
@@ -1364,6 +1396,8 @@ static int test_start_end(int cgrp)
 	for (i = 99; i <= 1600; i += 500) {
 		txmsg_start = 0;
 		txmsg_end = i;
+		txmsg_start_push = 0;
+		txmsg_end_push = i;
 		err = test_exec(cgrp, &opt);
 		if (err)
 			goto out;
@@ -1373,6 +1407,8 @@ static int test_start_end(int cgrp)
 	for (i = 199; i <= 1600; i += 500) {
 		txmsg_start = 100;
 		txmsg_end = i;
+		txmsg_start_push = 100;
+		txmsg_end_push = i;
 		err = test_exec(cgrp, &opt);
 		if (err)
 			goto out;
@@ -1381,6 +1417,8 @@ static int test_start_end(int cgrp)
 	/* Test start/end with cork pulling last sg entry */
 	txmsg_start = 1500;
 	txmsg_end = 1600;
+	txmsg_start_push = 1500;
+	txmsg_end_push = 1600;
 	err = test_exec(cgrp, &opt);
 	if (err)
 		goto out;
@@ -1388,6 +1426,8 @@ static int test_start_end(int cgrp)
 	/* Test start/end pull of single byte in last page */
 	txmsg_start = 1111;
 	txmsg_end = 1112;
+	txmsg_start_push = 1111;
+	txmsg_end_push = 1112;
 	err = test_exec(cgrp, &opt);
 	if (err)
 		goto out;
@@ -1395,6 +1435,8 @@ static int test_start_end(int cgrp)
 	/* Test start/end with end < start */
 	txmsg_start = 1111;
 	txmsg_end = 0;
+	txmsg_start_push = 1111;
+	txmsg_end_push = 0;
 	err = test_exec(cgrp, &opt);
 	if (err)
 		goto out;
@@ -1402,6 +1444,8 @@ static int test_start_end(int cgrp)
 	/* Test start/end with end > data */
 	txmsg_start = 0;
 	txmsg_end = 1601;
+	txmsg_start_push = 0;
+	txmsg_end_push = 1601;
 	err = test_exec(cgrp, &opt);
 	if (err)
 		goto out;
@@ -1409,6 +1453,8 @@ static int test_start_end(int cgrp)
 	/* Test start/end with start > data */
 	txmsg_start = 1601;
 	txmsg_end = 1600;
+	txmsg_start_push = 1601;
+	txmsg_end_push = 1600;
 	err = test_exec(cgrp, &opt);
 
 out:
@@ -1424,7 +1470,7 @@ char *map_names[] = {
 	"sock_map_redir",
 	"sock_apply_bytes",
 	"sock_cork_bytes",
-	"sock_pull_bytes",
+	"sock_bytes",
 	"sock_redir_flags",
 	"sock_skb_opts",
 };
@@ -1531,7 +1577,7 @@ static int __test_suite(int cg_fd, char *bpf_file)
 	}
 
 	/* Tests basic commands and APIs with range of iov values */
-	txmsg_start = txmsg_end = 0;
+	txmsg_start = txmsg_end = txmsg_start_push = txmsg_end_push = 0;
 	err = test_txmsg(cg_fd);
 	if (err)
 		goto out;
@@ -1580,7 +1626,7 @@ int main(int argc, char **argv)
 	if (argc < 2)
 		return test_suite(-1);
 
-	while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:",
+	while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:p:q:",
 				  long_options, &longindex)) != -1) {
 		switch (opt) {
 		case 's':
@@ -1589,6 +1635,12 @@ int main(int argc, char **argv)
 		case 'e':
 			txmsg_end = atoi(optarg);
 			break;
+		case 'p':
+			txmsg_start_push = atoi(optarg);
+			break;
+		case 'q':
+			txmsg_end_push = atoi(optarg);
+			break;
 		case 'a':
 			txmsg_apply = atoi(optarg);
 			break;
diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.h b/tools/testing/selftests/bpf/test_sockmap_kern.h
index 8e8e41780bb9..14b8bbac004f 100644
--- a/tools/testing/selftests/bpf/test_sockmap_kern.h
+++ b/tools/testing/selftests/bpf/test_sockmap_kern.h
@@ -70,11 +70,11 @@ struct bpf_map_def SEC("maps") sock_cork_bytes = {
 	.max_entries = 1
 };
 
-struct bpf_map_def SEC("maps") sock_pull_bytes = {
+struct bpf_map_def SEC("maps") sock_bytes = {
 	.type = BPF_MAP_TYPE_ARRAY,
 	.key_size = sizeof(int),
 	.value_size = sizeof(int),
-	.max_entries = 2
+	.max_entries = 4
 };
 
 struct bpf_map_def SEC("maps") sock_redir_flags = {
@@ -181,8 +181,8 @@ int bpf_sockmap(struct bpf_sock_ops *skops)
 SEC("sk_msg1")
 int bpf_prog4(struct sk_msg_md *msg)
 {
-	int *bytes, zero = 0, one = 1;
-	int *start, *end;
+	int *bytes, zero = 0, one = 1, two = 2, three = 3;
+	int *start, *end, *start_push, *end_push;
 
 	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
 	if (bytes)
@@ -190,18 +190,24 @@ int bpf_prog4(struct sk_msg_md *msg)
 	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
 	if (bytes)
 		bpf_msg_cork_bytes(msg, *bytes);
-	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+	start = bpf_map_lookup_elem(&sock_bytes, &zero);
+	end = bpf_map_lookup_elem(&sock_bytes, &one);
 	if (start && end)
 		bpf_msg_pull_data(msg, *start, *end, 0);
+	start_push = bpf_map_lookup_elem(&sock_bytes, &two);
+	end_push = bpf_map_lookup_elem(&sock_bytes, &three);
+	if (start_push && end_push)
+		bpf_msg_push_data(msg, *start_push, *end_push, 0);
 	return SK_PASS;
 }
 
 SEC("sk_msg2")
 int bpf_prog5(struct sk_msg_md *msg)
 {
-	int err1 = -1, err2 = -1, zero = 0, one = 1;
-	int *bytes, *start, *end, len1, len2;
+	int zero = 0, one = 1, two = 2, three = 3;
+	int *start, *end, *start_push, *end_push;
+	int *bytes, len1, len2 = 0, len3;
+	int err1 = -1, err2 = -1;
 
 	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
 	if (bytes)
@@ -210,8 +216,8 @@ int bpf_prog5(struct sk_msg_md *msg)
 	if (bytes)
 		err2 = bpf_msg_cork_bytes(msg, *bytes);
 	len1 = (__u64)msg->data_end - (__u64)msg->data;
-	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+	start = bpf_map_lookup_elem(&sock_bytes, &zero);
+	end = bpf_map_lookup_elem(&sock_bytes, &one);
 	if (start && end) {
 		int err;
 
@@ -225,6 +231,23 @@ int bpf_prog5(struct sk_msg_md *msg)
 		bpf_printk("sk_msg2: length update %i->%i\n",
 			   len1, len2);
 	}
+
+	start_push = bpf_map_lookup_elem(&sock_bytes, &two);
+	end_push = bpf_map_lookup_elem(&sock_bytes, &three);
+	if (start_push && end_push) {
+		int err;
+
+		bpf_printk("sk_msg2: push(%i:%i)\n",
+			   start_push ? *start_push : 0,
+			   end_push ? *end_push : 0);
+		err = bpf_msg_push_data(msg, *start_push, *end_push, 0);
+		if (err)
+			bpf_printk("sk_msg2: push_data err %i\n", err);
+		len3 = (__u64)msg->data_end - (__u64)msg->data;
+		bpf_printk("sk_msg2: length push_update %i->%i\n",
+			   len2 ? len2 : len1, len3);
+	}
+
 	bpf_printk("sk_msg2: data length %i err1 %i err2 %i\n",
 		   len1, err1, err2);
 	return SK_PASS;
@@ -233,8 +256,8 @@ int bpf_prog5(struct sk_msg_md *msg)
 SEC("sk_msg3")
 int bpf_prog6(struct sk_msg_md *msg)
 {
-	int *bytes, zero = 0, one = 1, key = 0;
-	int *start, *end, *f;
+	int *bytes, *start, *end, *start_push, *end_push, *f;
+	int zero = 0, one = 1, two = 2, three = 3, key = 0;
 	__u64 flags = 0;
 
 	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
@@ -243,10 +266,17 @@ int bpf_prog6(struct sk_msg_md *msg)
 	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
 	if (bytes)
 		bpf_msg_cork_bytes(msg, *bytes);
-	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+
+	start = bpf_map_lookup_elem(&sock_bytes, &zero);
+	end = bpf_map_lookup_elem(&sock_bytes, &one);
 	if (start && end)
 		bpf_msg_pull_data(msg, *start, *end, 0);
+
+	start_push = bpf_map_lookup_elem(&sock_bytes, &two);
+	end_push = bpf_map_lookup_elem(&sock_bytes, &three);
+	if (start_push && end_push)
+		bpf_msg_push_data(msg, *start_push, *end_push, 0);
+
 	f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
 	if (f && *f) {
 		key = 2;
@@ -262,8 +292,9 @@ int bpf_prog6(struct sk_msg_md *msg)
 SEC("sk_msg4")
 int bpf_prog7(struct sk_msg_md *msg)
 {
-	int err1 = 0, err2 = 0, zero = 0, one = 1, key = 0;
-	int *f, *bytes, *start, *end, len1, len2;
+	int zero = 0, one = 1, two = 2, three = 3, len1, len2 = 0, len3;
+	int *bytes, *start, *end, *start_push, *end_push, *f;
+	int err1 = 0, err2 = 0, key = 0;
 	__u64 flags = 0;
 
 		int err;
@@ -274,10 +305,10 @@ int bpf_prog7(struct sk_msg_md *msg)
 	if (bytes)
 		err2 = bpf_msg_cork_bytes(msg, *bytes);
 	len1 = (__u64)msg->data_end - (__u64)msg->data;
-	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
-	if (start && end) {
 
+	start = bpf_map_lookup_elem(&sock_bytes, &zero);
+	end = bpf_map_lookup_elem(&sock_bytes, &one);
+	if (start && end) {
 		bpf_printk("sk_msg2: pull(%i:%i)\n",
 			   start ? *start : 0, end ? *end : 0);
 		err = bpf_msg_pull_data(msg, *start, *end, 0);
@@ -288,6 +319,22 @@ int bpf_prog7(struct sk_msg_md *msg)
 		bpf_printk("sk_msg2: length update %i->%i\n",
 			   len1, len2);
 	}
+
+	start_push = bpf_map_lookup_elem(&sock_bytes, &two);
+	end_push = bpf_map_lookup_elem(&sock_bytes, &three);
+	if (start_push && end_push) {
+		bpf_printk("sk_msg4: push(%i:%i)\n",
+			   start_push ? *start_push : 0,
+			   end_push ? *end_push : 0);
+		err = bpf_msg_push_data(msg, *start_push, *end_push, 0);
+		if (err)
+			bpf_printk("sk_msg4: push_data err %i\n",
+				   err);
+		len3 = (__u64)msg->data_end - (__u64)msg->data;
+		bpf_printk("sk_msg4: length push_update %i->%i\n",
+			   len2 ? len2 : len1, len3);
+	}
+
 	f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
 	if (f && *f) {
 		key = 2;
@@ -342,8 +389,8 @@ int bpf_prog9(struct sk_msg_md *msg)
 SEC("sk_msg7")
 int bpf_prog10(struct sk_msg_md *msg)
 {
-	int *bytes, zero = 0, one = 1;
-	int *start, *end;
+	int *bytes, *start, *end, *start_push, *end_push;
+	int zero = 0, one = 1, two = 2, three = 3;
 
 	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
 	if (bytes)
@@ -351,10 +398,14 @@ int bpf_prog10(struct sk_msg_md *msg)
 	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
 	if (bytes)
 		bpf_msg_cork_bytes(msg, *bytes);
-	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+	start = bpf_map_lookup_elem(&sock_bytes, &zero);
+	end = bpf_map_lookup_elem(&sock_bytes, &one);
 	if (start && end)
 		bpf_msg_pull_data(msg, *start, *end, 0);
+	start_push = bpf_map_lookup_elem(&sock_bytes, &two);
+	end_push = bpf_map_lookup_elem(&sock_bytes, &three);
+	if (start_push && end_push)
+		bpf_msg_push_data(msg, *start_push, *end_push, 0);
 
 	return SK_DROP;
 }
-- 
cgit 


From 2a159c6f82381a458bc56e7e202b6bee57a2ccb7 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sun, 21 Oct 2018 02:09:24 +0200
Subject: bpf, verifier: fix register type dump in xadd and st

Using reg_type_str[insn->dst_reg] is incorrect since insn->dst_reg
contains the register number but not the actual register type. Add
a small reg_state() helper and use it to get to the type. Also fix
up the test_verifier test cases that have an incorrect errstr.

Fixes: 9d2be44a7f33 ("bpf: Reuse canonical string formatter for ctx errs")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c                       | 19 +++++++++++++------
 tools/testing/selftests/bpf/test_verifier.c | 10 +++++-----
 2 files changed, 18 insertions(+), 11 deletions(-)

(limited to 'tools/testing')

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7d6d9cf9ebd5..64e0981a4074 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1528,14 +1528,19 @@ static bool __is_pointer_value(bool allow_ptr_leaks,
 	return reg->type != SCALAR_VALUE;
 }
 
+static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno)
+{
+	return cur_regs(env) + regno;
+}
+
 static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
 {
-	return __is_pointer_value(env->allow_ptr_leaks, cur_regs(env) + regno);
+	return __is_pointer_value(env->allow_ptr_leaks, reg_state(env, regno));
 }
 
 static bool is_ctx_reg(struct bpf_verifier_env *env, int regno)
 {
-	const struct bpf_reg_state *reg = cur_regs(env) + regno;
+	const struct bpf_reg_state *reg = reg_state(env, regno);
 
 	return reg->type == PTR_TO_CTX ||
 	       reg->type == PTR_TO_SOCKET;
@@ -1543,7 +1548,7 @@ static bool is_ctx_reg(struct bpf_verifier_env *env, int regno)
 
 static bool is_pkt_reg(struct bpf_verifier_env *env, int regno)
 {
-	const struct bpf_reg_state *reg = cur_regs(env) + regno;
+	const struct bpf_reg_state *reg = reg_state(env, regno);
 
 	return type_is_pkt_pointer(reg->type);
 }
@@ -1958,7 +1963,8 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins
 	if (is_ctx_reg(env, insn->dst_reg) ||
 	    is_pkt_reg(env, insn->dst_reg)) {
 		verbose(env, "BPF_XADD stores into R%d %s is not allowed\n",
-			insn->dst_reg, reg_type_str[insn->dst_reg]);
+			insn->dst_reg,
+			reg_type_str[reg_state(env, insn->dst_reg)->type]);
 		return -EACCES;
 	}
 
@@ -1983,7 +1989,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 				int access_size, bool zero_size_allowed,
 				struct bpf_call_arg_meta *meta)
 {
-	struct bpf_reg_state *reg = cur_regs(env) + regno;
+	struct bpf_reg_state *reg = reg_state(env, regno);
 	struct bpf_func_state *state = func(env, reg);
 	int off, i, slot, spi;
 
@@ -5264,7 +5270,8 @@ static int do_check(struct bpf_verifier_env *env)
 
 			if (is_ctx_reg(env, insn->dst_reg)) {
 				verbose(env, "BPF_ST stores into R%d %s is not allowed\n",
-					insn->dst_reg, reg_type_str[insn->dst_reg]);
+					insn->dst_reg,
+					reg_type_str[reg_state(env, insn->dst_reg)->type]);
 				return -EACCES;
 			}
 
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index f1ae8d09770f..769d68a48f30 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -3430,7 +3430,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_1, offsetof(struct __sk_buff, mark), 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "BPF_ST stores into R1 inv is not allowed",
+		.errstr = "BPF_ST stores into R1 ctx is not allowed",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -3442,7 +3442,7 @@ static struct bpf_test tests[] = {
 				     BPF_REG_0, offsetof(struct __sk_buff, mark), 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "BPF_XADD stores into R1 inv is not allowed",
+		.errstr = "BPF_XADD stores into R1 ctx is not allowed",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -5670,7 +5670,7 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R2 leaks addr into mem",
 		.result_unpriv = REJECT,
 		.result = REJECT,
-		.errstr = "BPF_XADD stores into R1 inv is not allowed",
+		.errstr = "BPF_XADD stores into R1 ctx is not allowed",
 	},
 	{
 		"leak pointer into ctx 2",
@@ -5685,7 +5685,7 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R10 leaks addr into mem",
 		.result_unpriv = REJECT,
 		.result = REJECT,
-		.errstr = "BPF_XADD stores into R1 inv is not allowed",
+		.errstr = "BPF_XADD stores into R1 ctx is not allowed",
 	},
 	{
 		"leak pointer into ctx 3",
@@ -12634,7 +12634,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = REJECT,
-		.errstr = "BPF_XADD stores into R2 ctx",
+		.errstr = "BPF_XADD stores into R2 pkt is not allowed",
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
 	{
-- 
cgit 


From 3dca21156b5f809510e8c3efe7f1046e27242e3d Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sun, 21 Oct 2018 02:09:28 +0200
Subject: bpf, libbpf: simplify and cleanup perf ring buffer walk

Simplify bpf_perf_event_read_simple() a bit and fix up some minor
things along the way: the return code in the header is not of type
int but enum bpf_perf_event_ret instead. Once callback indicated
to break the loop walking event data, it also needs to be consumed
in data_tail since it has been processed already.

Moreover, bpf_perf_event_print_t callback should avoid void * as
we actually get a pointer to struct perf_event_header and thus
applications can make use of container_of() to have type checks.
The walk also doesn't have to use modulo op since the ring size is
required to be power of two.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/map_perf_ring.c           | 10 +++--
 tools/lib/bpf/libbpf.c                      | 67 +++++++++++++----------------
 tools/lib/bpf/libbpf.h                      | 15 ++++---
 tools/testing/selftests/bpf/trace_helpers.c |  7 +--
 4 files changed, 47 insertions(+), 52 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c
index 6d41323be291..bdaf4062e26e 100644
--- a/tools/bpf/bpftool/map_perf_ring.c
+++ b/tools/bpf/bpftool/map_perf_ring.c
@@ -50,15 +50,17 @@ static void int_exit(int signo)
 	stop = true;
 }
 
-static enum bpf_perf_event_ret print_bpf_output(void *event, void *priv)
+static enum bpf_perf_event_ret
+print_bpf_output(struct perf_event_header *event, void *private_data)
 {
-	struct event_ring_info *ring = priv;
-	struct perf_event_sample *e = event;
+	struct perf_event_sample *e = container_of(event, struct perf_event_sample,
+						   header);
+	struct event_ring_info *ring = private_data;
 	struct {
 		struct perf_event_header header;
 		__u64 id;
 		__u64 lost;
-	} *lost = event;
+	} *lost = (typeof(lost))event;
 
 	if (json_output) {
 		jsonw_start_object(json_wtr);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 0c21355f04a7..b607be7236d3 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2415,56 +2415,47 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 }
 
 enum bpf_perf_event_ret
-bpf_perf_event_read_simple(void *mem, unsigned long size,
-			   unsigned long page_size, void **buf, size_t *buf_len,
-			   bpf_perf_event_print_t fn, void *priv)
+bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
+			   void **copy_mem, size_t *copy_size,
+			   bpf_perf_event_print_t fn, void *private_data)
 {
-	struct perf_event_mmap_page *header = mem;
+	struct perf_event_mmap_page *header = mmap_mem;
 	__u64 data_head = ring_buffer_read_head(header);
 	__u64 data_tail = header->data_tail;
-	int ret = LIBBPF_PERF_EVENT_ERROR;
-	void *base, *begin, *end;
-
-	if (data_head == data_tail)
-		return LIBBPF_PERF_EVENT_CONT;
-
-	base = ((char *)header) + page_size;
-
-	begin = base + data_tail % size;
-	end = base + data_head % size;
-
-	while (begin != end) {
-		struct perf_event_header *ehdr;
-
-		ehdr = begin;
-		if (begin + ehdr->size > base + size) {
-			long len = base + size - begin;
-
-			if (*buf_len < ehdr->size) {
-				free(*buf);
-				*buf = malloc(ehdr->size);
-				if (!*buf) {
+	void *base = ((__u8 *)header) + page_size;
+	int ret = LIBBPF_PERF_EVENT_CONT;
+	struct perf_event_header *ehdr;
+	size_t ehdr_size;
+
+	while (data_head != data_tail) {
+		ehdr = base + (data_tail & (mmap_size - 1));
+		ehdr_size = ehdr->size;
+
+		if (((void *)ehdr) + ehdr_size > base + mmap_size) {
+			void *copy_start = ehdr;
+			size_t len_first = base + mmap_size - copy_start;
+			size_t len_secnd = ehdr_size - len_first;
+
+			if (*copy_size < ehdr_size) {
+				free(*copy_mem);
+				*copy_mem = malloc(ehdr_size);
+				if (!*copy_mem) {
+					*copy_size = 0;
 					ret = LIBBPF_PERF_EVENT_ERROR;
 					break;
 				}
-				*buf_len = ehdr->size;
+				*copy_size = ehdr_size;
 			}
 
-			memcpy(*buf, begin, len);
-			memcpy(*buf + len, base, ehdr->size - len);
-			ehdr = (void *)*buf;
-			begin = base + ehdr->size - len;
-		} else if (begin + ehdr->size == base + size) {
-			begin = base;
-		} else {
-			begin += ehdr->size;
+			memcpy(*copy_mem, copy_start, len_first);
+			memcpy(*copy_mem + len_first, base, len_secnd);
+			ehdr = *copy_mem;
 		}
 
-		ret = fn(ehdr, priv);
+		ret = fn(ehdr, private_data);
+		data_tail += ehdr_size;
 		if (ret != LIBBPF_PERF_EVENT_CONT)
 			break;
-
-		data_tail += ehdr->size;
 	}
 
 	ring_buffer_write_tail(header, data_tail);
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 1354cc9f8cba..1f3468dad8b2 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -297,13 +297,14 @@ enum bpf_perf_event_ret {
 	LIBBPF_PERF_EVENT_CONT	= -2,
 };
 
-typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(void *event,
-							  void *priv);
-LIBBPF_API int bpf_perf_event_read_simple(void *mem, unsigned long size,
-					  unsigned long page_size,
-					  void **buf, size_t *buf_len,
-					  bpf_perf_event_print_t fn,
-					  void *priv);
+struct perf_event_header;
+typedef enum bpf_perf_event_ret
+	(*bpf_perf_event_print_t)(struct perf_event_header *hdr,
+				  void *private_data);
+LIBBPF_API enum bpf_perf_event_ret
+bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
+			   void **copy_mem, size_t *copy_size,
+			   bpf_perf_event_print_t fn, void *private_data);
 
 struct nlattr;
 typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index a3d1dace4a75..4cdb63bf0521 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -125,10 +125,11 @@ struct perf_event_sample {
 	char data[];
 };
 
-static enum bpf_perf_event_ret bpf_perf_event_print(void *event, void *priv)
+static enum bpf_perf_event_ret
+bpf_perf_event_print(struct perf_event_header *hdr, void *private_data)
 {
-	struct perf_event_sample *e = event;
-	perf_event_print_fn fn = priv;
+	struct perf_event_sample *e = (struct perf_event_sample *)hdr;
+	perf_event_print_fn fn = private_data;
 	int ret;
 
 	if (e->header.type == PERF_RECORD_SAMPLE) {
-- 
cgit 


From c5fa5d602221362f8341ecd9e32d83194abf5bd9 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Sat, 20 Oct 2018 22:58:44 +0100
Subject: selftests/bpf: fix return value comparison for tests in
 test_libbpf.sh

The return value for each test in test_libbpf.sh is compared with

    if (( $? == 0 )) ; then ...

This works well with bash, but not with dash, that /bin/sh is aliased to
on some systems (such as Ubuntu).

Let's replace this comparison by something that works on both shells.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_libbpf.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_libbpf.sh b/tools/testing/selftests/bpf/test_libbpf.sh
index d97dc914cd49..156d89f1edcc 100755
--- a/tools/testing/selftests/bpf/test_libbpf.sh
+++ b/tools/testing/selftests/bpf/test_libbpf.sh
@@ -6,7 +6,7 @@ export TESTNAME=test_libbpf
 # Determine selftest success via shell exit code
 exit_handler()
 {
-	if (( $? == 0 )); then
+	if [ $? -eq 0 ]; then
 		echo "selftests: $TESTNAME [PASS]";
 	else
 		echo "$TESTNAME: failed at file $LAST_LOADED" 1>&2
-- 
cgit 


From f8d5d0cc145cc21bfc56ef807dc28102aebbf228 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Tue, 7 Nov 2017 16:30:10 -0500
Subject: xarray: Add definition of struct xarray

This is a direct replacement for struct radix_tree_root.  Some of the
struct members have changed name; convert those, and use a #define so
that radix_tree users continue to work without change.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
Reviewed-by: Josef Bacik <jbacik@fb.com>
---
 include/linux/radix-tree.h               | 28 ++++--------
 include/linux/xarray.h                   | 70 +++++++++++++++++++++++++++++
 lib/Makefile                             |  2 +-
 lib/idr.c                                |  4 +-
 lib/radix-tree.c                         | 75 ++++++++++++++++----------------
 lib/xarray.c                             | 44 +++++++++++++++++++
 tools/testing/radix-tree/Makefile        |  5 ++-
 tools/testing/radix-tree/linux/bug.h     |  1 +
 tools/testing/radix-tree/linux/kconfig.h |  1 +
 tools/testing/radix-tree/multiorder.c    |  6 +--
 tools/testing/radix-tree/test.c          |  6 +--
 tools/testing/radix-tree/xarray.c        |  7 +++
 12 files changed, 181 insertions(+), 68 deletions(-)
 create mode 100644 lib/xarray.c
 create mode 100644 tools/testing/radix-tree/linux/kconfig.h
 create mode 100644 tools/testing/radix-tree/xarray.c

(limited to 'tools/testing')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 60f3d8eb2cb7..0b080bd88ab7 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -30,6 +30,9 @@
 #include <linux/types.h>
 #include <linux/xarray.h>
 
+/* Keep unconverted code working */
+#define radix_tree_root		xarray
+
 /*
  * The bottom two bits of the slot determine how the remaining bits in the
  * slot are interpreted:
@@ -92,36 +95,21 @@ struct radix_tree_node {
 	unsigned long	tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS];
 };
 
-/* The IDR tag is stored in the low bits of the GFP flags */
+/* The IDR tag is stored in the low bits of xa_flags */
 #define ROOT_IS_IDR	((__force gfp_t)4)
-/* The top bits of gfp_mask are used to store the root tags */
+/* The top bits of xa_flags are used to store the root tags */
 #define ROOT_TAG_SHIFT	(__GFP_BITS_SHIFT)
 
-struct radix_tree_root {
-	spinlock_t		xa_lock;
-	gfp_t			gfp_mask;
-	struct radix_tree_node	__rcu *rnode;
-};
-
-#define RADIX_TREE_INIT(name, mask)	{				\
-	.xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock),			\
-	.gfp_mask = (mask),						\
-	.rnode = NULL,							\
-}
+#define RADIX_TREE_INIT(name, mask)	XARRAY_INIT(name, mask)
 
 #define RADIX_TREE(name, mask) \
 	struct radix_tree_root name = RADIX_TREE_INIT(name, mask)
 
-#define INIT_RADIX_TREE(root, mask)					\
-do {									\
-	spin_lock_init(&(root)->xa_lock);				\
-	(root)->gfp_mask = (mask);					\
-	(root)->rnode = NULL;						\
-} while (0)
+#define INIT_RADIX_TREE(root, mask) xa_init_flags(root, mask)
 
 static inline bool radix_tree_empty(const struct radix_tree_root *root)
 {
-	return root->rnode == NULL;
+	return root->xa_head == NULL;
 }
 
 /**
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 4d1cd7a083e8..9122cf8bf52a 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -10,6 +10,8 @@
  */
 
 #include <linux/bug.h>
+#include <linux/compiler.h>
+#include <linux/kconfig.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
 
@@ -153,6 +155,74 @@ static inline bool xa_is_internal(const void *entry)
 	return ((unsigned long)entry & 3) == 2;
 }
 
+/**
+ * struct xarray - The anchor of the XArray.
+ * @xa_lock: Lock that protects the contents of the XArray.
+ *
+ * To use the xarray, define it statically or embed it in your data structure.
+ * It is a very small data structure, so it does not usually make sense to
+ * allocate it separately and keep a pointer to it in your data structure.
+ *
+ * You may use the xa_lock to protect your own data structures as well.
+ */
+/*
+ * If all of the entries in the array are NULL, @xa_head is a NULL pointer.
+ * If the only non-NULL entry in the array is at index 0, @xa_head is that
+ * entry.  If any other entry in the array is non-NULL, @xa_head points
+ * to an @xa_node.
+ */
+struct xarray {
+	spinlock_t	xa_lock;
+/* private: The rest of the data structure is not to be used directly. */
+	gfp_t		xa_flags;
+	void __rcu *	xa_head;
+};
+
+#define XARRAY_INIT(name, flags) {				\
+	.xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock),		\
+	.xa_flags = flags,					\
+	.xa_head = NULL,					\
+}
+
+/**
+ * DEFINE_XARRAY_FLAGS() - Define an XArray with custom flags.
+ * @name: A string that names your XArray.
+ * @flags: XA_FLAG values.
+ *
+ * This is intended for file scope definitions of XArrays.  It declares
+ * and initialises an empty XArray with the chosen name and flags.  It is
+ * equivalent to calling xa_init_flags() on the array, but it does the
+ * initialisation at compiletime instead of runtime.
+ */
+#define DEFINE_XARRAY_FLAGS(name, flags)				\
+	struct xarray name = XARRAY_INIT(name, flags)
+
+/**
+ * DEFINE_XARRAY() - Define an XArray.
+ * @name: A string that names your XArray.
+ *
+ * This is intended for file scope definitions of XArrays.  It declares
+ * and initialises an empty XArray with the chosen name.  It is equivalent
+ * to calling xa_init() on the array, but it does the initialisation at
+ * compiletime instead of runtime.
+ */
+#define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0)
+
+void xa_init_flags(struct xarray *, gfp_t flags);
+
+/**
+ * xa_init() - Initialise an empty XArray.
+ * @xa: XArray.
+ *
+ * An empty XArray is full of NULL entries.
+ *
+ * Context: Any context.
+ */
+static inline void xa_init(struct xarray *xa)
+{
+	xa_init_flags(xa, 0);
+}
+
 #define xa_trylock(xa)		spin_trylock(&(xa)->xa_lock)
 #define xa_lock(xa)		spin_lock(&(xa)->xa_lock)
 #define xa_unlock(xa)		spin_unlock(&(xa)->xa_lock)
diff --git a/lib/Makefile b/lib/Makefile
index ca3f7ebb900d..057385f1f145 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -18,7 +18,7 @@ KCOV_INSTRUMENT_debugobjects.o := n
 KCOV_INSTRUMENT_dynamic_debug.o := n
 
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
-	 rbtree.o radix-tree.o timerqueue.o\
+	 rbtree.o radix-tree.o timerqueue.o xarray.o \
 	 idr.o int_sqrt.o extable.o \
 	 sha1.o chacha20.o irq_regs.o argv_split.o \
 	 flex_proportions.o ratelimit.o show_mem.o \
diff --git a/lib/idr.c b/lib/idr.c
index 88419fbc5737..9a366b5be2c2 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -39,8 +39,8 @@ int idr_alloc_u32(struct idr *idr, void *ptr, u32 *nextid,
 	unsigned int base = idr->idr_base;
 	unsigned int id = *nextid;
 
-	if (WARN_ON_ONCE(!(idr->idr_rt.gfp_mask & ROOT_IS_IDR)))
-		idr->idr_rt.gfp_mask |= IDR_RT_MARKER;
+	if (WARN_ON_ONCE(!(idr->idr_rt.xa_flags & ROOT_IS_IDR)))
+		idr->idr_rt.xa_flags |= IDR_RT_MARKER;
 
 	id = (id < base) ? 0 : id - base;
 	radix_tree_iter_init(&iter, id);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 59b28111eabc..299d4bdba109 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -124,7 +124,7 @@ static unsigned int radix_tree_descend(const struct radix_tree_node *parent,
 
 static inline gfp_t root_gfp_mask(const struct radix_tree_root *root)
 {
-	return root->gfp_mask & (__GFP_BITS_MASK & ~GFP_ZONEMASK);
+	return root->xa_flags & (__GFP_BITS_MASK & ~GFP_ZONEMASK);
 }
 
 static inline void tag_set(struct radix_tree_node *node, unsigned int tag,
@@ -147,32 +147,32 @@ static inline int tag_get(const struct radix_tree_node *node, unsigned int tag,
 
 static inline void root_tag_set(struct radix_tree_root *root, unsigned tag)
 {
-	root->gfp_mask |= (__force gfp_t)(1 << (tag + ROOT_TAG_SHIFT));
+	root->xa_flags |= (__force gfp_t)(1 << (tag + ROOT_TAG_SHIFT));
 }
 
 static inline void root_tag_clear(struct radix_tree_root *root, unsigned tag)
 {
-	root->gfp_mask &= (__force gfp_t)~(1 << (tag + ROOT_TAG_SHIFT));
+	root->xa_flags &= (__force gfp_t)~(1 << (tag + ROOT_TAG_SHIFT));
 }
 
 static inline void root_tag_clear_all(struct radix_tree_root *root)
 {
-	root->gfp_mask &= (1 << ROOT_TAG_SHIFT) - 1;
+	root->xa_flags &= (__force gfp_t)((1 << ROOT_TAG_SHIFT) - 1);
 }
 
 static inline int root_tag_get(const struct radix_tree_root *root, unsigned tag)
 {
-	return (__force int)root->gfp_mask & (1 << (tag + ROOT_TAG_SHIFT));
+	return (__force int)root->xa_flags & (1 << (tag + ROOT_TAG_SHIFT));
 }
 
 static inline unsigned root_tags_get(const struct radix_tree_root *root)
 {
-	return (__force unsigned)root->gfp_mask >> ROOT_TAG_SHIFT;
+	return (__force unsigned)root->xa_flags >> ROOT_TAG_SHIFT;
 }
 
 static inline bool is_idr(const struct radix_tree_root *root)
 {
-	return !!(root->gfp_mask & ROOT_IS_IDR);
+	return !!(root->xa_flags & ROOT_IS_IDR);
 }
 
 /*
@@ -291,12 +291,12 @@ static void dump_node(struct radix_tree_node *node, unsigned long index)
 /* For debug */
 static void radix_tree_dump(struct radix_tree_root *root)
 {
-	pr_debug("radix root: %p rnode %p tags %x\n",
-			root, root->rnode,
-			root->gfp_mask >> ROOT_TAG_SHIFT);
-	if (!radix_tree_is_internal_node(root->rnode))
+	pr_debug("radix root: %p xa_head %p tags %x\n",
+			root, root->xa_head,
+			root->xa_flags >> ROOT_TAG_SHIFT);
+	if (!radix_tree_is_internal_node(root->xa_head))
 		return;
-	dump_node(entry_to_node(root->rnode), 0);
+	dump_node(entry_to_node(root->xa_head), 0);
 }
 
 static void dump_ida_node(void *entry, unsigned long index)
@@ -340,9 +340,9 @@ static void dump_ida_node(void *entry, unsigned long index)
 static void ida_dump(struct ida *ida)
 {
 	struct radix_tree_root *root = &ida->ida_rt;
-	pr_debug("ida: %p node %p free %d\n", ida, root->rnode,
-				root->gfp_mask >> ROOT_TAG_SHIFT);
-	dump_ida_node(root->rnode, 0);
+	pr_debug("ida: %p node %p free %d\n", ida, root->xa_head,
+				root->xa_flags >> ROOT_TAG_SHIFT);
+	dump_ida_node(root->xa_head, 0);
 }
 #endif
 
@@ -576,7 +576,7 @@ int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order)
 static unsigned radix_tree_load_root(const struct radix_tree_root *root,
 		struct radix_tree_node **nodep, unsigned long *maxindex)
 {
-	struct radix_tree_node *node = rcu_dereference_raw(root->rnode);
+	struct radix_tree_node *node = rcu_dereference_raw(root->xa_head);
 
 	*nodep = node;
 
@@ -605,7 +605,7 @@ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp,
 	while (index > shift_maxindex(maxshift))
 		maxshift += RADIX_TREE_MAP_SHIFT;
 
-	entry = rcu_dereference_raw(root->rnode);
+	entry = rcu_dereference_raw(root->xa_head);
 	if (!entry && (!is_idr(root) || root_tag_get(root, IDR_FREE)))
 		goto out;
 
@@ -633,7 +633,7 @@ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp,
 		if (radix_tree_is_internal_node(entry)) {
 			entry_to_node(entry)->parent = node;
 		} else if (xa_is_value(entry)) {
-			/* Moving an exceptional root->rnode to a node */
+			/* Moving an exceptional root->xa_head to a node */
 			node->exceptional = 1;
 		}
 		/*
@@ -642,7 +642,7 @@ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp,
 		 */
 		node->slots[0] = (void __rcu *)entry;
 		entry = node_to_entry(node);
-		rcu_assign_pointer(root->rnode, entry);
+		rcu_assign_pointer(root->xa_head, entry);
 		shift += RADIX_TREE_MAP_SHIFT;
 	} while (shift <= maxshift);
 out:
@@ -659,7 +659,7 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root,
 	bool shrunk = false;
 
 	for (;;) {
-		struct radix_tree_node *node = rcu_dereference_raw(root->rnode);
+		struct radix_tree_node *node = rcu_dereference_raw(root->xa_head);
 		struct radix_tree_node *child;
 
 		if (!radix_tree_is_internal_node(node))
@@ -695,9 +695,9 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root,
 		 * moving the node from one part of the tree to another: if it
 		 * was safe to dereference the old pointer to it
 		 * (node->slots[0]), it will be safe to dereference the new
-		 * one (root->rnode) as far as dependent read barriers go.
+		 * one (root->xa_head) as far as dependent read barriers go.
 		 */
-		root->rnode = (void __rcu *)child;
+		root->xa_head = (void __rcu *)child;
 		if (is_idr(root) && !tag_get(node, IDR_FREE, 0))
 			root_tag_clear(root, IDR_FREE);
 
@@ -745,9 +745,8 @@ static bool delete_node(struct radix_tree_root *root,
 
 		if (node->count) {
 			if (node_to_entry(node) ==
-					rcu_dereference_raw(root->rnode))
-				deleted |= radix_tree_shrink(root,
-								update_node);
+					rcu_dereference_raw(root->xa_head))
+				deleted |= radix_tree_shrink(root, update_node);
 			return deleted;
 		}
 
@@ -762,7 +761,7 @@ static bool delete_node(struct radix_tree_root *root,
 			 */
 			if (!is_idr(root))
 				root_tag_clear_all(root);
-			root->rnode = NULL;
+			root->xa_head = NULL;
 		}
 
 		WARN_ON_ONCE(!list_empty(&node->private_list));
@@ -787,7 +786,7 @@ static bool delete_node(struct radix_tree_root *root,
  *	at position @index in the radix tree @root.
  *
  *	Until there is more than one item in the tree, no nodes are
- *	allocated and @root->rnode is used as a direct slot instead of
+ *	allocated and @root->xa_head is used as a direct slot instead of
  *	pointing to a node, in which case *@nodep will be NULL.
  *
  *	Returns -ENOMEM, or 0 for success.
@@ -797,7 +796,7 @@ int __radix_tree_create(struct radix_tree_root *root, unsigned long index,
 			void __rcu ***slotp)
 {
 	struct radix_tree_node *node = NULL, *child;
-	void __rcu **slot = (void __rcu **)&root->rnode;
+	void __rcu **slot = (void __rcu **)&root->xa_head;
 	unsigned long maxindex;
 	unsigned int shift, offset = 0;
 	unsigned long max = index | ((1UL << order) - 1);
@@ -813,7 +812,7 @@ int __radix_tree_create(struct radix_tree_root *root, unsigned long index,
 		if (error < 0)
 			return error;
 		shift = error;
-		child = rcu_dereference_raw(root->rnode);
+		child = rcu_dereference_raw(root->xa_head);
 	}
 
 	while (shift > order) {
@@ -1004,7 +1003,7 @@ EXPORT_SYMBOL(__radix_tree_insert);
  *	tree @root.
  *
  *	Until there is more than one item in the tree, no nodes are
- *	allocated and @root->rnode is used as a direct slot instead of
+ *	allocated and @root->xa_head is used as a direct slot instead of
  *	pointing to a node, in which case *@nodep will be NULL.
  */
 void *__radix_tree_lookup(const struct radix_tree_root *root,
@@ -1017,7 +1016,7 @@ void *__radix_tree_lookup(const struct radix_tree_root *root,
 
  restart:
 	parent = NULL;
-	slot = (void __rcu **)&root->rnode;
+	slot = (void __rcu **)&root->xa_head;
 	radix_tree_load_root(root, &node, &maxindex);
 	if (index > maxindex)
 		return NULL;
@@ -1168,9 +1167,9 @@ void __radix_tree_replace(struct radix_tree_root *root,
 	/*
 	 * This function supports replacing exceptional entries and
 	 * deleting entries, but that needs accounting against the
-	 * node unless the slot is root->rnode.
+	 * node unless the slot is root->xa_head.
 	 */
-	WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->rnode) &&
+	WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->xa_head) &&
 			(count || exceptional));
 	replace_slot(slot, item, node, count, exceptional);
 
@@ -1722,7 +1721,7 @@ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root,
 		iter->tags = 1;
 		iter->node = NULL;
 		__set_iter_shift(iter, 0);
-		return (void __rcu **)&root->rnode;
+		return (void __rcu **)&root->xa_head;
 	}
 
 	do {
@@ -2109,7 +2108,7 @@ void __rcu **idr_get_free(struct radix_tree_root *root,
 			      unsigned long max)
 {
 	struct radix_tree_node *node = NULL, *child;
-	void __rcu **slot = (void __rcu **)&root->rnode;
+	void __rcu **slot = (void __rcu **)&root->xa_head;
 	unsigned long maxindex, start = iter->next_index;
 	unsigned int shift, offset = 0;
 
@@ -2125,7 +2124,7 @@ void __rcu **idr_get_free(struct radix_tree_root *root,
 		if (error < 0)
 			return ERR_PTR(error);
 		shift = error;
-		child = rcu_dereference_raw(root->rnode);
+		child = rcu_dereference_raw(root->xa_head);
 	}
 	if (start == 0 && shift == 0)
 		shift = RADIX_TREE_MAP_SHIFT;
@@ -2190,10 +2189,10 @@ void __rcu **idr_get_free(struct radix_tree_root *root,
  */
 void idr_destroy(struct idr *idr)
 {
-	struct radix_tree_node *node = rcu_dereference_raw(idr->idr_rt.rnode);
+	struct radix_tree_node *node = rcu_dereference_raw(idr->idr_rt.xa_head);
 	if (radix_tree_is_internal_node(node))
 		radix_tree_free_nodes(node);
-	idr->idr_rt.rnode = NULL;
+	idr->idr_rt.xa_head = NULL;
 	root_tag_set(&idr->idr_rt, IDR_FREE);
 }
 EXPORT_SYMBOL(idr_destroy);
diff --git a/lib/xarray.c b/lib/xarray.c
new file mode 100644
index 000000000000..862f4c64c754
--- /dev/null
+++ b/lib/xarray.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * XArray implementation
+ * Copyright (c) 2017 Microsoft Corporation
+ * Author: Matthew Wilcox <willy@infradead.org>
+ */
+
+#include <linux/export.h>
+#include <linux/xarray.h>
+
+/*
+ * Coding conventions in this file:
+ *
+ * @xa is used to refer to the entire xarray.
+ * @xas is the 'xarray operation state'.  It may be either a pointer to
+ * an xa_state, or an xa_state stored on the stack.  This is an unfortunate
+ * ambiguity.
+ * @index is the index of the entry being operated on
+ * @mark is an xa_mark_t; a small number indicating one of the mark bits.
+ * @node refers to an xa_node; usually the primary one being operated on by
+ * this function.
+ * @offset is the index into the slots array inside an xa_node.
+ * @parent refers to the @xa_node closer to the head than @node.
+ * @entry refers to something stored in a slot in the xarray
+ */
+
+/**
+ * xa_init_flags() - Initialise an empty XArray with flags.
+ * @xa: XArray.
+ * @flags: XA_FLAG values.
+ *
+ * If you need to initialise an XArray with special flags (eg you need
+ * to take the lock from interrupt context), use this function instead
+ * of xa_init().
+ *
+ * Context: Any context.
+ */
+void xa_init_flags(struct xarray *xa, gfp_t flags)
+{
+	spin_lock_init(&xa->xa_lock);
+	xa->xa_flags = flags;
+	xa->xa_head = NULL;
+}
+EXPORT_SYMBOL(xa_init_flags);
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index 12adcf9ffe86..c0cf1c79efd5 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -5,7 +5,7 @@ CFLAGS += -I. -I../../include -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address \
 LDFLAGS += -fsanitize=address -fsanitize=undefined
 LDLIBS+= -lpthread -lurcu
 TARGETS = main idr-test multiorder
-CORE_OFILES := radix-tree.o idr.o linux.o test.o find_bit.o
+CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o
 OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \
 	 tag_check.o multiorder.o idr-test.o iteration_check.o benchmark.o
 
@@ -35,6 +35,7 @@ vpath %.c ../../lib
 $(OFILES): Makefile *.h */*.h generated/map-shift.h \
 	../../include/linux/*.h \
 	../../include/asm/*.h \
+	../../../include/linux/xarray.h \
 	../../../include/linux/radix-tree.h \
 	../../../include/linux/idr.h
 
@@ -44,6 +45,8 @@ radix-tree.c: ../../../lib/radix-tree.c
 idr.c: ../../../lib/idr.c
 	sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@
 
+xarray.o: ../../../lib/xarray.c
+
 generated/map-shift.h:
 	@if ! grep -qws $(SHIFT) generated/map-shift.h; then		\
 		echo "#define XA_CHUNK_SHIFT $(SHIFT)" >		\
diff --git a/tools/testing/radix-tree/linux/bug.h b/tools/testing/radix-tree/linux/bug.h
index 23b8ed52f8c8..03dc8a57eb99 100644
--- a/tools/testing/radix-tree/linux/bug.h
+++ b/tools/testing/radix-tree/linux/bug.h
@@ -1 +1,2 @@
+#include <stdio.h>
 #include "asm/bug.h"
diff --git a/tools/testing/radix-tree/linux/kconfig.h b/tools/testing/radix-tree/linux/kconfig.h
new file mode 100644
index 000000000000..6c8675859913
--- /dev/null
+++ b/tools/testing/radix-tree/linux/kconfig.h
@@ -0,0 +1 @@
+#include "../../../../include/linux/kconfig.h"
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 2b4f4dba1882..080aea450430 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -192,13 +192,13 @@ static void multiorder_shrink(unsigned long index, int order)
 
 	assert(item_insert_order(&tree, 0, order) == 0);
 
-	node = tree.rnode;
+	node = tree.xa_head;
 
 	assert(item_insert(&tree, index) == 0);
-	assert(node != tree.rnode);
+	assert(node != tree.xa_head);
 
 	assert(item_delete(&tree, index) != 0);
-	assert(node == tree.rnode);
+	assert(node == tree.xa_head);
 
 	for (i = 0; i < max; i++) {
 		struct item *item = item_lookup(&tree, i);
diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index 62de66c314b7..70ddf964d51c 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -281,7 +281,7 @@ static int verify_node(struct radix_tree_node *slot, unsigned int tag,
 
 void verify_tag_consistency(struct radix_tree_root *root, unsigned int tag)
 {
-	struct radix_tree_node *node = root->rnode;
+	struct radix_tree_node *node = root->xa_head;
 	if (!radix_tree_is_internal_node(node))
 		return;
 	verify_node(node, tag, !!root_tag_get(root, tag));
@@ -311,13 +311,13 @@ void item_kill_tree(struct radix_tree_root *root)
 		}
 	}
 	assert(radix_tree_gang_lookup(root, (void **)items, 0, 32) == 0);
-	assert(root->rnode == NULL);
+	assert(root->xa_head == NULL);
 }
 
 void tree_verify_min_height(struct radix_tree_root *root, int maxindex)
 {
 	unsigned shift;
-	struct radix_tree_node *node = root->rnode;
+	struct radix_tree_node *node = root->xa_head;
 	if (!radix_tree_is_internal_node(node)) {
 		assert(maxindex == 0);
 		return;
diff --git a/tools/testing/radix-tree/xarray.c b/tools/testing/radix-tree/xarray.c
new file mode 100644
index 000000000000..9bbd667172a7
--- /dev/null
+++ b/tools/testing/radix-tree/xarray.c
@@ -0,0 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * xarray.c: Userspace shim for XArray test-suite
+ * Copyright (c) 2018 Matthew Wilcox <willy@infradead.org>
+ */
+
+#include "../../../lib/xarray.c"
-- 
cgit 


From 01959dfe771c6893365482ec78dc1d9cbbbe6de8 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Thu, 9 Nov 2017 09:23:56 -0500
Subject: xarray: Define struct xa_node

This is a direct replacement for struct radix_tree_node.  A couple of
struct members have changed name, so convert those.  Use a #define so
that radix tree users continue to work without change.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
Reviewed-by: Josef Bacik <jbacik@fb.com>
---
 include/linux/radix-tree.h            | 29 +++------------------
 include/linux/xarray.h                | 27 ++++++++++++++++++++
 lib/radix-tree.c                      | 48 +++++++++++++++++------------------
 mm/workingset.c                       | 16 ++++++------
 tools/testing/radix-tree/multiorder.c | 30 +++++++++++-----------
 5 files changed, 77 insertions(+), 73 deletions(-)

(limited to 'tools/testing')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 0b080bd88ab7..15388b7e38b9 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -32,6 +32,7 @@
 
 /* Keep unconverted code working */
 #define radix_tree_root		xarray
+#define radix_tree_node		xa_node
 
 /*
  * The bottom two bits of the slot determine how the remaining bits in the
@@ -60,41 +61,17 @@ static inline bool radix_tree_is_internal_node(void *ptr)
 
 /*** radix-tree API starts here ***/
 
-#define RADIX_TREE_MAX_TAGS 3
-
 #define RADIX_TREE_MAP_SHIFT	XA_CHUNK_SHIFT
 #define RADIX_TREE_MAP_SIZE	(1UL << RADIX_TREE_MAP_SHIFT)
 #define RADIX_TREE_MAP_MASK	(RADIX_TREE_MAP_SIZE-1)
 
-#define RADIX_TREE_TAG_LONGS	\
-	((RADIX_TREE_MAP_SIZE + BITS_PER_LONG - 1) / BITS_PER_LONG)
+#define RADIX_TREE_MAX_TAGS	XA_MAX_MARKS
+#define RADIX_TREE_TAG_LONGS	XA_MARK_LONGS
 
 #define RADIX_TREE_INDEX_BITS  (8 /* CHAR_BIT */ * sizeof(unsigned long))
 #define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \
 					  RADIX_TREE_MAP_SHIFT))
 
-/*
- * @count is the count of every non-NULL element in the ->slots array
- * whether that is a value entry, a retry entry, a user pointer,
- * a sibling entry or a pointer to the next level of the tree.
- * @exceptional is the count of every element in ->slots which is
- * either a value entry or a sibling of a value entry.
- */
-struct radix_tree_node {
-	unsigned char	shift;		/* Bits remaining in each slot */
-	unsigned char	offset;		/* Slot offset in parent */
-	unsigned char	count;		/* Total entry count */
-	unsigned char	exceptional;	/* Exceptional entry count */
-	struct radix_tree_node *parent;		/* Used when ascending tree */
-	struct radix_tree_root *root;		/* The tree we belong to */
-	union {
-		struct list_head private_list;	/* For tree user */
-		struct rcu_head	rcu_head;	/* Used when freeing node */
-	};
-	void __rcu	*slots[RADIX_TREE_MAP_SIZE];
-	unsigned long	tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS];
-};
-
 /* The IDR tag is stored in the low bits of xa_flags */
 #define ROOT_IS_IDR	((__force gfp_t)4)
 /* The top bits of xa_flags are used to store the root tags */
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 9122cf8bf52a..52141dfc5a90 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -252,6 +252,33 @@ static inline void xa_init(struct xarray *xa)
 #endif
 #define XA_CHUNK_SIZE		(1UL << XA_CHUNK_SHIFT)
 #define XA_CHUNK_MASK		(XA_CHUNK_SIZE - 1)
+#define XA_MAX_MARKS		3
+#define XA_MARK_LONGS		DIV_ROUND_UP(XA_CHUNK_SIZE, BITS_PER_LONG)
+
+/*
+ * @count is the count of every non-NULL element in the ->slots array
+ * whether that is a value entry, a retry entry, a user pointer,
+ * a sibling entry or a pointer to the next level of the tree.
+ * @nr_values is the count of every element in ->slots which is
+ * either a value entry or a sibling of a value entry.
+ */
+struct xa_node {
+	unsigned char	shift;		/* Bits remaining in each slot */
+	unsigned char	offset;		/* Slot offset in parent */
+	unsigned char	count;		/* Total entry count */
+	unsigned char	nr_values;	/* Value entry count */
+	struct xa_node __rcu *parent;	/* NULL at top of tree */
+	struct xarray	*array;		/* The array we belong to */
+	union {
+		struct list_head private_list;	/* For tree user */
+		struct rcu_head	rcu_head;	/* Used when freeing node */
+	};
+	void __rcu	*slots[XA_CHUNK_SIZE];
+	union {
+		unsigned long	tags[XA_MAX_MARKS][XA_MARK_LONGS];
+		unsigned long	marks[XA_MAX_MARKS][XA_MARK_LONGS];
+	};
+};
 
 /* Private */
 static inline bool xa_is_node(const void *entry)
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 299d4bdba109..8a568cea1237 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -260,11 +260,11 @@ static void dump_node(struct radix_tree_node *node, unsigned long index)
 {
 	unsigned long i;
 
-	pr_debug("radix node: %p offset %d indices %lu-%lu parent %p tags %lx %lx %lx shift %d count %d exceptional %d\n",
+	pr_debug("radix node: %p offset %d indices %lu-%lu parent %p tags %lx %lx %lx shift %d count %d nr_values %d\n",
 		node, node->offset, index, index | node_maxindex(node),
 		node->parent,
 		node->tags[0][0], node->tags[1][0], node->tags[2][0],
-		node->shift, node->count, node->exceptional);
+		node->shift, node->count, node->nr_values);
 
 	for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) {
 		unsigned long first = index | (i << node->shift);
@@ -354,7 +354,7 @@ static struct radix_tree_node *
 radix_tree_node_alloc(gfp_t gfp_mask, struct radix_tree_node *parent,
 			struct radix_tree_root *root,
 			unsigned int shift, unsigned int offset,
-			unsigned int count, unsigned int exceptional)
+			unsigned int count, unsigned int nr_values)
 {
 	struct radix_tree_node *ret = NULL;
 
@@ -401,9 +401,9 @@ out:
 		ret->shift = shift;
 		ret->offset = offset;
 		ret->count = count;
-		ret->exceptional = exceptional;
+		ret->nr_values = nr_values;
 		ret->parent = parent;
-		ret->root = root;
+		ret->array = root;
 	}
 	return ret;
 }
@@ -633,8 +633,8 @@ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp,
 		if (radix_tree_is_internal_node(entry)) {
 			entry_to_node(entry)->parent = node;
 		} else if (xa_is_value(entry)) {
-			/* Moving an exceptional root->xa_head to a node */
-			node->exceptional = 1;
+			/* Moving a value entry root->xa_head to a node */
+			node->nr_values = 1;
 		}
 		/*
 		 * entry was already in the radix tree, so we do not need
@@ -928,12 +928,12 @@ static inline int insert_entries(struct radix_tree_node *node,
 		if (xa_is_node(old))
 			radix_tree_free_nodes(old);
 		if (xa_is_value(old))
-			node->exceptional--;
+			node->nr_values--;
 	}
 	if (node) {
 		node->count += n;
 		if (xa_is_value(item))
-			node->exceptional += n;
+			node->nr_values += n;
 	}
 	return n;
 }
@@ -947,7 +947,7 @@ static inline int insert_entries(struct radix_tree_node *node,
 	if (node) {
 		node->count++;
 		if (xa_is_value(item))
-			node->exceptional++;
+			node->nr_values++;
 	}
 	return 1;
 }
@@ -1083,7 +1083,7 @@ void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index)
 EXPORT_SYMBOL(radix_tree_lookup);
 
 static inline void replace_sibling_entries(struct radix_tree_node *node,
-				void __rcu **slot, int count, int exceptional)
+				void __rcu **slot, int count, int values)
 {
 #ifdef CONFIG_RADIX_TREE_MULTIORDER
 	unsigned offset = get_slot_offset(node, slot);
@@ -1096,18 +1096,18 @@ static inline void replace_sibling_entries(struct radix_tree_node *node,
 			node->slots[offset] = NULL;
 			node->count--;
 		}
-		node->exceptional += exceptional;
+		node->nr_values += values;
 	}
 #endif
 }
 
 static void replace_slot(void __rcu **slot, void *item,
-		struct radix_tree_node *node, int count, int exceptional)
+		struct radix_tree_node *node, int count, int values)
 {
-	if (node && (count || exceptional)) {
+	if (node && (count || values)) {
 		node->count += count;
-		node->exceptional += exceptional;
-		replace_sibling_entries(node, slot, count, exceptional);
+		node->nr_values += values;
+		replace_sibling_entries(node, slot, count, values);
 	}
 
 	rcu_assign_pointer(*slot, item);
@@ -1161,17 +1161,17 @@ void __radix_tree_replace(struct radix_tree_root *root,
 			  radix_tree_update_node_t update_node)
 {
 	void *old = rcu_dereference_raw(*slot);
-	int exceptional = !!xa_is_value(item) - !!xa_is_value(old);
+	int values = !!xa_is_value(item) - !!xa_is_value(old);
 	int count = calculate_count(root, node, slot, item, old);
 
 	/*
-	 * This function supports replacing exceptional entries and
+	 * This function supports replacing value entries and
 	 * deleting entries, but that needs accounting against the
 	 * node unless the slot is root->xa_head.
 	 */
 	WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->xa_head) &&
-			(count || exceptional));
-	replace_slot(slot, item, node, count, exceptional);
+			(count || values));
+	replace_slot(slot, item, node, count, values);
 
 	if (!node)
 		return;
@@ -1193,7 +1193,7 @@ void __radix_tree_replace(struct radix_tree_root *root,
  * across slot lookup and replacement.
  *
  * NOTE: This cannot be used to switch between non-entries (empty slots),
- * regular entries, and exceptional entries, as that requires accounting
+ * regular entries, and value entries, as that requires accounting
  * inside the radix tree node. When switching from one type of entry or
  * deleting, use __radix_tree_lookup() and __radix_tree_replace() or
  * radix_tree_iter_replace().
@@ -1301,7 +1301,7 @@ int radix_tree_split(struct radix_tree_root *root, unsigned long index,
 		rcu_assign_pointer(parent->slots[end], RADIX_TREE_RETRY);
 	}
 	rcu_assign_pointer(parent->slots[offset], RADIX_TREE_RETRY);
-	parent->exceptional -= (end - offset);
+	parent->nr_values -= (end - offset);
 
 	if (order == parent->shift)
 		return 0;
@@ -1961,7 +1961,7 @@ static bool __radix_tree_delete(struct radix_tree_root *root,
 				struct radix_tree_node *node, void __rcu **slot)
 {
 	void *old = rcu_dereference_raw(*slot);
-	int exceptional = xa_is_value(old) ? -1 : 0;
+	int values = xa_is_value(old) ? -1 : 0;
 	unsigned offset = get_slot_offset(node, slot);
 	int tag;
 
@@ -1971,7 +1971,7 @@ static bool __radix_tree_delete(struct radix_tree_root *root,
 		for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
 			node_tag_clear(root, node, tag, offset);
 
-	replace_slot(slot, NULL, node, -1, exceptional);
+	replace_slot(slot, NULL, node, -1, values);
 	return node && delete_node(root, node, NULL);
 }
 
diff --git a/mm/workingset.c b/mm/workingset.c
index bb109b3afac2..c201cbb8c00f 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -349,7 +349,7 @@ void workingset_update_node(struct radix_tree_node *node)
 	 * already where they should be. The list_empty() test is safe
 	 * as node->private_list is protected by the i_pages lock.
 	 */
-	if (node->count && node->count == node->exceptional) {
+	if (node->count && node->count == node->nr_values) {
 		if (list_empty(&node->private_list))
 			list_lru_add(&shadow_nodes, &node->private_list);
 	} else {
@@ -428,8 +428,8 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 	 * to reclaim, take the node off-LRU, and drop the lru_lock.
 	 */
 
-	node = container_of(item, struct radix_tree_node, private_list);
-	mapping = container_of(node->root, struct address_space, i_pages);
+	node = container_of(item, struct xa_node, private_list);
+	mapping = container_of(node->array, struct address_space, i_pages);
 
 	/* Coming from the list, invert the lock order */
 	if (!xa_trylock(&mapping->i_pages)) {
@@ -446,25 +446,25 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 	 * no pages, so we expect to be able to remove them all and
 	 * delete and free the empty node afterwards.
 	 */
-	if (WARN_ON_ONCE(!node->exceptional))
+	if (WARN_ON_ONCE(!node->nr_values))
 		goto out_invalid;
-	if (WARN_ON_ONCE(node->count != node->exceptional))
+	if (WARN_ON_ONCE(node->count != node->nr_values))
 		goto out_invalid;
 	for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) {
 		if (node->slots[i]) {
 			if (WARN_ON_ONCE(!xa_is_value(node->slots[i])))
 				goto out_invalid;
-			if (WARN_ON_ONCE(!node->exceptional))
+			if (WARN_ON_ONCE(!node->nr_values))
 				goto out_invalid;
 			if (WARN_ON_ONCE(!mapping->nrexceptional))
 				goto out_invalid;
 			node->slots[i] = NULL;
-			node->exceptional--;
+			node->nr_values--;
 			node->count--;
 			mapping->nrexceptional--;
 		}
 	}
-	if (WARN_ON_ONCE(node->exceptional))
+	if (WARN_ON_ONCE(node->nr_values))
 		goto out_invalid;
 	inc_lruvec_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM);
 	__radix_tree_delete_node(&mapping->i_pages, node,
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 080aea450430..60786fa55302 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -393,7 +393,7 @@ static void multiorder_join2(unsigned order1, unsigned order2)
 	radix_tree_insert(&tree, 1 << order2, xa_mk_value(5));
 	item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL);
 	assert(item2 == xa_mk_value(5));
-	assert(node->exceptional == 1);
+	assert(node->nr_values == 1);
 
 	item2 = radix_tree_lookup(&tree, 0);
 	free(item2);
@@ -401,7 +401,7 @@ static void multiorder_join2(unsigned order1, unsigned order2)
 	radix_tree_join(&tree, 0, order1, item1);
 	item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL);
 	assert(item2 == item1);
-	assert(node->exceptional == 0);
+	assert(node->nr_values == 0);
 	item_kill_tree(&tree);
 }
 
@@ -409,7 +409,7 @@ static void multiorder_join2(unsigned order1, unsigned order2)
  * This test revealed an accounting bug for value entries at one point.
  * Nodes were being freed back into the pool with an elevated exception count
  * by radix_tree_join() and then radix_tree_split() was failing to zero the
- * count of exceptional entries.
+ * count of value entries.
  */
 static void multiorder_join3(unsigned int order)
 {
@@ -433,7 +433,7 @@ static void multiorder_join3(unsigned int order)
 	}
 
 	__radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(node->exceptional == node->count);
+	assert(node->nr_values == node->count);
 
 	item_kill_tree(&tree);
 }
@@ -520,7 +520,7 @@ static void __multiorder_split2(int old_order, int new_order)
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
 	assert(item == xa_mk_value(5));
-	assert(node->exceptional > 0);
+	assert(node->nr_values > 0);
 
 	radix_tree_split(&tree, 0, new_order);
 	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
@@ -530,7 +530,7 @@ static void __multiorder_split2(int old_order, int new_order)
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
 	assert(item != xa_mk_value(5));
-	assert(node->exceptional == 0);
+	assert(node->nr_values == 0);
 
 	item_kill_tree(&tree);
 }
@@ -547,7 +547,7 @@ static void __multiorder_split3(int old_order, int new_order)
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
 	assert(item == xa_mk_value(5));
-	assert(node->exceptional > 0);
+	assert(node->nr_values > 0);
 
 	radix_tree_split(&tree, 0, new_order);
 	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
@@ -556,7 +556,7 @@ static void __multiorder_split3(int old_order, int new_order)
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
 	assert(item == xa_mk_value(7));
-	assert(node->exceptional > 0);
+	assert(node->nr_values > 0);
 
 	item_kill_tree(&tree);
 
@@ -564,7 +564,7 @@ static void __multiorder_split3(int old_order, int new_order)
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
 	assert(item == xa_mk_value(5));
-	assert(node->exceptional > 0);
+	assert(node->nr_values > 0);
 
 	radix_tree_split(&tree, 0, new_order);
 	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
@@ -577,13 +577,13 @@ static void __multiorder_split3(int old_order, int new_order)
 
 	item = __radix_tree_lookup(&tree, 1 << new_order, &node, NULL);
 	assert(item == xa_mk_value(7));
-	assert(node->count == node->exceptional);
+	assert(node->count == node->nr_values);
 	do {
 		node = node->parent;
 		if (!node)
 			break;
 		assert(node->count == 1);
-		assert(node->exceptional == 0);
+		assert(node->nr_values == 0);
 	} while (1);
 
 	item_kill_tree(&tree);
@@ -611,15 +611,15 @@ static void multiorder_account(void)
 
 	__radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5));
 	__radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(node->count == node->exceptional * 2);
+	assert(node->count == node->nr_values * 2);
 	radix_tree_delete(&tree, 1 << 5);
-	assert(node->exceptional == 0);
+	assert(node->nr_values == 0);
 
 	__radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5));
 	__radix_tree_lookup(&tree, 1 << 5, &node, &slot);
-	assert(node->count == node->exceptional * 2);
+	assert(node->count == node->nr_values * 2);
 	__radix_tree_replace(&tree, node, slot, NULL, NULL);
-	assert(node->exceptional == 0);
+	assert(node->nr_values == 0);
 
 	item_kill_tree(&tree);
 }
-- 
cgit 


From ad3d6c7263e368abdc151e1cc13dc78aa39cc7a7 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Tue, 7 Nov 2017 14:57:46 -0500
Subject: xarray: Add XArray load operation

The xa_load function brings with it a lot of infrastructure; xa_empty(),
xa_is_err(), and large chunks of the XArray advanced API that are used
to implement xa_load.

As the test-suite demonstrates, it is possible to use the XArray functions
on a radix tree.  The radix tree functions depend on the GFP flags being
stored in the root of the tree, so it's not possible to use the radix
tree functions on an XArray.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 include/linux/xarray.h                    | 336 ++++++++++++++++++++++++++++++
 lib/Kconfig.debug                         |   3 +
 lib/Makefile                              |   1 +
 lib/radix-tree.c                          |  43 ----
 lib/test_xarray.c                         |  87 ++++++++
 lib/xarray.c                              | 195 +++++++++++++++++
 tools/include/linux/kernel.h              |   1 +
 tools/testing/radix-tree/.gitignore       |   1 +
 tools/testing/radix-tree/Makefile         |   6 +-
 tools/testing/radix-tree/linux/kernel.h   |   1 +
 tools/testing/radix-tree/linux/rcupdate.h |   2 +
 tools/testing/radix-tree/main.c           |   1 +
 tools/testing/radix-tree/test.h           |   1 +
 tools/testing/radix-tree/xarray.c         |  28 +++
 14 files changed, 661 insertions(+), 45 deletions(-)
 create mode 100644 lib/test_xarray.c

(limited to 'tools/testing')

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 52141dfc5a90..a0df8217068c 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -12,6 +12,8 @@
 #include <linux/bug.h>
 #include <linux/compiler.h>
 #include <linux/kconfig.h>
+#include <linux/kernel.h>
+#include <linux/rcupdate.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
 
@@ -30,6 +32,10 @@
  *
  * 0-62: Sibling entries
  * 256: Retry entry
+ *
+ * Errors are also represented as internal entries, but use the negative
+ * space (-4094 to -2).  They're never stored in the slots array; only
+ * returned by the normal API.
  */
 
 #define BITS_PER_XA_VALUE	(BITS_PER_LONG - 1)
@@ -155,6 +161,42 @@ static inline bool xa_is_internal(const void *entry)
 	return ((unsigned long)entry & 3) == 2;
 }
 
+/**
+ * xa_is_err() - Report whether an XArray operation returned an error
+ * @entry: Result from calling an XArray function
+ *
+ * If an XArray operation cannot complete an operation, it will return
+ * a special value indicating an error.  This function tells you
+ * whether an error occurred; xa_err() tells you which error occurred.
+ *
+ * Context: Any context.
+ * Return: %true if the entry indicates an error.
+ */
+static inline bool xa_is_err(const void *entry)
+{
+	return unlikely(xa_is_internal(entry));
+}
+
+/**
+ * xa_err() - Turn an XArray result into an errno.
+ * @entry: Result from calling an XArray function.
+ *
+ * If an XArray operation cannot complete an operation, it will return
+ * a special pointer value which encodes an errno.  This function extracts
+ * the errno from the pointer value, or returns 0 if the pointer does not
+ * represent an errno.
+ *
+ * Context: Any context.
+ * Return: A negative errno or 0.
+ */
+static inline int xa_err(void *entry)
+{
+	/* xa_to_internal() would not do sign extension. */
+	if (xa_is_err(entry))
+		return (long)entry >> 2;
+	return 0;
+}
+
 /**
  * struct xarray - The anchor of the XArray.
  * @xa_lock: Lock that protects the contents of the XArray.
@@ -209,6 +251,7 @@ struct xarray {
 #define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0)
 
 void xa_init_flags(struct xarray *, gfp_t flags);
+void *xa_load(struct xarray *, unsigned long index);
 
 /**
  * xa_init() - Initialise an empty XArray.
@@ -223,6 +266,18 @@ static inline void xa_init(struct xarray *xa)
 	xa_init_flags(xa, 0);
 }
 
+/**
+ * xa_empty() - Determine if an array has any present entries.
+ * @xa: XArray.
+ *
+ * Context: Any context.
+ * Return: %true if the array contains only NULL pointers.
+ */
+static inline bool xa_empty(const struct xarray *xa)
+{
+	return xa->xa_head == NULL;
+}
+
 #define xa_trylock(xa)		spin_trylock(&(xa)->xa_lock)
 #define xa_lock(xa)		spin_lock(&(xa)->xa_lock)
 #define xa_unlock(xa)		spin_unlock(&(xa)->xa_lock)
@@ -280,6 +335,65 @@ struct xa_node {
 	};
 };
 
+void xa_dump(const struct xarray *);
+void xa_dump_node(const struct xa_node *);
+
+#ifdef XA_DEBUG
+#define XA_BUG_ON(xa, x) do {					\
+		if (x) {					\
+			xa_dump(xa);				\
+			BUG();					\
+		}						\
+	} while (0)
+#define XA_NODE_BUG_ON(node, x) do {				\
+		if (x) {					\
+			if (node) xa_dump_node(node);		\
+			BUG();					\
+		}						\
+	} while (0)
+#else
+#define XA_BUG_ON(xa, x)	do { } while (0)
+#define XA_NODE_BUG_ON(node, x)	do { } while (0)
+#endif
+
+/* Private */
+static inline void *xa_head(const struct xarray *xa)
+{
+	return rcu_dereference_check(xa->xa_head,
+						lockdep_is_held(&xa->xa_lock));
+}
+
+/* Private */
+static inline void *xa_head_locked(const struct xarray *xa)
+{
+	return rcu_dereference_protected(xa->xa_head,
+						lockdep_is_held(&xa->xa_lock));
+}
+
+/* Private */
+static inline void *xa_entry(const struct xarray *xa,
+				const struct xa_node *node, unsigned int offset)
+{
+	XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE);
+	return rcu_dereference_check(node->slots[offset],
+						lockdep_is_held(&xa->xa_lock));
+}
+
+/* Private */
+static inline void *xa_entry_locked(const struct xarray *xa,
+				const struct xa_node *node, unsigned int offset)
+{
+	XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE);
+	return rcu_dereference_protected(node->slots[offset],
+						lockdep_is_held(&xa->xa_lock));
+}
+
+/* Private */
+static inline struct xa_node *xa_to_node(const void *entry)
+{
+	return (struct xa_node *)((unsigned long)entry - 2);
+}
+
 /* Private */
 static inline bool xa_is_node(const void *entry)
 {
@@ -312,4 +426,226 @@ static inline bool xa_is_sibling(const void *entry)
 
 #define XA_RETRY_ENTRY		xa_mk_internal(256)
 
+/**
+ * xa_is_retry() - Is the entry a retry entry?
+ * @entry: Entry retrieved from the XArray
+ *
+ * Return: %true if the entry is a retry entry.
+ */
+static inline bool xa_is_retry(const void *entry)
+{
+	return unlikely(entry == XA_RETRY_ENTRY);
+}
+
+/**
+ * typedef xa_update_node_t - A callback function from the XArray.
+ * @node: The node which is being processed
+ *
+ * This function is called every time the XArray updates the count of
+ * present and value entries in a node.  It allows advanced users to
+ * maintain the private_list in the node.
+ *
+ * Context: The xa_lock is held and interrupts may be disabled.
+ *	    Implementations should not drop the xa_lock, nor re-enable
+ *	    interrupts.
+ */
+typedef void (*xa_update_node_t)(struct xa_node *node);
+
+/*
+ * The xa_state is opaque to its users.  It contains various different pieces
+ * of state involved in the current operation on the XArray.  It should be
+ * declared on the stack and passed between the various internal routines.
+ * The various elements in it should not be accessed directly, but only
+ * through the provided accessor functions.  The below documentation is for
+ * the benefit of those working on the code, not for users of the XArray.
+ *
+ * @xa_node usually points to the xa_node containing the slot we're operating
+ * on (and @xa_offset is the offset in the slots array).  If there is a
+ * single entry in the array at index 0, there are no allocated xa_nodes to
+ * point to, and so we store %NULL in @xa_node.  @xa_node is set to
+ * the value %XAS_RESTART if the xa_state is not walked to the correct
+ * position in the tree of nodes for this operation.  If an error occurs
+ * during an operation, it is set to an %XAS_ERROR value.  If we run off the
+ * end of the allocated nodes, it is set to %XAS_BOUNDS.
+ */
+struct xa_state {
+	struct xarray *xa;
+	unsigned long xa_index;
+	unsigned char xa_shift;
+	unsigned char xa_sibs;
+	unsigned char xa_offset;
+	unsigned char xa_pad;		/* Helps gcc generate better code */
+	struct xa_node *xa_node;
+	struct xa_node *xa_alloc;
+	xa_update_node_t xa_update;
+};
+
+/*
+ * We encode errnos in the xas->xa_node.  If an error has happened, we need to
+ * drop the lock to fix it, and once we've done so the xa_state is invalid.
+ */
+#define XA_ERROR(errno) ((struct xa_node *)(((unsigned long)errno << 2) | 2UL))
+#define XAS_BOUNDS	((struct xa_node *)1UL)
+#define XAS_RESTART	((struct xa_node *)3UL)
+
+#define __XA_STATE(array, index, shift, sibs)  {	\
+	.xa = array,					\
+	.xa_index = index,				\
+	.xa_shift = shift,				\
+	.xa_sibs = sibs,				\
+	.xa_offset = 0,					\
+	.xa_pad = 0,					\
+	.xa_node = XAS_RESTART,				\
+	.xa_alloc = NULL,				\
+	.xa_update = NULL				\
+}
+
+/**
+ * XA_STATE() - Declare an XArray operation state.
+ * @name: Name of this operation state (usually xas).
+ * @array: Array to operate on.
+ * @index: Initial index of interest.
+ *
+ * Declare and initialise an xa_state on the stack.
+ */
+#define XA_STATE(name, array, index)				\
+	struct xa_state name = __XA_STATE(array, index, 0, 0)
+
+/**
+ * XA_STATE_ORDER() - Declare an XArray operation state.
+ * @name: Name of this operation state (usually xas).
+ * @array: Array to operate on.
+ * @index: Initial index of interest.
+ * @order: Order of entry.
+ *
+ * Declare and initialise an xa_state on the stack.  This variant of
+ * XA_STATE() allows you to specify the 'order' of the element you
+ * want to operate on.`
+ */
+#define XA_STATE_ORDER(name, array, index, order)		\
+	struct xa_state name = __XA_STATE(array,		\
+			(index >> order) << order,		\
+			order - (order % XA_CHUNK_SHIFT),	\
+			(1U << (order % XA_CHUNK_SHIFT)) - 1)
+
+#define xas_marked(xas, mark)	xa_marked((xas)->xa, (mark))
+#define xas_trylock(xas)	xa_trylock((xas)->xa)
+#define xas_lock(xas)		xa_lock((xas)->xa)
+#define xas_unlock(xas)		xa_unlock((xas)->xa)
+#define xas_lock_bh(xas)	xa_lock_bh((xas)->xa)
+#define xas_unlock_bh(xas)	xa_unlock_bh((xas)->xa)
+#define xas_lock_irq(xas)	xa_lock_irq((xas)->xa)
+#define xas_unlock_irq(xas)	xa_unlock_irq((xas)->xa)
+#define xas_lock_irqsave(xas, flags) \
+				xa_lock_irqsave((xas)->xa, flags)
+#define xas_unlock_irqrestore(xas, flags) \
+				xa_unlock_irqrestore((xas)->xa, flags)
+
+/**
+ * xas_error() - Return an errno stored in the xa_state.
+ * @xas: XArray operation state.
+ *
+ * Return: 0 if no error has been noted.  A negative errno if one has.
+ */
+static inline int xas_error(const struct xa_state *xas)
+{
+	return xa_err(xas->xa_node);
+}
+
+/**
+ * xas_set_err() - Note an error in the xa_state.
+ * @xas: XArray operation state.
+ * @err: Negative error number.
+ *
+ * Only call this function with a negative @err; zero or positive errors
+ * will probably not behave the way you think they should.  If you want
+ * to clear the error from an xa_state, use xas_reset().
+ */
+static inline void xas_set_err(struct xa_state *xas, long err)
+{
+	xas->xa_node = XA_ERROR(err);
+}
+
+/**
+ * xas_invalid() - Is the xas in a retry or error state?
+ * @xas: XArray operation state.
+ *
+ * Return: %true if the xas cannot be used for operations.
+ */
+static inline bool xas_invalid(const struct xa_state *xas)
+{
+	return (unsigned long)xas->xa_node & 3;
+}
+
+/**
+ * xas_valid() - Is the xas a valid cursor into the array?
+ * @xas: XArray operation state.
+ *
+ * Return: %true if the xas can be used for operations.
+ */
+static inline bool xas_valid(const struct xa_state *xas)
+{
+	return !xas_invalid(xas);
+}
+
+/**
+ * xas_reset() - Reset an XArray operation state.
+ * @xas: XArray operation state.
+ *
+ * Resets the error or walk state of the @xas so future walks of the
+ * array will start from the root.  Use this if you have dropped the
+ * xarray lock and want to reuse the xa_state.
+ *
+ * Context: Any context.
+ */
+static inline void xas_reset(struct xa_state *xas)
+{
+	xas->xa_node = XAS_RESTART;
+}
+
+/**
+ * xas_retry() - Retry the operation if appropriate.
+ * @xas: XArray operation state.
+ * @entry: Entry from xarray.
+ *
+ * The advanced functions may sometimes return an internal entry, such as
+ * a retry entry or a zero entry.  This function sets up the @xas to restart
+ * the walk from the head of the array if needed.
+ *
+ * Context: Any context.
+ * Return: true if the operation needs to be retried.
+ */
+static inline bool xas_retry(struct xa_state *xas, const void *entry)
+{
+	if (!xa_is_retry(entry))
+		return false;
+	xas_reset(xas);
+	return true;
+}
+
+void *xas_load(struct xa_state *);
+
+/**
+ * xas_reload() - Refetch an entry from the xarray.
+ * @xas: XArray operation state.
+ *
+ * Use this function to check that a previously loaded entry still has
+ * the same value.  This is useful for the lockless pagecache lookup where
+ * we walk the array with only the RCU lock to protect us, lock the page,
+ * then check that the page hasn't moved since we looked it up.
+ *
+ * The caller guarantees that @xas is still valid.  If it may be in an
+ * error or restart state, call xas_load() instead.
+ *
+ * Return: The entry at this location in the xarray.
+ */
+static inline void *xas_reload(struct xa_state *xas)
+{
+	struct xa_node *node = xas->xa_node;
+
+	if (node)
+		return xa_entry(xas->xa, node, xas->xa_offset);
+	return xa_head(xas->xa);
+}
+
 #endif /* _LINUX_XARRAY_H */
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 4966c4fbe7f7..091155e12422 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1813,6 +1813,9 @@ config TEST_BITFIELD
 config TEST_UUID
 	tristate "Test functions located in the uuid module at runtime"
 
+config TEST_XARRAY
+	tristate "Test the XArray code at runtime"
+
 config TEST_OVERFLOW
 	tristate "Test check_*_overflow() functions at runtime"
 
diff --git a/lib/Makefile b/lib/Makefile
index 057385f1f145..e6f809556af5 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -68,6 +68,7 @@ obj-$(CONFIG_TEST_PRINTF) += test_printf.o
 obj-$(CONFIG_TEST_BITMAP) += test_bitmap.o
 obj-$(CONFIG_TEST_BITFIELD) += test_bitfield.o
 obj-$(CONFIG_TEST_UUID) += test_uuid.o
+obj-$(CONFIG_TEST_XARRAY) += test_xarray.o
 obj-$(CONFIG_TEST_PARMAN) += test_parman.o
 obj-$(CONFIG_TEST_KMOD) += test_kmod.o
 obj-$(CONFIG_TEST_DEBUG_VIRTUAL) += test_debug_virtual.o
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 8a568cea1237..b8e961428484 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -256,49 +256,6 @@ static unsigned long next_index(unsigned long index,
 }
 
 #ifndef __KERNEL__
-static void dump_node(struct radix_tree_node *node, unsigned long index)
-{
-	unsigned long i;
-
-	pr_debug("radix node: %p offset %d indices %lu-%lu parent %p tags %lx %lx %lx shift %d count %d nr_values %d\n",
-		node, node->offset, index, index | node_maxindex(node),
-		node->parent,
-		node->tags[0][0], node->tags[1][0], node->tags[2][0],
-		node->shift, node->count, node->nr_values);
-
-	for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) {
-		unsigned long first = index | (i << node->shift);
-		unsigned long last = first | ((1UL << node->shift) - 1);
-		void *entry = node->slots[i];
-		if (!entry)
-			continue;
-		if (entry == RADIX_TREE_RETRY) {
-			pr_debug("radix retry offset %ld indices %lu-%lu parent %p\n",
-					i, first, last, node);
-		} else if (!radix_tree_is_internal_node(entry)) {
-			pr_debug("radix entry %p offset %ld indices %lu-%lu parent %p\n",
-					entry, i, first, last, node);
-		} else if (xa_is_sibling(entry)) {
-			pr_debug("radix sblng %p offset %ld indices %lu-%lu parent %p val %p\n",
-					entry, i, first, last, node,
-					node->slots[xa_to_sibling(entry)]);
-		} else {
-			dump_node(entry_to_node(entry), first);
-		}
-	}
-}
-
-/* For debug */
-static void radix_tree_dump(struct radix_tree_root *root)
-{
-	pr_debug("radix root: %p xa_head %p tags %x\n",
-			root, root->xa_head,
-			root->xa_flags >> ROOT_TAG_SHIFT);
-	if (!radix_tree_is_internal_node(root->xa_head))
-		return;
-	dump_node(entry_to_node(root->xa_head), 0);
-}
-
 static void dump_ida_node(void *entry, unsigned long index)
 {
 	unsigned long i;
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
new file mode 100644
index 000000000000..a7248b87617f
--- /dev/null
+++ b/lib/test_xarray.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * test_xarray.c: Test the XArray API
+ * Copyright (c) 2017-2018 Microsoft Corporation
+ * Author: Matthew Wilcox <willy@infradead.org>
+ */
+
+#include <linux/xarray.h>
+#include <linux/module.h>
+
+static unsigned int tests_run;
+static unsigned int tests_passed;
+
+#ifndef XA_DEBUG
+# ifdef __KERNEL__
+void xa_dump(const struct xarray *xa) { }
+# endif
+#undef XA_BUG_ON
+#define XA_BUG_ON(xa, x) do {					\
+	tests_run++;						\
+	if (x) {						\
+		printk("BUG at %s:%d\n", __func__, __LINE__);	\
+		xa_dump(xa);					\
+		dump_stack();					\
+	} else {						\
+		tests_passed++;					\
+	}							\
+} while (0)
+#endif
+
+static void *xa_store_index(struct xarray *xa, unsigned long index, gfp_t gfp)
+{
+	radix_tree_insert(xa, index, xa_mk_value(index));
+	return NULL;
+}
+
+static void xa_erase_index(struct xarray *xa, unsigned long index)
+{
+	radix_tree_delete(xa, index);
+}
+
+static noinline void check_xa_load(struct xarray *xa)
+{
+	unsigned long i, j;
+
+	for (i = 0; i < 1024; i++) {
+		for (j = 0; j < 1024; j++) {
+			void *entry = xa_load(xa, j);
+			if (j < i)
+				XA_BUG_ON(xa, xa_to_value(entry) != j);
+			else
+				XA_BUG_ON(xa, entry);
+		}
+		XA_BUG_ON(xa, xa_store_index(xa, i, GFP_KERNEL) != NULL);
+	}
+
+	for (i = 0; i < 1024; i++) {
+		for (j = 0; j < 1024; j++) {
+			void *entry = xa_load(xa, j);
+			if (j >= i)
+				XA_BUG_ON(xa, xa_to_value(entry) != j);
+			else
+				XA_BUG_ON(xa, entry);
+		}
+		xa_erase_index(xa, i);
+	}
+	XA_BUG_ON(xa, !xa_empty(xa));
+}
+
+static RADIX_TREE(array, GFP_KERNEL);
+
+static int xarray_checks(void)
+{
+	check_xa_load(&array);
+
+	printk("XArray: %u of %u tests passed\n", tests_passed, tests_run);
+	return (tests_run == tests_passed) ? 0 : -EINVAL;
+}
+
+static void xarray_exit(void)
+{
+}
+
+module_init(xarray_checks);
+module_exit(xarray_exit);
+MODULE_AUTHOR("Matthew Wilcox <willy@infradead.org>");
+MODULE_LICENSE("GPL");
diff --git a/lib/xarray.c b/lib/xarray.c
index 862f4c64c754..19cfcbc69a68 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -24,6 +24,100 @@
  * @entry refers to something stored in a slot in the xarray
  */
 
+/* extracts the offset within this node from the index */
+static unsigned int get_offset(unsigned long index, struct xa_node *node)
+{
+	return (index >> node->shift) & XA_CHUNK_MASK;
+}
+
+/* move the index either forwards (find) or backwards (sibling slot) */
+static void xas_move_index(struct xa_state *xas, unsigned long offset)
+{
+	unsigned int shift = xas->xa_node->shift;
+	xas->xa_index &= ~XA_CHUNK_MASK << shift;
+	xas->xa_index += offset << shift;
+}
+
+static void *set_bounds(struct xa_state *xas)
+{
+	xas->xa_node = XAS_BOUNDS;
+	return NULL;
+}
+
+/*
+ * Starts a walk.  If the @xas is already valid, we assume that it's on
+ * the right path and just return where we've got to.  If we're in an
+ * error state, return NULL.  If the index is outside the current scope
+ * of the xarray, return NULL without changing @xas->xa_node.  Otherwise
+ * set @xas->xa_node to NULL and return the current head of the array.
+ */
+static void *xas_start(struct xa_state *xas)
+{
+	void *entry;
+
+	if (xas_valid(xas))
+		return xas_reload(xas);
+	if (xas_error(xas))
+		return NULL;
+
+	entry = xa_head(xas->xa);
+	if (!xa_is_node(entry)) {
+		if (xas->xa_index)
+			return set_bounds(xas);
+	} else {
+		if ((xas->xa_index >> xa_to_node(entry)->shift) > XA_CHUNK_MASK)
+			return set_bounds(xas);
+	}
+
+	xas->xa_node = NULL;
+	return entry;
+}
+
+static void *xas_descend(struct xa_state *xas, struct xa_node *node)
+{
+	unsigned int offset = get_offset(xas->xa_index, node);
+	void *entry = xa_entry(xas->xa, node, offset);
+
+	xas->xa_node = node;
+	if (xa_is_sibling(entry)) {
+		offset = xa_to_sibling(entry);
+		entry = xa_entry(xas->xa, node, offset);
+	}
+
+	xas->xa_offset = offset;
+	return entry;
+}
+
+/**
+ * xas_load() - Load an entry from the XArray (advanced).
+ * @xas: XArray operation state.
+ *
+ * Usually walks the @xas to the appropriate state to load the entry
+ * stored at xa_index.  However, it will do nothing and return %NULL if
+ * @xas is in an error state.  xas_load() will never expand the tree.
+ *
+ * If the xa_state is set up to operate on a multi-index entry, xas_load()
+ * may return %NULL or an internal entry, even if there are entries
+ * present within the range specified by @xas.
+ *
+ * Context: Any context.  The caller should hold the xa_lock or the RCU lock.
+ * Return: Usually an entry in the XArray, but see description for exceptions.
+ */
+void *xas_load(struct xa_state *xas)
+{
+	void *entry = xas_start(xas);
+
+	while (xa_is_node(entry)) {
+		struct xa_node *node = xa_to_node(entry);
+
+		if (xas->xa_shift > node->shift)
+			break;
+		entry = xas_descend(xas, node);
+	}
+	return entry;
+}
+EXPORT_SYMBOL_GPL(xas_load);
+
 /**
  * xa_init_flags() - Initialise an empty XArray with flags.
  * @xa: XArray.
@@ -42,3 +136,104 @@ void xa_init_flags(struct xarray *xa, gfp_t flags)
 	xa->xa_head = NULL;
 }
 EXPORT_SYMBOL(xa_init_flags);
+
+/**
+ * xa_load() - Load an entry from an XArray.
+ * @xa: XArray.
+ * @index: index into array.
+ *
+ * Context: Any context.  Takes and releases the RCU lock.
+ * Return: The entry at @index in @xa.
+ */
+void *xa_load(struct xarray *xa, unsigned long index)
+{
+	XA_STATE(xas, xa, index);
+	void *entry;
+
+	rcu_read_lock();
+	do {
+		entry = xas_load(&xas);
+	} while (xas_retry(&xas, entry));
+	rcu_read_unlock();
+
+	return entry;
+}
+EXPORT_SYMBOL(xa_load);
+
+#ifdef XA_DEBUG
+void xa_dump_node(const struct xa_node *node)
+{
+	unsigned i, j;
+
+	if (!node)
+		return;
+	if ((unsigned long)node & 3) {
+		pr_cont("node %px\n", node);
+		return;
+	}
+
+	pr_cont("node %px %s %d parent %px shift %d count %d values %d "
+		"array %px list %px %px marks",
+		node, node->parent ? "offset" : "max", node->offset,
+		node->parent, node->shift, node->count, node->nr_values,
+		node->array, node->private_list.prev, node->private_list.next);
+	for (i = 0; i < XA_MAX_MARKS; i++)
+		for (j = 0; j < XA_MARK_LONGS; j++)
+			pr_cont(" %lx", node->marks[i][j]);
+	pr_cont("\n");
+}
+
+void xa_dump_index(unsigned long index, unsigned int shift)
+{
+	if (!shift)
+		pr_info("%lu: ", index);
+	else if (shift >= BITS_PER_LONG)
+		pr_info("0-%lu: ", ~0UL);
+	else
+		pr_info("%lu-%lu: ", index, index | ((1UL << shift) - 1));
+}
+
+void xa_dump_entry(const void *entry, unsigned long index, unsigned long shift)
+{
+	if (!entry)
+		return;
+
+	xa_dump_index(index, shift);
+
+	if (xa_is_node(entry)) {
+		if (shift == 0) {
+			pr_cont("%px\n", entry);
+		} else {
+			unsigned long i;
+			struct xa_node *node = xa_to_node(entry);
+			xa_dump_node(node);
+			for (i = 0; i < XA_CHUNK_SIZE; i++)
+				xa_dump_entry(node->slots[i],
+				      index + (i << node->shift), node->shift);
+		}
+	} else if (xa_is_value(entry))
+		pr_cont("value %ld (0x%lx) [%px]\n", xa_to_value(entry),
+						xa_to_value(entry), entry);
+	else if (!xa_is_internal(entry))
+		pr_cont("%px\n", entry);
+	else if (xa_is_retry(entry))
+		pr_cont("retry (%ld)\n", xa_to_internal(entry));
+	else if (xa_is_sibling(entry))
+		pr_cont("sibling (slot %ld)\n", xa_to_sibling(entry));
+	else
+		pr_cont("UNKNOWN ENTRY (%px)\n", entry);
+}
+
+void xa_dump(const struct xarray *xa)
+{
+	void *entry = xa->xa_head;
+	unsigned int shift = 0;
+
+	pr_info("xarray: %px head %px flags %x marks %d %d %d\n", xa, entry,
+			xa->xa_flags, radix_tree_tagged(xa, 0),
+			radix_tree_tagged(xa, 1), radix_tree_tagged(xa, 2));
+	if (xa_is_node(entry))
+		shift = xa_to_node(entry)->shift + XA_CHUNK_SHIFT;
+	xa_dump_entry(entry, 0, shift);
+}
+#endif
diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h
index 0ad884452c5c..6935ef94e77a 100644
--- a/tools/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -70,6 +70,7 @@
 #define BUG_ON(cond) assert(!(cond))
 #endif
 #endif
+#define BUG()	BUG_ON(1)
 
 #if __BYTE_ORDER == __BIG_ENDIAN
 #define cpu_to_le16 bswap_16
diff --git a/tools/testing/radix-tree/.gitignore b/tools/testing/radix-tree/.gitignore
index d4706c0ffceb..3834899b6693 100644
--- a/tools/testing/radix-tree/.gitignore
+++ b/tools/testing/radix-tree/.gitignore
@@ -4,3 +4,4 @@ idr-test
 main
 multiorder
 radix-tree.c
+xarray
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index c0cf1c79efd5..1379f1d78d0b 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -4,7 +4,7 @@ CFLAGS += -I. -I../../include -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address \
 	  -fsanitize=undefined
 LDFLAGS += -fsanitize=address -fsanitize=undefined
 LDLIBS+= -lpthread -lurcu
-TARGETS = main idr-test multiorder
+TARGETS = main idr-test multiorder xarray
 CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o
 OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \
 	 tag_check.o multiorder.o idr-test.o iteration_check.o benchmark.o
@@ -25,6 +25,8 @@ main:	$(OFILES)
 idr-test.o: ../../../lib/test_ida.c
 idr-test: idr-test.o $(CORE_OFILES)
 
+xarray: $(CORE_OFILES)
+
 multiorder: multiorder.o $(CORE_OFILES)
 
 clean:
@@ -45,7 +47,7 @@ radix-tree.c: ../../../lib/radix-tree.c
 idr.c: ../../../lib/idr.c
 	sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@
 
-xarray.o: ../../../lib/xarray.c
+xarray.o: ../../../lib/xarray.c ../../../lib/test_xarray.c
 
 generated/map-shift.h:
 	@if ! grep -qws $(SHIFT) generated/map-shift.h; then		\
diff --git a/tools/testing/radix-tree/linux/kernel.h b/tools/testing/radix-tree/linux/kernel.h
index 426f32f28547..5d06ac75a14d 100644
--- a/tools/testing/radix-tree/linux/kernel.h
+++ b/tools/testing/radix-tree/linux/kernel.h
@@ -14,6 +14,7 @@
 #include "../../../include/linux/kconfig.h"
 
 #define printk printf
+#define pr_info printk
 #define pr_debug printk
 #define pr_cont printk
 
diff --git a/tools/testing/radix-tree/linux/rcupdate.h b/tools/testing/radix-tree/linux/rcupdate.h
index 73ed33658203..fd280b070fdb 100644
--- a/tools/testing/radix-tree/linux/rcupdate.h
+++ b/tools/testing/radix-tree/linux/rcupdate.h
@@ -6,5 +6,7 @@
 
 #define rcu_dereference_raw(p) rcu_dereference(p)
 #define rcu_dereference_protected(p, cond) rcu_dereference(p)
+#define rcu_dereference_check(p, cond) rcu_dereference(p)
+#define RCU_INIT_POINTER(p, v)	(p) = (v)
 
 #endif
diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c
index b741686e53d6..09deaf4f0959 100644
--- a/tools/testing/radix-tree/main.c
+++ b/tools/testing/radix-tree/main.c
@@ -365,6 +365,7 @@ int main(int argc, char **argv)
 	rcu_register_thread();
 	radix_tree_init();
 
+	xarray_tests();
 	regression1_test();
 	regression2_test();
 	regression3_test();
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index 92d901eacf49..e3dc7a16f09b 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -34,6 +34,7 @@ int tag_tagged_items(struct radix_tree_root *, pthread_mutex_t *,
 			unsigned iftag, unsigned thentag);
 unsigned long find_item(struct radix_tree_root *, void *item);
 
+void xarray_tests(void);
 void tag_check(void);
 void multiorder_checks(void);
 void iteration_test(unsigned order, unsigned duration);
diff --git a/tools/testing/radix-tree/xarray.c b/tools/testing/radix-tree/xarray.c
index 9bbd667172a7..e61e43efe463 100644
--- a/tools/testing/radix-tree/xarray.c
+++ b/tools/testing/radix-tree/xarray.c
@@ -4,4 +4,32 @@
  * Copyright (c) 2018 Matthew Wilcox <willy@infradead.org>
  */
 
+#define XA_DEBUG
+#include "test.h"
+
+#define module_init(x)
+#define module_exit(x)
+#define MODULE_AUTHOR(x)
+#define MODULE_LICENSE(x)
+#define dump_stack()	assert(0)
+
 #include "../../../lib/xarray.c"
+#undef XA_DEBUG
+#include "../../../lib/test_xarray.c"
+
+void xarray_tests(void)
+{
+	xarray_checks();
+	xarray_exit();
+}
+
+int __weak main(void)
+{
+	radix_tree_init();
+	xarray_tests();
+	radix_tree_cpu_dead(1);
+	rcu_barrier();
+	if (nr_allocated)
+		printf("nr_allocated = %d\n", nr_allocated);
+	return 0;
+}
-- 
cgit 


From 58d6ea3085f2e53714810a513c61629f6d2be0a6 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Fri, 10 Nov 2017 15:15:08 -0500
Subject: xarray: Add XArray unconditional store operations

xa_store() differs from radix_tree_insert() in that it will overwrite an
existing element in the array rather than returning an error.  This is
the behaviour which most users want, and those that want more complex
behaviour generally want to use the xas family of routines anyway.

For memory allocation, xa_store() will first attempt to request memory
from the slab allocator; if memory is not immediately available, it will
drop the xa_lock and allocate memory, keeping a pointer in the xa_state.
It does not use the per-CPU cache, although those will continue to exist
until all radix tree users are converted to the xarray.

This patch also includes xa_erase() and __xa_erase() for a streamlined
way to store NULL.  Since there is no need to allocate memory in order
to store a NULL in the XArray, we do not need to trouble the user with
deciding what memory allocation flags to use.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 include/linux/xarray.h                   | 147 ++++++-
 lib/radix-tree.c                         |   4 +-
 lib/test_xarray.c                        | 177 +++++++-
 lib/xarray.c                             | 693 +++++++++++++++++++++++++++++++
 tools/include/linux/bitmap.h             |   1 +
 tools/include/linux/spinlock.h           |   2 +
 tools/testing/radix-tree/Makefile        |   2 +-
 tools/testing/radix-tree/bitmap.c        |  23 +
 tools/testing/radix-tree/linux/kernel.h  |   4 +
 tools/testing/radix-tree/linux/lockdep.h |  11 +
 10 files changed, 1055 insertions(+), 9 deletions(-)
 create mode 100644 tools/testing/radix-tree/bitmap.c
 create mode 100644 tools/testing/radix-tree/linux/lockdep.h

(limited to 'tools/testing')

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 2de504ae9ba4..15eab63286ed 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -205,10 +205,17 @@ typedef unsigned __bitwise xa_mark_t;
 #define XA_PRESENT		((__force xa_mark_t)8U)
 #define XA_MARK_MAX		XA_MARK_2
 
+enum xa_lock_type {
+	XA_LOCK_IRQ = 1,
+	XA_LOCK_BH = 2,
+};
+
 /*
  * Values for xa_flags.  The radix tree stores its GFP flags in the xa_flags,
  * and we remain compatible with that.
  */
+#define XA_FLAGS_LOCK_IRQ	((__force gfp_t)XA_LOCK_IRQ)
+#define XA_FLAGS_LOCK_BH	((__force gfp_t)XA_LOCK_BH)
 #define XA_FLAGS_MARK(mark)	((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \
 						(__force unsigned)(mark)))
 
@@ -267,6 +274,7 @@ struct xarray {
 
 void xa_init_flags(struct xarray *, gfp_t flags);
 void *xa_load(struct xarray *, unsigned long index);
+void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t);
 bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t);
 void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t);
 void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t);
@@ -309,6 +317,23 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark)
 	return xa->xa_flags & XA_FLAGS_MARK(mark);
 }
 
+/**
+ * xa_erase() - Erase this entry from the XArray.
+ * @xa: XArray.
+ * @index: Index of entry.
+ *
+ * This function is the equivalent of calling xa_store() with %NULL as
+ * the third argument.  The XArray does not need to allocate memory, so
+ * the user does not need to provide GFP flags.
+ *
+ * Context: Process context.  Takes and releases the xa_lock.
+ * Return: The entry which used to be at this index.
+ */
+static inline void *xa_erase(struct xarray *xa, unsigned long index)
+{
+	return xa_store(xa, index, NULL, 0);
+}
+
 #define xa_trylock(xa)		spin_trylock(&(xa)->xa_lock)
 #define xa_lock(xa)		spin_lock(&(xa)->xa_lock)
 #define xa_unlock(xa)		spin_unlock(&(xa)->xa_lock)
@@ -322,11 +347,65 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark)
 				spin_unlock_irqrestore(&(xa)->xa_lock, flags)
 
 /*
- * Versions of the normal API which require the caller to hold the xa_lock.
- */
+ * Versions of the normal API which require the caller to hold the
+ * xa_lock.  If the GFP flags allow it, they will drop the lock to
+ * allocate memory, then reacquire it afterwards.  These functions
+ * may also re-enable interrupts if the XArray flags indicate the
+ * locking should be interrupt safe.
+ */
+void *__xa_erase(struct xarray *, unsigned long index);
+void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t);
 void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t);
 void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t);
 
+/**
+ * xa_erase_bh() - Erase this entry from the XArray.
+ * @xa: XArray.
+ * @index: Index of entry.
+ *
+ * This function is the equivalent of calling xa_store() with %NULL as
+ * the third argument.  The XArray does not need to allocate memory, so
+ * the user does not need to provide GFP flags.
+ *
+ * Context: Process context.  Takes and releases the xa_lock while
+ * disabling softirqs.
+ * Return: The entry which used to be at this index.
+ */
+static inline void *xa_erase_bh(struct xarray *xa, unsigned long index)
+{
+	void *entry;
+
+	xa_lock_bh(xa);
+	entry = __xa_erase(xa, index);
+	xa_unlock_bh(xa);
+
+	return entry;
+}
+
+/**
+ * xa_erase_irq() - Erase this entry from the XArray.
+ * @xa: XArray.
+ * @index: Index of entry.
+ *
+ * This function is the equivalent of calling xa_store() with %NULL as
+ * the third argument.  The XArray does not need to allocate memory, so
+ * the user does not need to provide GFP flags.
+ *
+ * Context: Process context.  Takes and releases the xa_lock while
+ * disabling interrupts.
+ * Return: The entry which used to be at this index.
+ */
+static inline void *xa_erase_irq(struct xarray *xa, unsigned long index)
+{
+	void *entry;
+
+	xa_lock_irq(xa);
+	entry = __xa_erase(xa, index);
+	xa_unlock_irq(xa);
+
+	return entry;
+}
+
 /* Everything below here is the Advanced API.  Proceed with caution. */
 
 /*
@@ -441,6 +520,12 @@ static inline struct xa_node *xa_parent_locked(const struct xarray *xa,
 						lockdep_is_held(&xa->xa_lock));
 }
 
+/* Private */
+static inline void *xa_mk_node(const struct xa_node *node)
+{
+	return (void *)((unsigned long)node | 2);
+}
+
 /* Private */
 static inline struct xa_node *xa_to_node(const void *entry)
 {
@@ -647,6 +732,12 @@ static inline bool xas_not_node(struct xa_node *node)
 	return ((unsigned long)node & 3) || !node;
 }
 
+/* True if the node represents head-of-tree, RESTART or BOUNDS */
+static inline bool xas_top(struct xa_node *node)
+{
+	return node <= XAS_RESTART;
+}
+
 /**
  * xas_reset() - Reset an XArray operation state.
  * @xas: XArray operation state.
@@ -683,10 +774,14 @@ static inline bool xas_retry(struct xa_state *xas, const void *entry)
 }
 
 void *xas_load(struct xa_state *);
+void *xas_store(struct xa_state *, void *entry);
 
 bool xas_get_mark(const struct xa_state *, xa_mark_t);
 void xas_set_mark(const struct xa_state *, xa_mark_t);
 void xas_clear_mark(const struct xa_state *, xa_mark_t);
+void xas_init_marks(const struct xa_state *);
+
+bool xas_nomem(struct xa_state *, gfp_t);
 
 /**
  * xas_reload() - Refetch an entry from the xarray.
@@ -711,4 +806,52 @@ static inline void *xas_reload(struct xa_state *xas)
 	return xa_head(xas->xa);
 }
 
+/**
+ * xas_set() - Set up XArray operation state for a different index.
+ * @xas: XArray operation state.
+ * @index: New index into the XArray.
+ *
+ * Move the operation state to refer to a different index.  This will
+ * have the effect of starting a walk from the top; see xas_next()
+ * to move to an adjacent index.
+ */
+static inline void xas_set(struct xa_state *xas, unsigned long index)
+{
+	xas->xa_index = index;
+	xas->xa_node = XAS_RESTART;
+}
+
+/**
+ * xas_set_order() - Set up XArray operation state for a multislot entry.
+ * @xas: XArray operation state.
+ * @index: Target of the operation.
+ * @order: Entry occupies 2^@order indices.
+ */
+static inline void xas_set_order(struct xa_state *xas, unsigned long index,
+					unsigned int order)
+{
+#ifdef CONFIG_XARRAY_MULTI
+	xas->xa_index = order < BITS_PER_LONG ? (index >> order) << order : 0;
+	xas->xa_shift = order - (order % XA_CHUNK_SHIFT);
+	xas->xa_sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1;
+	xas->xa_node = XAS_RESTART;
+#else
+	BUG_ON(order > 0);
+	xas_set(xas, index);
+#endif
+}
+
+/**
+ * xas_set_update() - Set up XArray operation state for a callback.
+ * @xas: XArray operation state.
+ * @update: Function to call when updating a node.
+ *
+ * The XArray can notify a caller after it has updated an xa_node.
+ * This is advanced functionality and is only needed by the page cache.
+ */
+static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update)
+{
+	xas->xa_update = update;
+}
+
 #endif /* _LINUX_XARRAY_H */
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index b8e961428484..3479d93c32b9 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -47,7 +47,7 @@ static unsigned long height_to_maxnodes[RADIX_TREE_MAX_PATH + 1] __read_mostly;
 /*
  * Radix tree node cache.
  */
-static struct kmem_cache *radix_tree_node_cachep;
+struct kmem_cache *radix_tree_node_cachep;
 
 /*
  * The radix tree is variable-height, so an insert operation not only has
@@ -365,7 +365,7 @@ out:
 	return ret;
 }
 
-static void radix_tree_node_rcu_free(struct rcu_head *head)
+void radix_tree_node_rcu_free(struct rcu_head *head)
 {
 	struct radix_tree_node *node =
 			container_of(head, struct radix_tree_node, rcu_head);
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index f8b0e9ba80a4..b711030fbc32 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -30,13 +30,49 @@ void xa_dump(const struct xarray *xa) { }
 
 static void *xa_store_index(struct xarray *xa, unsigned long index, gfp_t gfp)
 {
-	radix_tree_insert(xa, index, xa_mk_value(index));
-	return NULL;
+	return xa_store(xa, index, xa_mk_value(index & LONG_MAX), gfp);
 }
 
 static void xa_erase_index(struct xarray *xa, unsigned long index)
 {
-	radix_tree_delete(xa, index);
+	XA_BUG_ON(xa, xa_erase(xa, index) != xa_mk_value(index & LONG_MAX));
+	XA_BUG_ON(xa, xa_load(xa, index) != NULL);
+}
+
+/*
+ * If anyone needs this, please move it to xarray.c.  We have no current
+ * users outside the test suite because all current multislot users want
+ * to use the advanced API.
+ */
+static void *xa_store_order(struct xarray *xa, unsigned long index,
+		unsigned order, void *entry, gfp_t gfp)
+{
+	XA_STATE_ORDER(xas, xa, index, order);
+	void *curr;
+
+	do {
+		xas_lock(&xas);
+		curr = xas_store(&xas, entry);
+		xas_unlock(&xas);
+	} while (xas_nomem(&xas, gfp));
+
+	return curr;
+}
+
+static noinline void check_xa_err(struct xarray *xa)
+{
+	XA_BUG_ON(xa, xa_err(xa_store_index(xa, 0, GFP_NOWAIT)) != 0);
+	XA_BUG_ON(xa, xa_err(xa_erase(xa, 0)) != 0);
+#ifndef __KERNEL__
+	/* The kernel does not fail GFP_NOWAIT allocations */
+	XA_BUG_ON(xa, xa_err(xa_store_index(xa, 1, GFP_NOWAIT)) != -ENOMEM);
+	XA_BUG_ON(xa, xa_err(xa_store_index(xa, 1, GFP_NOWAIT)) != -ENOMEM);
+#endif
+	XA_BUG_ON(xa, xa_err(xa_store_index(xa, 1, GFP_KERNEL)) != 0);
+	XA_BUG_ON(xa, xa_err(xa_store(xa, 1, xa_mk_value(0), GFP_KERNEL)) != 0);
+	XA_BUG_ON(xa, xa_err(xa_erase(xa, 1)) != 0);
+// kills the test-suite :-(
+//	XA_BUG_ON(xa, xa_err(xa_store(xa, 0, xa_mk_internal(0), 0)) != -EINVAL);
 }
 
 static noinline void check_xa_load(struct xarray *xa)
@@ -69,6 +105,9 @@ static noinline void check_xa_load(struct xarray *xa)
 
 static noinline void check_xa_mark_1(struct xarray *xa, unsigned long index)
 {
+	unsigned int order;
+	unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 8 : 1;
+
 	/* NULL elements have no marks set */
 	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0));
 	xa_set_mark(xa, index, XA_MARK_0);
@@ -90,6 +129,37 @@ static noinline void check_xa_mark_1(struct xarray *xa, unsigned long index)
 	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0));
 	xa_set_mark(xa, index, XA_MARK_0);
 	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0));
+
+	/*
+	 * Storing a multi-index entry over entries with marks gives the
+	 * entire entry the union of the marks
+	 */
+	BUG_ON((index % 4) != 0);
+	for (order = 2; order < max_order; order++) {
+		unsigned long base = round_down(index, 1UL << order);
+		unsigned long next = base + (1UL << order);
+		unsigned long i;
+
+		XA_BUG_ON(xa, xa_store_index(xa, index + 1, GFP_KERNEL));
+		xa_set_mark(xa, index + 1, XA_MARK_0);
+		XA_BUG_ON(xa, xa_store_index(xa, index + 2, GFP_KERNEL));
+		xa_set_mark(xa, index + 2, XA_MARK_1);
+		XA_BUG_ON(xa, xa_store_index(xa, next, GFP_KERNEL));
+		xa_store_order(xa, index, order, xa_mk_value(index),
+				GFP_KERNEL);
+		for (i = base; i < next; i++) {
+			XA_BUG_ON(xa, !xa_get_mark(xa, i, XA_MARK_0));
+			XA_BUG_ON(xa, !xa_get_mark(xa, i, XA_MARK_1));
+			XA_BUG_ON(xa, xa_get_mark(xa, i, XA_MARK_2));
+		}
+		XA_BUG_ON(xa, xa_get_mark(xa, next, XA_MARK_0));
+		XA_BUG_ON(xa, xa_get_mark(xa, next, XA_MARK_1));
+		XA_BUG_ON(xa, xa_get_mark(xa, next, XA_MARK_2));
+		xa_erase_index(xa, index);
+		xa_erase_index(xa, next);
+		XA_BUG_ON(xa, !xa_empty(xa));
+	}
+	XA_BUG_ON(xa, !xa_empty(xa));
 }
 
 static noinline void check_xa_mark(struct xarray *xa)
@@ -100,12 +170,111 @@ static noinline void check_xa_mark(struct xarray *xa)
 		check_xa_mark_1(xa, index);
 }
 
-static RADIX_TREE(array, GFP_KERNEL);
+static noinline void check_xa_shrink(struct xarray *xa)
+{
+	XA_STATE(xas, xa, 1);
+	struct xa_node *node;
+
+	XA_BUG_ON(xa, !xa_empty(xa));
+	XA_BUG_ON(xa, xa_store_index(xa, 0, GFP_KERNEL) != NULL);
+	XA_BUG_ON(xa, xa_store_index(xa, 1, GFP_KERNEL) != NULL);
+
+	/*
+	 * Check that erasing the entry at 1 shrinks the tree and properly
+	 * marks the node as being deleted.
+	 */
+	xas_lock(&xas);
+	XA_BUG_ON(xa, xas_load(&xas) != xa_mk_value(1));
+	node = xas.xa_node;
+	XA_BUG_ON(xa, xa_entry_locked(xa, node, 0) != xa_mk_value(0));
+	XA_BUG_ON(xa, xas_store(&xas, NULL) != xa_mk_value(1));
+	XA_BUG_ON(xa, xa_load(xa, 1) != NULL);
+	XA_BUG_ON(xa, xas.xa_node != XAS_BOUNDS);
+	XA_BUG_ON(xa, xa_entry_locked(xa, node, 0) != XA_RETRY_ENTRY);
+	XA_BUG_ON(xa, xas_load(&xas) != NULL);
+	xas_unlock(&xas);
+	XA_BUG_ON(xa, xa_load(xa, 0) != xa_mk_value(0));
+	xa_erase_index(xa, 0);
+	XA_BUG_ON(xa, !xa_empty(xa));
+}
+
+static noinline void check_multi_store(struct xarray *xa)
+{
+#ifdef CONFIG_XARRAY_MULTI
+	unsigned long i, j, k;
+	unsigned int max_order = (sizeof(long) == 4) ? 30 : 60;
+
+	/* Loading from any position returns the same value */
+	xa_store_order(xa, 0, 1, xa_mk_value(0), GFP_KERNEL);
+	XA_BUG_ON(xa, xa_load(xa, 0) != xa_mk_value(0));
+	XA_BUG_ON(xa, xa_load(xa, 1) != xa_mk_value(0));
+	XA_BUG_ON(xa, xa_load(xa, 2) != NULL);
+	rcu_read_lock();
+	XA_BUG_ON(xa, xa_to_node(xa_head(xa))->count != 2);
+	XA_BUG_ON(xa, xa_to_node(xa_head(xa))->nr_values != 2);
+	rcu_read_unlock();
+
+	/* Storing adjacent to the value does not alter the value */
+	xa_store(xa, 3, xa, GFP_KERNEL);
+	XA_BUG_ON(xa, xa_load(xa, 0) != xa_mk_value(0));
+	XA_BUG_ON(xa, xa_load(xa, 1) != xa_mk_value(0));
+	XA_BUG_ON(xa, xa_load(xa, 2) != NULL);
+	rcu_read_lock();
+	XA_BUG_ON(xa, xa_to_node(xa_head(xa))->count != 3);
+	XA_BUG_ON(xa, xa_to_node(xa_head(xa))->nr_values != 2);
+	rcu_read_unlock();
+
+	/* Overwriting multiple indexes works */
+	xa_store_order(xa, 0, 2, xa_mk_value(1), GFP_KERNEL);
+	XA_BUG_ON(xa, xa_load(xa, 0) != xa_mk_value(1));
+	XA_BUG_ON(xa, xa_load(xa, 1) != xa_mk_value(1));
+	XA_BUG_ON(xa, xa_load(xa, 2) != xa_mk_value(1));
+	XA_BUG_ON(xa, xa_load(xa, 3) != xa_mk_value(1));
+	XA_BUG_ON(xa, xa_load(xa, 4) != NULL);
+	rcu_read_lock();
+	XA_BUG_ON(xa, xa_to_node(xa_head(xa))->count != 4);
+	XA_BUG_ON(xa, xa_to_node(xa_head(xa))->nr_values != 4);
+	rcu_read_unlock();
+
+	/* We can erase multiple values with a single store */
+	xa_store_order(xa, 0, 63, NULL, GFP_KERNEL);
+	XA_BUG_ON(xa, !xa_empty(xa));
+
+	/* Even when the first slot is empty but the others aren't */
+	xa_store_index(xa, 1, GFP_KERNEL);
+	xa_store_index(xa, 2, GFP_KERNEL);
+	xa_store_order(xa, 0, 2, NULL, GFP_KERNEL);
+	XA_BUG_ON(xa, !xa_empty(xa));
+
+	for (i = 0; i < max_order; i++) {
+		for (j = 0; j < max_order; j++) {
+			xa_store_order(xa, 0, i, xa_mk_value(i), GFP_KERNEL);
+			xa_store_order(xa, 0, j, xa_mk_value(j), GFP_KERNEL);
+
+			for (k = 0; k < max_order; k++) {
+				void *entry = xa_load(xa, (1UL << k) - 1);
+				if ((i < k) && (j < k))
+					XA_BUG_ON(xa, entry != NULL);
+				else
+					XA_BUG_ON(xa, entry != xa_mk_value(j));
+			}
+
+			xa_erase(xa, 0);
+			XA_BUG_ON(xa, !xa_empty(xa));
+		}
+	}
+#endif
+}
+
+static DEFINE_XARRAY(array);
 
 static int xarray_checks(void)
 {
+	check_xa_err(&array);
 	check_xa_load(&array);
 	check_xa_mark(&array);
+	check_xa_shrink(&array);
+	check_multi_store(&array);
 
 	printk("XArray: %u of %u tests passed\n", tests_passed, tests_run);
 	return (tests_run == tests_passed) ? 0 : -EINVAL;
diff --git a/lib/xarray.c b/lib/xarray.c
index aa86c47e532f..4596a95ed9cd 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -7,6 +7,8 @@
 
 #include <linux/bitmap.h>
 #include <linux/export.h>
+#include <linux/list.h>
+#include <linux/slab.h>
 #include <linux/xarray.h>
 
 /*
@@ -25,6 +27,31 @@
  * @entry refers to something stored in a slot in the xarray
  */
 
+static inline unsigned int xa_lock_type(const struct xarray *xa)
+{
+	return (__force unsigned int)xa->xa_flags & 3;
+}
+
+static inline void xas_lock_type(struct xa_state *xas, unsigned int lock_type)
+{
+	if (lock_type == XA_LOCK_IRQ)
+		xas_lock_irq(xas);
+	else if (lock_type == XA_LOCK_BH)
+		xas_lock_bh(xas);
+	else
+		xas_lock(xas);
+}
+
+static inline void xas_unlock_type(struct xa_state *xas, unsigned int lock_type)
+{
+	if (lock_type == XA_LOCK_IRQ)
+		xas_unlock_irq(xas);
+	else if (lock_type == XA_LOCK_BH)
+		xas_unlock_bh(xas);
+	else
+		xas_unlock(xas);
+}
+
 static inline void xa_mark_set(struct xarray *xa, xa_mark_t mark)
 {
 	if (!(xa->xa_flags & XA_FLAGS_MARK(mark)))
@@ -67,6 +94,34 @@ static inline bool node_any_mark(struct xa_node *node, xa_mark_t mark)
 	return !bitmap_empty(node_marks(node, mark), XA_CHUNK_SIZE);
 }
 
+#define mark_inc(mark) do { \
+	mark = (__force xa_mark_t)((__force unsigned)(mark) + 1); \
+} while (0)
+
+/*
+ * xas_squash_marks() - Merge all marks to the first entry
+ * @xas: Array operation state.
+ *
+ * Set a mark on the first entry if any entry has it set.  Clear marks on
+ * all sibling entries.
+ */
+static void xas_squash_marks(const struct xa_state *xas)
+{
+	unsigned int mark = 0;
+	unsigned int limit = xas->xa_offset + xas->xa_sibs + 1;
+
+	if (!xas->xa_sibs)
+		return;
+
+	do {
+		unsigned long *marks = xas->xa_node->marks[mark];
+		if (find_next_bit(marks, limit, xas->xa_offset + 1) == limit)
+			continue;
+		__set_bit(xas->xa_offset, marks);
+		bitmap_clear(marks, xas->xa_offset + 1, xas->xa_sibs);
+	} while (mark++ != (__force unsigned)XA_MARK_MAX);
+}
+
 /* extracts the offset within this node from the index */
 static unsigned int get_offset(unsigned long index, struct xa_node *node)
 {
@@ -161,6 +216,516 @@ void *xas_load(struct xa_state *xas)
 }
 EXPORT_SYMBOL_GPL(xas_load);
 
+/* Move the radix tree node cache here */
+extern struct kmem_cache *radix_tree_node_cachep;
+extern void radix_tree_node_rcu_free(struct rcu_head *head);
+
+#define XA_RCU_FREE	((struct xarray *)1)
+
+static void xa_node_free(struct xa_node *node)
+{
+	XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
+	node->array = XA_RCU_FREE;
+	call_rcu(&node->rcu_head, radix_tree_node_rcu_free);
+}
+
+/*
+ * xas_destroy() - Free any resources allocated during the XArray operation.
+ * @xas: XArray operation state.
+ *
+ * This function is now internal-only.
+ */
+static void xas_destroy(struct xa_state *xas)
+{
+	struct xa_node *node = xas->xa_alloc;
+
+	if (!node)
+		return;
+	XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
+	kmem_cache_free(radix_tree_node_cachep, node);
+	xas->xa_alloc = NULL;
+}
+
+/**
+ * xas_nomem() - Allocate memory if needed.
+ * @xas: XArray operation state.
+ * @gfp: Memory allocation flags.
+ *
+ * If we need to add new nodes to the XArray, we try to allocate memory
+ * with GFP_NOWAIT while holding the lock, which will usually succeed.
+ * If it fails, @xas is flagged as needing memory to continue.  The caller
+ * should drop the lock and call xas_nomem().  If xas_nomem() succeeds,
+ * the caller should retry the operation.
+ *
+ * Forward progress is guaranteed as one node is allocated here and
+ * stored in the xa_state where it will be found by xas_alloc().  More
+ * nodes will likely be found in the slab allocator, but we do not tie
+ * them up here.
+ *
+ * Return: true if memory was needed, and was successfully allocated.
+ */
+bool xas_nomem(struct xa_state *xas, gfp_t gfp)
+{
+	if (xas->xa_node != XA_ERROR(-ENOMEM)) {
+		xas_destroy(xas);
+		return false;
+	}
+	xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp);
+	if (!xas->xa_alloc)
+		return false;
+	XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list));
+	xas->xa_node = XAS_RESTART;
+	return true;
+}
+EXPORT_SYMBOL_GPL(xas_nomem);
+
+/*
+ * __xas_nomem() - Drop locks and allocate memory if needed.
+ * @xas: XArray operation state.
+ * @gfp: Memory allocation flags.
+ *
+ * Internal variant of xas_nomem().
+ *
+ * Return: true if memory was needed, and was successfully allocated.
+ */
+static bool __xas_nomem(struct xa_state *xas, gfp_t gfp)
+	__must_hold(xas->xa->xa_lock)
+{
+	unsigned int lock_type = xa_lock_type(xas->xa);
+
+	if (xas->xa_node != XA_ERROR(-ENOMEM)) {
+		xas_destroy(xas);
+		return false;
+	}
+	if (gfpflags_allow_blocking(gfp)) {
+		xas_unlock_type(xas, lock_type);
+		xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp);
+		xas_lock_type(xas, lock_type);
+	} else {
+		xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp);
+	}
+	if (!xas->xa_alloc)
+		return false;
+	XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list));
+	xas->xa_node = XAS_RESTART;
+	return true;
+}
+
+static void xas_update(struct xa_state *xas, struct xa_node *node)
+{
+	if (xas->xa_update)
+		xas->xa_update(node);
+	else
+		XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
+}
+
+static void *xas_alloc(struct xa_state *xas, unsigned int shift)
+{
+	struct xa_node *parent = xas->xa_node;
+	struct xa_node *node = xas->xa_alloc;
+
+	if (xas_invalid(xas))
+		return NULL;
+
+	if (node) {
+		xas->xa_alloc = NULL;
+	} else {
+		node = kmem_cache_alloc(radix_tree_node_cachep,
+					GFP_NOWAIT | __GFP_NOWARN);
+		if (!node) {
+			xas_set_err(xas, -ENOMEM);
+			return NULL;
+		}
+	}
+
+	if (parent) {
+		node->offset = xas->xa_offset;
+		parent->count++;
+		XA_NODE_BUG_ON(node, parent->count > XA_CHUNK_SIZE);
+		xas_update(xas, parent);
+	}
+	XA_NODE_BUG_ON(node, shift > BITS_PER_LONG);
+	XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
+	node->shift = shift;
+	node->count = 0;
+	node->nr_values = 0;
+	RCU_INIT_POINTER(node->parent, xas->xa_node);
+	node->array = xas->xa;
+
+	return node;
+}
+
+/*
+ * Use this to calculate the maximum index that will need to be created
+ * in order to add the entry described by @xas.  Because we cannot store a
+ * multiple-index entry at index 0, the calculation is a little more complex
+ * than you might expect.
+ */
+static unsigned long xas_max(struct xa_state *xas)
+{
+	unsigned long max = xas->xa_index;
+
+#ifdef CONFIG_XARRAY_MULTI
+	if (xas->xa_shift || xas->xa_sibs) {
+		unsigned long mask;
+		mask = (((xas->xa_sibs + 1UL) << xas->xa_shift) - 1);
+		max |= mask;
+		if (mask == max)
+			max++;
+	}
+#endif
+
+	return max;
+}
+
+/* The maximum index that can be contained in the array without expanding it */
+static unsigned long max_index(void *entry)
+{
+	if (!xa_is_node(entry))
+		return 0;
+	return (XA_CHUNK_SIZE << xa_to_node(entry)->shift) - 1;
+}
+
+static void xas_shrink(struct xa_state *xas)
+{
+	struct xarray *xa = xas->xa;
+	struct xa_node *node = xas->xa_node;
+
+	for (;;) {
+		void *entry;
+
+		XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE);
+		if (node->count != 1)
+			break;
+		entry = xa_entry_locked(xa, node, 0);
+		if (!entry)
+			break;
+		if (!xa_is_node(entry) && node->shift)
+			break;
+		xas->xa_node = XAS_BOUNDS;
+
+		RCU_INIT_POINTER(xa->xa_head, entry);
+
+		node->count = 0;
+		node->nr_values = 0;
+		if (!xa_is_node(entry))
+			RCU_INIT_POINTER(node->slots[0], XA_RETRY_ENTRY);
+		xas_update(xas, node);
+		xa_node_free(node);
+		if (!xa_is_node(entry))
+			break;
+		node = xa_to_node(entry);
+		node->parent = NULL;
+	}
+}
+
+/*
+ * xas_delete_node() - Attempt to delete an xa_node
+ * @xas: Array operation state.
+ *
+ * Attempts to delete the @xas->xa_node.  This will fail if xa->node has
+ * a non-zero reference count.
+ */
+static void xas_delete_node(struct xa_state *xas)
+{
+	struct xa_node *node = xas->xa_node;
+
+	for (;;) {
+		struct xa_node *parent;
+
+		XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE);
+		if (node->count)
+			break;
+
+		parent = xa_parent_locked(xas->xa, node);
+		xas->xa_node = parent;
+		xas->xa_offset = node->offset;
+		xa_node_free(node);
+
+		if (!parent) {
+			xas->xa->xa_head = NULL;
+			xas->xa_node = XAS_BOUNDS;
+			return;
+		}
+
+		parent->slots[xas->xa_offset] = NULL;
+		parent->count--;
+		XA_NODE_BUG_ON(parent, parent->count > XA_CHUNK_SIZE);
+		node = parent;
+		xas_update(xas, node);
+	}
+
+	if (!node->parent)
+		xas_shrink(xas);
+}
+
+/**
+ * xas_free_nodes() - Free this node and all nodes that it references
+ * @xas: Array operation state.
+ * @top: Node to free
+ *
+ * This node has been removed from the tree.  We must now free it and all
+ * of its subnodes.  There may be RCU walkers with references into the tree,
+ * so we must replace all entries with retry markers.
+ */
+static void xas_free_nodes(struct xa_state *xas, struct xa_node *top)
+{
+	unsigned int offset = 0;
+	struct xa_node *node = top;
+
+	for (;;) {
+		void *entry = xa_entry_locked(xas->xa, node, offset);
+
+		if (xa_is_node(entry)) {
+			node = xa_to_node(entry);
+			offset = 0;
+			continue;
+		}
+		if (entry)
+			RCU_INIT_POINTER(node->slots[offset], XA_RETRY_ENTRY);
+		offset++;
+		while (offset == XA_CHUNK_SIZE) {
+			struct xa_node *parent;
+
+			parent = xa_parent_locked(xas->xa, node);
+			offset = node->offset + 1;
+			node->count = 0;
+			node->nr_values = 0;
+			xas_update(xas, node);
+			xa_node_free(node);
+			if (node == top)
+				return;
+			node = parent;
+		}
+	}
+}
+
+/*
+ * xas_expand adds nodes to the head of the tree until it has reached
+ * sufficient height to be able to contain @xas->xa_index
+ */
+static int xas_expand(struct xa_state *xas, void *head)
+{
+	struct xarray *xa = xas->xa;
+	struct xa_node *node = NULL;
+	unsigned int shift = 0;
+	unsigned long max = xas_max(xas);
+
+	if (!head) {
+		if (max == 0)
+			return 0;
+		while ((max >> shift) >= XA_CHUNK_SIZE)
+			shift += XA_CHUNK_SHIFT;
+		return shift + XA_CHUNK_SHIFT;
+	} else if (xa_is_node(head)) {
+		node = xa_to_node(head);
+		shift = node->shift + XA_CHUNK_SHIFT;
+	}
+	xas->xa_node = NULL;
+
+	while (max > max_index(head)) {
+		xa_mark_t mark = 0;
+
+		XA_NODE_BUG_ON(node, shift > BITS_PER_LONG);
+		node = xas_alloc(xas, shift);
+		if (!node)
+			return -ENOMEM;
+
+		node->count = 1;
+		if (xa_is_value(head))
+			node->nr_values = 1;
+		RCU_INIT_POINTER(node->slots[0], head);
+
+		/* Propagate the aggregated mark info to the new child */
+		for (;;) {
+			if (xa_marked(xa, mark))
+				node_set_mark(node, 0, mark);
+			if (mark == XA_MARK_MAX)
+				break;
+			mark_inc(mark);
+		}
+
+		/*
+		 * Now that the new node is fully initialised, we can add
+		 * it to the tree
+		 */
+		if (xa_is_node(head)) {
+			xa_to_node(head)->offset = 0;
+			rcu_assign_pointer(xa_to_node(head)->parent, node);
+		}
+		head = xa_mk_node(node);
+		rcu_assign_pointer(xa->xa_head, head);
+		xas_update(xas, node);
+
+		shift += XA_CHUNK_SHIFT;
+	}
+
+	xas->xa_node = node;
+	return shift;
+}
+
+/*
+ * xas_create() - Create a slot to store an entry in.
+ * @xas: XArray operation state.
+ *
+ * Most users will not need to call this function directly, as it is called
+ * by xas_store().  It is useful for doing conditional store operations
+ * (see the xa_cmpxchg() implementation for an example).
+ *
+ * Return: If the slot already existed, returns the contents of this slot.
+ * If the slot was newly created, returns NULL.  If it failed to create the
+ * slot, returns NULL and indicates the error in @xas.
+ */
+static void *xas_create(struct xa_state *xas)
+{
+	struct xarray *xa = xas->xa;
+	void *entry;
+	void __rcu **slot;
+	struct xa_node *node = xas->xa_node;
+	int shift;
+	unsigned int order = xas->xa_shift;
+
+	if (xas_top(node)) {
+		entry = xa_head_locked(xa);
+		xas->xa_node = NULL;
+		shift = xas_expand(xas, entry);
+		if (shift < 0)
+			return NULL;
+		entry = xa_head_locked(xa);
+		slot = &xa->xa_head;
+	} else if (xas_error(xas)) {
+		return NULL;
+	} else if (node) {
+		unsigned int offset = xas->xa_offset;
+
+		shift = node->shift;
+		entry = xa_entry_locked(xa, node, offset);
+		slot = &node->slots[offset];
+	} else {
+		shift = 0;
+		entry = xa_head_locked(xa);
+		slot = &xa->xa_head;
+	}
+
+	while (shift > order) {
+		shift -= XA_CHUNK_SHIFT;
+		if (!entry) {
+			node = xas_alloc(xas, shift);
+			if (!node)
+				break;
+			rcu_assign_pointer(*slot, xa_mk_node(node));
+		} else if (xa_is_node(entry)) {
+			node = xa_to_node(entry);
+		} else {
+			break;
+		}
+		entry = xas_descend(xas, node);
+		slot = &node->slots[xas->xa_offset];
+	}
+
+	return entry;
+}
+
+static void update_node(struct xa_state *xas, struct xa_node *node,
+		int count, int values)
+{
+	if (!node || (!count && !values))
+		return;
+
+	node->count += count;
+	node->nr_values += values;
+	XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE);
+	XA_NODE_BUG_ON(node, node->nr_values > XA_CHUNK_SIZE);
+	xas_update(xas, node);
+	if (count < 0)
+		xas_delete_node(xas);
+}
+
+/**
+ * xas_store() - Store this entry in the XArray.
+ * @xas: XArray operation state.
+ * @entry: New entry.
+ *
+ * If @xas is operating on a multi-index entry, the entry returned by this
+ * function is essentially meaningless (it may be an internal entry or it
+ * may be %NULL, even if there are non-NULL entries at some of the indices
+ * covered by the range).  This is not a problem for any current users,
+ * and can be changed if needed.
+ *
+ * Return: The old entry at this index.
+ */
+void *xas_store(struct xa_state *xas, void *entry)
+{
+	struct xa_node *node;
+	void __rcu **slot = &xas->xa->xa_head;
+	unsigned int offset, max;
+	int count = 0;
+	int values = 0;
+	void *first, *next;
+	bool value = xa_is_value(entry);
+
+	if (entry)
+		first = xas_create(xas);
+	else
+		first = xas_load(xas);
+
+	if (xas_invalid(xas))
+		return first;
+	node = xas->xa_node;
+	if (node && (xas->xa_shift < node->shift))
+		xas->xa_sibs = 0;
+	if ((first == entry) && !xas->xa_sibs)
+		return first;
+
+	next = first;
+	offset = xas->xa_offset;
+	max = xas->xa_offset + xas->xa_sibs;
+	if (node) {
+		slot = &node->slots[offset];
+		if (xas->xa_sibs)
+			xas_squash_marks(xas);
+	}
+	if (!entry)
+		xas_init_marks(xas);
+
+	for (;;) {
+		/*
+		 * Must clear the marks before setting the entry to NULL,
+		 * otherwise xas_for_each_marked may find a NULL entry and
+		 * stop early.  rcu_assign_pointer contains a release barrier
+		 * so the mark clearing will appear to happen before the
+		 * entry is set to NULL.
+		 */
+		rcu_assign_pointer(*slot, entry);
+		if (xa_is_node(next))
+			xas_free_nodes(xas, xa_to_node(next));
+		if (!node)
+			break;
+		count += !next - !entry;
+		values += !xa_is_value(first) - !value;
+		if (entry) {
+			if (offset == max)
+				break;
+			if (!xa_is_sibling(entry))
+				entry = xa_mk_sibling(xas->xa_offset);
+		} else {
+			if (offset == XA_CHUNK_MASK)
+				break;
+		}
+		next = xa_entry_locked(xas->xa, node, ++offset);
+		if (!xa_is_sibling(next)) {
+			if (!entry && (offset > max))
+				break;
+			first = next;
+		}
+		slot++;
+	}
+
+	update_node(xas, node, count, values);
+	return first;
+}
+EXPORT_SYMBOL_GPL(xas_store);
+
 /**
  * xas_get_mark() - Returns the state of this mark.
  * @xas: XArray operation state.
@@ -240,6 +805,30 @@ void xas_clear_mark(const struct xa_state *xas, xa_mark_t mark)
 }
 EXPORT_SYMBOL_GPL(xas_clear_mark);
 
+/**
+ * xas_init_marks() - Initialise all marks for the entry
+ * @xas: Array operations state.
+ *
+ * Initialise all marks for the entry specified by @xas.  If we're tracking
+ * free entries with a mark, we need to set it on all entries.  All other
+ * marks are cleared.
+ *
+ * This implementation is not as efficient as it could be; we may walk
+ * up the tree multiple times.
+ */
+void xas_init_marks(const struct xa_state *xas)
+{
+	xa_mark_t mark = 0;
+
+	for (;;) {
+		xas_clear_mark(xas, mark);
+		if (mark == XA_MARK_MAX)
+			break;
+		mark_inc(mark);
+	}
+}
+EXPORT_SYMBOL_GPL(xas_init_marks);
+
 /**
  * xa_init_flags() - Initialise an empty XArray with flags.
  * @xa: XArray.
@@ -253,9 +842,19 @@ EXPORT_SYMBOL_GPL(xas_clear_mark);
  */
 void xa_init_flags(struct xarray *xa, gfp_t flags)
 {
+	unsigned int lock_type;
+	static struct lock_class_key xa_lock_irq;
+	static struct lock_class_key xa_lock_bh;
+
 	spin_lock_init(&xa->xa_lock);
 	xa->xa_flags = flags;
 	xa->xa_head = NULL;
+
+	lock_type = xa_lock_type(xa);
+	if (lock_type == XA_LOCK_IRQ)
+		lockdep_set_class(&xa->xa_lock, &xa_lock_irq);
+	else if (lock_type == XA_LOCK_BH)
+		lockdep_set_class(&xa->xa_lock, &xa_lock_bh);
 }
 EXPORT_SYMBOL(xa_init_flags);
 
@@ -282,6 +881,100 @@ void *xa_load(struct xarray *xa, unsigned long index)
 }
 EXPORT_SYMBOL(xa_load);
 
+static void *xas_result(struct xa_state *xas, void *curr)
+{
+	XA_NODE_BUG_ON(xas->xa_node, xa_is_internal(curr));
+	if (xas_error(xas))
+		curr = xas->xa_node;
+	return curr;
+}
+
+/**
+ * __xa_erase() - Erase this entry from the XArray while locked.
+ * @xa: XArray.
+ * @index: Index into array.
+ *
+ * If the entry at this index is a multi-index entry then all indices will
+ * be erased, and the entry will no longer be a multi-index entry.
+ * This function expects the xa_lock to be held on entry.
+ *
+ * Context: Any context.  Expects xa_lock to be held on entry.  May
+ * release and reacquire xa_lock if @gfp flags permit.
+ * Return: The old entry at this index.
+ */
+void *__xa_erase(struct xarray *xa, unsigned long index)
+{
+	XA_STATE(xas, xa, index);
+	return xas_result(&xas, xas_store(&xas, NULL));
+}
+EXPORT_SYMBOL_GPL(__xa_erase);
+
+/**
+ * xa_store() - Store this entry in the XArray.
+ * @xa: XArray.
+ * @index: Index into array.
+ * @entry: New entry.
+ * @gfp: Memory allocation flags.
+ *
+ * After this function returns, loads from this index will return @entry.
+ * Storing into an existing multislot entry updates the entry of every index.
+ * The marks associated with @index are unaffected unless @entry is %NULL.
+ *
+ * Context: Process context.  Takes and releases the xa_lock.  May sleep
+ * if the @gfp flags permit.
+ * Return: The old entry at this index on success, xa_err(-EINVAL) if @entry
+ * cannot be stored in an XArray, or xa_err(-ENOMEM) if memory allocation
+ * failed.
+ */
+void *xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp)
+{
+	XA_STATE(xas, xa, index);
+	void *curr;
+
+	if (WARN_ON_ONCE(xa_is_internal(entry)))
+		return XA_ERROR(-EINVAL);
+
+	do {
+		xas_lock(&xas);
+		curr = xas_store(&xas, entry);
+		xas_unlock(&xas);
+	} while (xas_nomem(&xas, gfp));
+
+	return xas_result(&xas, curr);
+}
+EXPORT_SYMBOL(xa_store);
+
+/**
+ * __xa_store() - Store this entry in the XArray.
+ * @xa: XArray.
+ * @index: Index into array.
+ * @entry: New entry.
+ * @gfp: Memory allocation flags.
+ *
+ * You must already be holding the xa_lock when calling this function.
+ * It will drop the lock if needed to allocate memory, and then reacquire
+ * it afterwards.
+ *
+ * Context: Any context.  Expects xa_lock to be held on entry.  May
+ * release and reacquire xa_lock if @gfp flags permit.
+ * Return: The old entry at this index or xa_err() if an error happened.
+ */
+void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp)
+{
+	XA_STATE(xas, xa, index);
+	void *curr;
+
+	if (WARN_ON_ONCE(xa_is_internal(entry)))
+		return XA_ERROR(-EINVAL);
+
+	do {
+		curr = xas_store(&xas, entry);
+	} while (__xas_nomem(&xas, gfp));
+
+	return xas_result(&xas, curr);
+}
+EXPORT_SYMBOL(__xa_store);
+
 /**
  * __xa_set_mark() - Set this mark on this entry while locked.
  * @xa: XArray.
diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index e63662db131b..05dca5c203f3 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -15,6 +15,7 @@ void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, int bits);
 int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, unsigned int bits);
+void bitmap_clear(unsigned long *map, unsigned int start, int len);
 
 #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
 
diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h
index 622266b197d0..c934572d935c 100644
--- a/tools/include/linux/spinlock.h
+++ b/tools/include/linux/spinlock.h
@@ -37,4 +37,6 @@ static inline bool arch_spin_is_locked(arch_spinlock_t *mutex)
 	return true;
 }
 
+#include <linux/lockdep.h>
+
 #endif
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index 1379f1d78d0b..acf1afa01c5b 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -5,7 +5,7 @@ CFLAGS += -I. -I../../include -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address \
 LDFLAGS += -fsanitize=address -fsanitize=undefined
 LDLIBS+= -lpthread -lurcu
 TARGETS = main idr-test multiorder xarray
-CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o
+CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o bitmap.o
 OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \
 	 tag_check.o multiorder.o idr-test.o iteration_check.o benchmark.o
 
diff --git a/tools/testing/radix-tree/bitmap.c b/tools/testing/radix-tree/bitmap.c
new file mode 100644
index 000000000000..66ec4a24a203
--- /dev/null
+++ b/tools/testing/radix-tree/bitmap.c
@@ -0,0 +1,23 @@
+/* lib/bitmap.c pulls in at least two other files. */
+
+#include <linux/bitmap.h>
+
+void bitmap_clear(unsigned long *map, unsigned int start, int len)
+{
+	unsigned long *p = map + BIT_WORD(start);
+	const unsigned int size = start + len;
+	int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
+	unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);
+
+	while (len - bits_to_clear >= 0) {
+		*p &= ~mask_to_clear;
+		len -= bits_to_clear;
+		bits_to_clear = BITS_PER_LONG;
+		mask_to_clear = ~0UL;
+		p++;
+	}
+	if (len) {
+		mask_to_clear &= BITMAP_LAST_WORD_MASK(size);
+		*p &= ~mask_to_clear;
+	}
+}
diff --git a/tools/testing/radix-tree/linux/kernel.h b/tools/testing/radix-tree/linux/kernel.h
index 5d06ac75a14d..4568248222ae 100644
--- a/tools/testing/radix-tree/linux/kernel.h
+++ b/tools/testing/radix-tree/linux/kernel.h
@@ -18,4 +18,8 @@
 #define pr_debug printk
 #define pr_cont printk
 
+#define __acquires(x)
+#define __releases(x)
+#define __must_hold(x)
+
 #endif /* _KERNEL_H */
diff --git a/tools/testing/radix-tree/linux/lockdep.h b/tools/testing/radix-tree/linux/lockdep.h
new file mode 100644
index 000000000000..565fccdfe6e9
--- /dev/null
+++ b/tools/testing/radix-tree/linux/lockdep.h
@@ -0,0 +1,11 @@
+#ifndef _LINUX_LOCKDEP_H
+#define _LINUX_LOCKDEP_H
+struct lock_class_key {
+	unsigned int a;
+};
+
+static inline void lockdep_set_class(spinlock_t *lock,
+					struct lock_class_key *key)
+{
+}
+#endif /* _LINUX_LOCKDEP_H */
-- 
cgit 


From f32f004cddf86d63a9c42994bbce9f4e2f07c9fa Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Wed, 4 Jul 2018 15:42:46 -0400
Subject: ida: Convert to XArray

Use the XA_TRACK_FREE ability to track which entries have a free bit,
similarly to how it uses the radix tree's IDR_FREE tag.  This eliminates
the per-cpu ida_bitmap preload, and fixes the memory consumption
regression I introduced when making the IDR able to store any pointer.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 include/linux/idr.h                 |  18 +-
 lib/idr.c                           | 379 +++++++++++++++++++-----------------
 lib/radix-tree.c                    |  71 -------
 tools/testing/radix-tree/idr-test.c |   8 +-
 4 files changed, 213 insertions(+), 263 deletions(-)

(limited to 'tools/testing')

diff --git a/include/linux/idr.h b/include/linux/idr.h
index 3ec8628ce17f..60daf34b625d 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -214,8 +214,7 @@ static inline void idr_preload_end(void)
 	     ++id, (entry) = idr_get_next((idr), &(id)))
 
 /*
- * IDA - IDR based id allocator, use when translation from id to
- * pointer isn't necessary.
+ * IDA - ID Allocator, use when translation from id to pointer isn't necessary.
  */
 #define IDA_CHUNK_SIZE		128	/* 128 bytes per chunk */
 #define IDA_BITMAP_LONGS	(IDA_CHUNK_SIZE / sizeof(long))
@@ -225,14 +224,14 @@ struct ida_bitmap {
 	unsigned long		bitmap[IDA_BITMAP_LONGS];
 };
 
-DECLARE_PER_CPU(struct ida_bitmap *, ida_bitmap);
-
 struct ida {
-	struct radix_tree_root	ida_rt;
+	struct xarray xa;
 };
 
+#define IDA_INIT_FLAGS	(XA_FLAGS_LOCK_IRQ | XA_FLAGS_ALLOC)
+
 #define IDA_INIT(name)	{						\
-	.ida_rt = RADIX_TREE_INIT(name, IDR_RT_MARKER | GFP_NOWAIT),	\
+	.xa = XARRAY_INIT(name, IDA_INIT_FLAGS)				\
 }
 #define DEFINE_IDA(name)	struct ida name = IDA_INIT(name)
 
@@ -292,7 +291,7 @@ static inline int ida_alloc_max(struct ida *ida, unsigned int max, gfp_t gfp)
 
 static inline void ida_init(struct ida *ida)
 {
-	INIT_RADIX_TREE(&ida->ida_rt, IDR_RT_MARKER | GFP_NOWAIT);
+	xa_init_flags(&ida->xa, IDA_INIT_FLAGS);
 }
 
 #define ida_simple_get(ida, start, end, gfp)	\
@@ -301,9 +300,6 @@ static inline void ida_init(struct ida *ida)
 
 static inline bool ida_is_empty(const struct ida *ida)
 {
-	return radix_tree_empty(&ida->ida_rt);
+	return xa_empty(&ida->xa);
 }
-
-/* in lib/radix-tree.c */
-int ida_pre_get(struct ida *ida, gfp_t gfp_mask);
 #endif /* __IDR_H__ */
diff --git a/lib/idr.c b/lib/idr.c
index 9a366b5be2c2..3c20ad9b0463 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -6,8 +6,6 @@
 #include <linux/spinlock.h>
 #include <linux/xarray.h>
 
-DEFINE_PER_CPU(struct ida_bitmap *, ida_bitmap);
-
 /**
  * idr_alloc_u32() - Allocate an ID.
  * @idr: IDR handle.
@@ -320,6 +318,9 @@ EXPORT_SYMBOL(idr_replace);
  * free the individual IDs in it.  You can use ida_is_empty() to find
  * out whether the IDA has any IDs currently allocated.
  *
+ * The IDA handles its own locking.  It is safe to call any of the IDA
+ * functions without synchronisation in your code.
+ *
  * IDs are currently limited to the range [0-INT_MAX].  If this is an awkward
  * limitation, it should be quite straightforward to raise the maximum.
  */
@@ -327,151 +328,197 @@ EXPORT_SYMBOL(idr_replace);
 /*
  * Developer's notes:
  *
- * The IDA uses the functionality provided by the IDR & radix tree to store
- * bitmaps in each entry.  The IDR_FREE tag means there is at least one bit
- * free, unlike the IDR where it means at least one entry is free.
+ * The IDA uses the functionality provided by the XArray to store bitmaps in
+ * each entry.  The XA_FREE_MARK is only cleared when all bits in the bitmap
+ * have been set.
  *
- * I considered telling the radix tree that each slot is an order-10 node
- * and storing the bit numbers in the radix tree, but the radix tree can't
- * allow a single multiorder entry at index 0, which would significantly
- * increase memory consumption for the IDA.  So instead we divide the index
- * by the number of bits in the leaf bitmap before doing a radix tree lookup.
+ * I considered telling the XArray that each slot is an order-10 node
+ * and indexing by bit number, but the XArray can't allow a single multi-index
+ * entry in the head, which would significantly increase memory consumption
+ * for the IDA.  So instead we divide the index by the number of bits in the
+ * leaf bitmap before doing a radix tree lookup.
  *
  * As an optimisation, if there are only a few low bits set in any given
  * leaf, instead of allocating a 128-byte bitmap, we store the bits
- * directly in the entry.
- *
- * We allow the radix tree 'exceptional' count to get out of date.  Nothing
- * in the IDA nor the radix tree code checks it.  If it becomes important
- * to maintain an accurate exceptional count, switch the rcu_assign_pointer()
- * calls to radix_tree_iter_replace() which will correct the exceptional
- * count.
- *
- * The IDA always requires a lock to alloc/free.  If we add a 'test_bit'
+ * as a value entry.  Value entries never have the XA_FREE_MARK cleared
+ * because we can always convert them into a bitmap entry.
+ *
+ * It would be possible to optimise further; once we've run out of a
+ * single 128-byte bitmap, we currently switch to a 576-byte node, put
+ * the 128-byte bitmap in the first entry and then start allocating extra
+ * 128-byte entries.  We could instead use the 512 bytes of the node's
+ * data as a bitmap before moving to that scheme.  I do not believe this
+ * is a worthwhile optimisation; Rasmus Villemoes surveyed the current
+ * users of the IDA and almost none of them use more than 1024 entries.
+ * Those that do use more than the 8192 IDs that the 512 bytes would
+ * provide.
+ *
+ * The IDA always uses a lock to alloc/free.  If we add a 'test_bit'
  * equivalent, it will still need locking.  Going to RCU lookup would require
  * using RCU to free bitmaps, and that's not trivial without embedding an
  * RCU head in the bitmap, which adds a 2-pointer overhead to each 128-byte
  * bitmap, which is excessive.
  */
 
-#define IDA_MAX (0x80000000U / IDA_BITMAP_BITS - 1)
-
-static int ida_get_new_above(struct ida *ida, int start)
+/**
+ * ida_alloc_range() - Allocate an unused ID.
+ * @ida: IDA handle.
+ * @min: Lowest ID to allocate.
+ * @max: Highest ID to allocate.
+ * @gfp: Memory allocation flags.
+ *
+ * Allocate an ID between @min and @max, inclusive.  The allocated ID will
+ * not exceed %INT_MAX, even if @max is larger.
+ *
+ * Context: Any context.
+ * Return: The allocated ID, or %-ENOMEM if memory could not be allocated,
+ * or %-ENOSPC if there are no free IDs.
+ */
+int ida_alloc_range(struct ida *ida, unsigned int min, unsigned int max,
+			gfp_t gfp)
 {
-	struct radix_tree_root *root = &ida->ida_rt;
-	void __rcu **slot;
-	struct radix_tree_iter iter;
-	struct ida_bitmap *bitmap;
-	unsigned long index;
-	unsigned bit;
-	int new;
-
-	index = start / IDA_BITMAP_BITS;
-	bit = start % IDA_BITMAP_BITS;
-
-	slot = radix_tree_iter_init(&iter, index);
-	for (;;) {
-		if (slot)
-			slot = radix_tree_next_slot(slot, &iter,
-						RADIX_TREE_ITER_TAGGED);
-		if (!slot) {
-			slot = idr_get_free(root, &iter, GFP_NOWAIT, IDA_MAX);
-			if (IS_ERR(slot)) {
-				if (slot == ERR_PTR(-ENOMEM))
-					return -EAGAIN;
-				return PTR_ERR(slot);
+	XA_STATE(xas, &ida->xa, min / IDA_BITMAP_BITS);
+	unsigned bit = min % IDA_BITMAP_BITS;
+	unsigned long flags;
+	struct ida_bitmap *bitmap, *alloc = NULL;
+
+	if ((int)min < 0)
+		return -ENOSPC;
+
+	if ((int)max < 0)
+		max = INT_MAX;
+
+retry:
+	xas_lock_irqsave(&xas, flags);
+next:
+	bitmap = xas_find_marked(&xas, max / IDA_BITMAP_BITS, XA_FREE_MARK);
+	if (xas.xa_index > min / IDA_BITMAP_BITS)
+		bit = 0;
+	if (xas.xa_index * IDA_BITMAP_BITS + bit > max)
+		goto nospc;
+
+	if (xa_is_value(bitmap)) {
+		unsigned long tmp = xa_to_value(bitmap);
+
+		if (bit < BITS_PER_XA_VALUE) {
+			bit = find_next_zero_bit(&tmp, BITS_PER_XA_VALUE, bit);
+			if (xas.xa_index * IDA_BITMAP_BITS + bit > max)
+				goto nospc;
+			if (bit < BITS_PER_XA_VALUE) {
+				tmp |= 1UL << bit;
+				xas_store(&xas, xa_mk_value(tmp));
+				goto out;
 			}
 		}
-		if (iter.index > index)
-			bit = 0;
-		new = iter.index * IDA_BITMAP_BITS;
-		bitmap = rcu_dereference_raw(*slot);
-		if (xa_is_value(bitmap)) {
-			unsigned long tmp = xa_to_value(bitmap);
-			int vbit = find_next_zero_bit(&tmp, BITS_PER_XA_VALUE,
-							bit);
-			if (vbit < BITS_PER_XA_VALUE) {
-				tmp |= 1UL << vbit;
-				rcu_assign_pointer(*slot, xa_mk_value(tmp));
-				return new + vbit;
-			}
-			bitmap = this_cpu_xchg(ida_bitmap, NULL);
-			if (!bitmap)
-				return -EAGAIN;
-			bitmap->bitmap[0] = tmp;
-			rcu_assign_pointer(*slot, bitmap);
+		bitmap = alloc;
+		if (!bitmap)
+			bitmap = kzalloc(sizeof(*bitmap), GFP_NOWAIT);
+		if (!bitmap)
+			goto alloc;
+		bitmap->bitmap[0] = tmp;
+		xas_store(&xas, bitmap);
+		if (xas_error(&xas)) {
+			bitmap->bitmap[0] = 0;
+			goto out;
 		}
+	}
 
-		if (bitmap) {
-			bit = find_next_zero_bit(bitmap->bitmap,
-							IDA_BITMAP_BITS, bit);
-			new += bit;
-			if (new < 0)
-				return -ENOSPC;
-			if (bit == IDA_BITMAP_BITS)
-				continue;
+	if (bitmap) {
+		bit = find_next_zero_bit(bitmap->bitmap, IDA_BITMAP_BITS, bit);
+		if (xas.xa_index * IDA_BITMAP_BITS + bit > max)
+			goto nospc;
+		if (bit == IDA_BITMAP_BITS)
+			goto next;
 
-			__set_bit(bit, bitmap->bitmap);
-			if (bitmap_full(bitmap->bitmap, IDA_BITMAP_BITS))
-				radix_tree_iter_tag_clear(root, &iter,
-								IDR_FREE);
+		__set_bit(bit, bitmap->bitmap);
+		if (bitmap_full(bitmap->bitmap, IDA_BITMAP_BITS))
+			xas_clear_mark(&xas, XA_FREE_MARK);
+	} else {
+		if (bit < BITS_PER_XA_VALUE) {
+			bitmap = xa_mk_value(1UL << bit);
 		} else {
-			new += bit;
-			if (new < 0)
-				return -ENOSPC;
-			if (bit < BITS_PER_XA_VALUE) {
-				bitmap = xa_mk_value(1UL << bit);
-			} else {
-				bitmap = this_cpu_xchg(ida_bitmap, NULL);
-				if (!bitmap)
-					return -EAGAIN;
-				__set_bit(bit, bitmap->bitmap);
-			}
-			radix_tree_iter_replace(root, &iter, slot, bitmap);
+			bitmap = alloc;
+			if (!bitmap)
+				bitmap = kzalloc(sizeof(*bitmap), GFP_NOWAIT);
+			if (!bitmap)
+				goto alloc;
+			__set_bit(bit, bitmap->bitmap);
 		}
-
-		return new;
+		xas_store(&xas, bitmap);
+	}
+out:
+	xas_unlock_irqrestore(&xas, flags);
+	if (xas_nomem(&xas, gfp)) {
+		xas.xa_index = min / IDA_BITMAP_BITS;
+		bit = min % IDA_BITMAP_BITS;
+		goto retry;
 	}
+	if (bitmap != alloc)
+		kfree(alloc);
+	if (xas_error(&xas))
+		return xas_error(&xas);
+	return xas.xa_index * IDA_BITMAP_BITS + bit;
+alloc:
+	xas_unlock_irqrestore(&xas, flags);
+	alloc = kzalloc(sizeof(*bitmap), gfp);
+	if (!alloc)
+		return -ENOMEM;
+	xas_set(&xas, min / IDA_BITMAP_BITS);
+	bit = min % IDA_BITMAP_BITS;
+	goto retry;
+nospc:
+	xas_unlock_irqrestore(&xas, flags);
+	return -ENOSPC;
 }
+EXPORT_SYMBOL(ida_alloc_range);
 
-static void ida_remove(struct ida *ida, int id)
+/**
+ * ida_free() - Release an allocated ID.
+ * @ida: IDA handle.
+ * @id: Previously allocated ID.
+ *
+ * Context: Any context.
+ */
+void ida_free(struct ida *ida, unsigned int id)
 {
-	unsigned long index = id / IDA_BITMAP_BITS;
-	unsigned offset = id % IDA_BITMAP_BITS;
+	XA_STATE(xas, &ida->xa, id / IDA_BITMAP_BITS);
+	unsigned bit = id % IDA_BITMAP_BITS;
 	struct ida_bitmap *bitmap;
-	unsigned long *btmp;
-	struct radix_tree_iter iter;
-	void __rcu **slot;
+	unsigned long flags;
 
-	slot = radix_tree_iter_lookup(&ida->ida_rt, &iter, index);
-	if (!slot)
-		goto err;
+	BUG_ON((int)id < 0);
+
+	xas_lock_irqsave(&xas, flags);
+	bitmap = xas_load(&xas);
 
-	bitmap = rcu_dereference_raw(*slot);
 	if (xa_is_value(bitmap)) {
-		btmp = (unsigned long *)slot;
-		offset += 1; /* Intimate knowledge of the value encoding */
-		if (offset >= BITS_PER_LONG)
+		unsigned long v = xa_to_value(bitmap);
+		if (bit >= BITS_PER_XA_VALUE)
+			goto err;
+		if (!(v & (1UL << bit)))
 			goto err;
+		v &= ~(1UL << bit);
+		if (!v)
+			goto delete;
+		xas_store(&xas, xa_mk_value(v));
 	} else {
-		btmp = bitmap->bitmap;
-	}
-	if (!test_bit(offset, btmp))
-		goto err;
-
-	__clear_bit(offset, btmp);
-	radix_tree_iter_tag_set(&ida->ida_rt, &iter, IDR_FREE);
-	if (xa_is_value(bitmap)) {
-		if (xa_to_value(rcu_dereference_raw(*slot)) == 0)
-			radix_tree_iter_delete(&ida->ida_rt, &iter, slot);
-	} else if (bitmap_empty(btmp, IDA_BITMAP_BITS)) {
-		kfree(bitmap);
-		radix_tree_iter_delete(&ida->ida_rt, &iter, slot);
+		if (!test_bit(bit, bitmap->bitmap))
+			goto err;
+		__clear_bit(bit, bitmap->bitmap);
+		xas_set_mark(&xas, XA_FREE_MARK);
+		if (bitmap_empty(bitmap->bitmap, IDA_BITMAP_BITS)) {
+			kfree(bitmap);
+delete:
+			xas_store(&xas, NULL);
+		}
 	}
+	xas_unlock_irqrestore(&xas, flags);
 	return;
  err:
+	xas_unlock_irqrestore(&xas, flags);
 	WARN(1, "ida_free called for id=%d which is not allocated.\n", id);
 }
+EXPORT_SYMBOL(ida_free);
 
 /**
  * ida_destroy() - Free all IDs.
@@ -486,80 +533,60 @@ static void ida_remove(struct ida *ida, int id)
  */
 void ida_destroy(struct ida *ida)
 {
+	XA_STATE(xas, &ida->xa, 0);
+	struct ida_bitmap *bitmap;
 	unsigned long flags;
-	struct radix_tree_iter iter;
-	void __rcu **slot;
 
-	xa_lock_irqsave(&ida->ida_rt, flags);
-	radix_tree_for_each_slot(slot, &ida->ida_rt, &iter, 0) {
-		struct ida_bitmap *bitmap = rcu_dereference_raw(*slot);
+	xas_lock_irqsave(&xas, flags);
+	xas_for_each(&xas, bitmap, ULONG_MAX) {
 		if (!xa_is_value(bitmap))
 			kfree(bitmap);
-		radix_tree_iter_delete(&ida->ida_rt, &iter, slot);
+		xas_store(&xas, NULL);
 	}
-	xa_unlock_irqrestore(&ida->ida_rt, flags);
+	xas_unlock_irqrestore(&xas, flags);
 }
 EXPORT_SYMBOL(ida_destroy);
 
-/**
- * ida_alloc_range() - Allocate an unused ID.
- * @ida: IDA handle.
- * @min: Lowest ID to allocate.
- * @max: Highest ID to allocate.
- * @gfp: Memory allocation flags.
- *
- * Allocate an ID between @min and @max, inclusive.  The allocated ID will
- * not exceed %INT_MAX, even if @max is larger.
- *
- * Context: Any context.
- * Return: The allocated ID, or %-ENOMEM if memory could not be allocated,
- * or %-ENOSPC if there are no free IDs.
- */
-int ida_alloc_range(struct ida *ida, unsigned int min, unsigned int max,
-			gfp_t gfp)
-{
-	int id = 0;
-	unsigned long flags;
-
-	if ((int)min < 0)
-		return -ENOSPC;
+#ifndef __KERNEL__
+extern void xa_dump_index(unsigned long index, unsigned int shift);
+#define IDA_CHUNK_SHIFT		ilog2(IDA_BITMAP_BITS)
 
-	if ((int)max < 0)
-		max = INT_MAX;
-
-again:
-	xa_lock_irqsave(&ida->ida_rt, flags);
-	id = ida_get_new_above(ida, min);
-	if (id > (int)max) {
-		ida_remove(ida, id);
-		id = -ENOSPC;
-	}
-	xa_unlock_irqrestore(&ida->ida_rt, flags);
+static void ida_dump_entry(void *entry, unsigned long index)
+{
+	unsigned long i;
+
+	if (!entry)
+		return;
+
+	if (xa_is_node(entry)) {
+		struct xa_node *node = xa_to_node(entry);
+		unsigned int shift = node->shift + IDA_CHUNK_SHIFT +
+			XA_CHUNK_SHIFT;
+
+		xa_dump_index(index * IDA_BITMAP_BITS, shift);
+		xa_dump_node(node);
+		for (i = 0; i < XA_CHUNK_SIZE; i++)
+			ida_dump_entry(node->slots[i],
+					index | (i << node->shift));
+	} else if (xa_is_value(entry)) {
+		xa_dump_index(index * IDA_BITMAP_BITS, ilog2(BITS_PER_LONG));
+		pr_cont("value: data %lx [%px]\n", xa_to_value(entry), entry);
+	} else {
+		struct ida_bitmap *bitmap = entry;
 
-	if (unlikely(id == -EAGAIN)) {
-		if (!ida_pre_get(ida, gfp))
-			return -ENOMEM;
-		goto again;
+		xa_dump_index(index * IDA_BITMAP_BITS, IDA_CHUNK_SHIFT);
+		pr_cont("bitmap: %p data", bitmap);
+		for (i = 0; i < IDA_BITMAP_LONGS; i++)
+			pr_cont(" %lx", bitmap->bitmap[i]);
+		pr_cont("\n");
 	}
-
-	return id;
 }
-EXPORT_SYMBOL(ida_alloc_range);
 
-/**
- * ida_free() - Release an allocated ID.
- * @ida: IDA handle.
- * @id: Previously allocated ID.
- *
- * Context: Any context.
- */
-void ida_free(struct ida *ida, unsigned int id)
+static void ida_dump(struct ida *ida)
 {
-	unsigned long flags;
-
-	BUG_ON((int)id < 0);
-	xa_lock_irqsave(&ida->ida_rt, flags);
-	ida_remove(ida, id);
-	xa_unlock_irqrestore(&ida->ida_rt, flags);
+	struct xarray *xa = &ida->xa;
+	pr_debug("ida: %p node %p free %d\n", ida, xa->xa_head,
+				xa->xa_flags >> ROOT_TAG_SHIFT);
+	ida_dump_entry(xa->xa_head, 0);
 }
-EXPORT_SYMBOL(ida_free);
+#endif
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 3479d93c32b9..68702061464f 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -255,54 +255,6 @@ static unsigned long next_index(unsigned long index,
 	return (index & ~node_maxindex(node)) + (offset << node->shift);
 }
 
-#ifndef __KERNEL__
-static void dump_ida_node(void *entry, unsigned long index)
-{
-	unsigned long i;
-
-	if (!entry)
-		return;
-
-	if (radix_tree_is_internal_node(entry)) {
-		struct radix_tree_node *node = entry_to_node(entry);
-
-		pr_debug("ida node: %p offset %d indices %lu-%lu parent %p free %lx shift %d count %d\n",
-			node, node->offset, index * IDA_BITMAP_BITS,
-			((index | node_maxindex(node)) + 1) *
-				IDA_BITMAP_BITS - 1,
-			node->parent, node->tags[0][0], node->shift,
-			node->count);
-		for (i = 0; i < RADIX_TREE_MAP_SIZE; i++)
-			dump_ida_node(node->slots[i],
-					index | (i << node->shift));
-	} else if (xa_is_value(entry)) {
-		pr_debug("ida excp: %p offset %d indices %lu-%lu data %lx\n",
-				entry, (int)(index & RADIX_TREE_MAP_MASK),
-				index * IDA_BITMAP_BITS,
-				index * IDA_BITMAP_BITS + BITS_PER_XA_VALUE,
-				xa_to_value(entry));
-	} else {
-		struct ida_bitmap *bitmap = entry;
-
-		pr_debug("ida btmp: %p offset %d indices %lu-%lu data", bitmap,
-				(int)(index & RADIX_TREE_MAP_MASK),
-				index * IDA_BITMAP_BITS,
-				(index + 1) * IDA_BITMAP_BITS - 1);
-		for (i = 0; i < IDA_BITMAP_LONGS; i++)
-			pr_cont(" %lx", bitmap->bitmap[i]);
-		pr_cont("\n");
-	}
-}
-
-static void ida_dump(struct ida *ida)
-{
-	struct radix_tree_root *root = &ida->ida_rt;
-	pr_debug("ida: %p node %p free %d\n", ida, root->xa_head,
-				root->xa_flags >> ROOT_TAG_SHIFT);
-	dump_ida_node(root->xa_head, 0);
-}
-#endif
-
 /*
  * This assumes that the caller has performed appropriate preallocation, and
  * that the caller has pinned this thread of control to the current CPU.
@@ -2039,27 +1991,6 @@ void idr_preload(gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(idr_preload);
 
-int ida_pre_get(struct ida *ida, gfp_t gfp)
-{
-	/*
-	 * The IDA API has no preload_end() equivalent.  Instead,
-	 * ida_get_new() can return -EAGAIN, prompting the caller
-	 * to return to the ida_pre_get() step.
-	 */
-	if (!__radix_tree_preload(gfp, IDA_PRELOAD_SIZE))
-		preempt_enable();
-
-	if (!this_cpu_read(ida_bitmap)) {
-		struct ida_bitmap *bitmap = kzalloc(sizeof(*bitmap), gfp);
-		if (!bitmap)
-			return 0;
-		if (this_cpu_cmpxchg(ida_bitmap, NULL, bitmap))
-			kfree(bitmap);
-	}
-
-	return 1;
-}
-
 void __rcu **idr_get_free(struct radix_tree_root *root,
 			      struct radix_tree_iter *iter, gfp_t gfp,
 			      unsigned long max)
@@ -2201,8 +2132,6 @@ static int radix_tree_cpu_dead(unsigned int cpu)
 		kmem_cache_free(radix_tree_node_cachep, node);
 		rtp->nr--;
 	}
-	kfree(per_cpu(ida_bitmap, cpu));
-	per_cpu(ida_bitmap, cpu) = NULL;
 	return 0;
 }
 
diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index a5a4494922a6..1b63bdb7688f 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -402,16 +402,15 @@ void ida_check_nomem(void)
  */
 void ida_check_conv_user(void)
 {
-#if 0
 	DEFINE_IDA(ida);
 	unsigned long i;
 
-	radix_tree_cpu_dead(1);
 	for (i = 0; i < 1000000; i++) {
 		int id = ida_alloc(&ida, GFP_NOWAIT);
 		if (id == -ENOMEM) {
-			IDA_BUG_ON(&ida, (i % IDA_BITMAP_BITS) !=
-					BITS_PER_XA_VALUE);
+			IDA_BUG_ON(&ida, ((i % IDA_BITMAP_BITS) !=
+					  BITS_PER_XA_VALUE) &&
+					 ((i % IDA_BITMAP_BITS) != 0));
 			id = ida_alloc(&ida, GFP_KERNEL);
 		} else {
 			IDA_BUG_ON(&ida, (i % IDA_BITMAP_BITS) ==
@@ -420,7 +419,6 @@ void ida_check_conv_user(void)
 		IDA_BUG_ON(&ida, id != i);
 	}
 	ida_destroy(&ida);
-#endif
 }
 
 void ida_check_random(void)
-- 
cgit 


From 3ece58a270cd1e5026282abe778bd50db7a11d08 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Wed, 16 May 2018 18:00:33 -0400
Subject: page cache: Convert find_get_pages_contig to XArray

There's no direct replacement for radix_tree_for_each_contig()
in the XArray API as it's an unusual thing to do.  Instead,
open-code a loop using xas_next().  This removes the only user of
radix_tree_for_each_contig() so delete the iterator from the API and
the test suite code for it.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 .clang-format                          |  1 -
 include/linux/radix-tree.h             | 17 -----------
 mm/filemap.c                           | 53 ++++++++++++++--------------------
 tools/testing/radix-tree/regression3.c | 23 ---------------
 4 files changed, 22 insertions(+), 72 deletions(-)

(limited to 'tools/testing')

diff --git a/.clang-format b/.clang-format
index 1d5da22e0ba5..e6080f5834a3 100644
--- a/.clang-format
+++ b/.clang-format
@@ -323,7 +323,6 @@ ForEachMacros:
   - 'protocol_for_each_card'
   - 'protocol_for_each_dev'
   - 'queue_for_each_hw_ctx'
-  - 'radix_tree_for_each_contig'
   - 'radix_tree_for_each_slot'
   - 'radix_tree_for_each_tagged'
   - 'rbtree_postorder_for_each_entry_safe'
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index d55de428a589..023e888e1163 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -522,23 +522,6 @@ static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot,
 	     slot || (slot = radix_tree_next_chunk(root, iter, 0)) ;	\
 	     slot = radix_tree_next_slot(slot, iter, 0))
 
-/**
- * radix_tree_for_each_contig - iterate over contiguous slots
- *
- * @slot:	the void** variable for pointer to slot
- * @root:	the struct radix_tree_root pointer
- * @iter:	the struct radix_tree_iter pointer
- * @start:	iteration starting index
- *
- * @slot points to radix tree slot, @iter->index contains its index.
- */
-#define radix_tree_for_each_contig(slot, root, iter, start)		\
-	for (slot = radix_tree_iter_init(iter, start) ;			\
-	     slot || (slot = radix_tree_next_chunk(root, iter,		\
-				RADIX_TREE_ITER_CONTIG)) ;		\
-	     slot = radix_tree_next_slot(slot, iter,			\
-				RADIX_TREE_ITER_CONTIG))
-
 /**
  * radix_tree_for_each_tagged - iterate over tagged slots
  *
diff --git a/mm/filemap.c b/mm/filemap.c
index b72c39fe61c2..089b67598100 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1721,57 +1721,43 @@ out:
 unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
 			       unsigned int nr_pages, struct page **pages)
 {
-	struct radix_tree_iter iter;
-	void **slot;
+	XA_STATE(xas, &mapping->i_pages, index);
+	struct page *page;
 	unsigned int ret = 0;
 
 	if (unlikely(!nr_pages))
 		return 0;
 
 	rcu_read_lock();
-	radix_tree_for_each_contig(slot, &mapping->i_pages, &iter, index) {
-		struct page *head, *page;
-repeat:
-		page = radix_tree_deref_slot(slot);
-		/* The hole, there no reason to continue */
-		if (unlikely(!page))
-			break;
-
-		if (radix_tree_exception(page)) {
-			if (radix_tree_deref_retry(page)) {
-				slot = radix_tree_iter_retry(&iter);
-				continue;
-			}
-			/*
-			 * A shadow entry of a recently evicted page,
-			 * or a swap entry from shmem/tmpfs.  Stop
-			 * looking for contiguous pages.
-			 */
+	for (page = xas_load(&xas); page; page = xas_next(&xas)) {
+		struct page *head;
+		if (xas_retry(&xas, page))
+			continue;
+		/*
+		 * If the entry has been swapped out, we can stop looking.
+		 * No current caller is looking for DAX entries.
+		 */
+		if (xa_is_value(page))
 			break;
-		}
 
 		head = compound_head(page);
 		if (!page_cache_get_speculative(head))
-			goto repeat;
+			goto retry;
 
 		/* The page was split under us? */
-		if (compound_head(page) != head) {
-			put_page(head);
-			goto repeat;
-		}
+		if (compound_head(page) != head)
+			goto put_page;
 
 		/* Has the page moved? */
-		if (unlikely(page != *slot)) {
-			put_page(head);
-			goto repeat;
-		}
+		if (unlikely(page != xas_reload(&xas)))
+			goto put_page;
 
 		/*
 		 * must check mapping and index after taking the ref.
 		 * otherwise we can get both false positives and false
 		 * negatives, which is just confusing to the caller.
 		 */
-		if (page->mapping == NULL || page_to_pgoff(page) != iter.index) {
+		if (!page->mapping || page_to_pgoff(page) != xas.xa_index) {
 			put_page(page);
 			break;
 		}
@@ -1779,6 +1765,11 @@ repeat:
 		pages[ret] = page;
 		if (++ret == nr_pages)
 			break;
+		continue;
+put_page:
+		put_page(head);
+retry:
+		xas_reset(&xas);
 	}
 	rcu_read_unlock();
 	return ret;
diff --git a/tools/testing/radix-tree/regression3.c b/tools/testing/radix-tree/regression3.c
index ace2543c3eda..9f9a3b280f56 100644
--- a/tools/testing/radix-tree/regression3.c
+++ b/tools/testing/radix-tree/regression3.c
@@ -69,21 +69,6 @@ void regression3_test(void)
 			continue;
 		}
 	}
-	radix_tree_delete(&root, 1);
-
-	first = true;
-	radix_tree_for_each_contig(slot, &root, &iter, 0) {
-		printv(2, "contig %ld %p\n", iter.index, *slot);
-		if (first) {
-			radix_tree_insert(&root, 1, ptr);
-			first = false;
-		}
-		if (radix_tree_deref_retry(*slot)) {
-			printv(2, "retry at %ld\n", iter.index);
-			slot = radix_tree_iter_retry(&iter);
-			continue;
-		}
-	}
 
 	radix_tree_for_each_slot(slot, &root, &iter, 0) {
 		printv(2, "slot %ld %p\n", iter.index, *slot);
@@ -93,14 +78,6 @@ void regression3_test(void)
 		}
 	}
 
-	radix_tree_for_each_contig(slot, &root, &iter, 0) {
-		printv(2, "contig %ld %p\n", iter.index, *slot);
-		if (!iter.index) {
-			printv(2, "next at %ld\n", iter.index);
-			slot = radix_tree_iter_resume(slot, &iter);
-		}
-	}
-
 	radix_tree_tag_set(&root, 0, 0);
 	radix_tree_tag_set(&root, 1, 0);
 	radix_tree_for_each_tagged(slot, &root, &iter, 0, 0) {
-- 
cgit 


From a332125fc3223e1092f765db442b7afb9fd4ecde Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Thu, 17 May 2018 00:13:27 -0400
Subject: radix tree test suite: Convert regression1 to XArray

Now the page cache lookup is using the XArray, let's convert this
regression test from the radix tree API to the XArray so it's testing
roughly the same thing it was testing before.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 tools/testing/radix-tree/regression1.c | 58 +++++++++++-----------------------
 1 file changed, 19 insertions(+), 39 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/radix-tree/regression1.c b/tools/testing/radix-tree/regression1.c
index 0aece092f40e..b4a4a7168986 100644
--- a/tools/testing/radix-tree/regression1.c
+++ b/tools/testing/radix-tree/regression1.c
@@ -53,12 +53,12 @@ struct page {
 	unsigned long index;
 };
 
-static struct page *page_alloc(void)
+static struct page *page_alloc(int index)
 {
 	struct page *p;
 	p = malloc(sizeof(struct page));
 	p->count = 1;
-	p->index = 1;
+	p->index = index;
 	pthread_mutex_init(&p->lock, NULL);
 
 	return p;
@@ -80,53 +80,33 @@ static void page_free(struct page *p)
 static unsigned find_get_pages(unsigned long start,
 			    unsigned int nr_pages, struct page **pages)
 {
-	unsigned int i;
-	unsigned int ret;
-	unsigned int nr_found;
+	XA_STATE(xas, &mt_tree, start);
+	struct page *page;
+	unsigned int ret = 0;
 
 	rcu_read_lock();
-restart:
-	nr_found = radix_tree_gang_lookup_slot(&mt_tree,
-				(void ***)pages, NULL, start, nr_pages);
-	ret = 0;
-	for (i = 0; i < nr_found; i++) {
-		struct page *page;
-repeat:
-		page = radix_tree_deref_slot((void **)pages[i]);
-		if (unlikely(!page))
+	xas_for_each(&xas, page, ULONG_MAX) {
+		if (xas_retry(&xas, page))
 			continue;
 
-		if (radix_tree_exception(page)) {
-			if (radix_tree_deref_retry(page)) {
-				/*
-				 * Transient condition which can only trigger
-				 * when entry at index 0 moves out of or back
-				 * to root: none yet gotten, safe to restart.
-				 */
-				assert((start | i) == 0);
-				goto restart;
-			}
-			/*
-			 * No exceptional entries are inserted in this test.
-			 */
-			assert(0);
-		}
-
 		pthread_mutex_lock(&page->lock);
-		if (!page->count) {
-			pthread_mutex_unlock(&page->lock);
-			goto repeat;
-		}
+		if (!page->count)
+			goto unlock;
+
 		/* don't actually update page refcount */
 		pthread_mutex_unlock(&page->lock);
 
 		/* Has the page moved? */
-		if (unlikely(page != *((void **)pages[i]))) {
-			goto repeat;
-		}
+		if (unlikely(page != xas_reload(&xas)))
+			goto put_page;
 
 		pages[ret] = page;
 		ret++;
+		continue;
+unlock:
+		pthread_mutex_unlock(&page->lock);
+put_page:
+		xas_reset(&xas);
 	}
 	rcu_read_unlock();
 	return ret;
@@ -145,12 +125,12 @@ static void *regression1_fn(void *arg)
 		for (j = 0; j < 1000000; j++) {
 			struct page *p;
 
-			p = page_alloc();
+			p = page_alloc(0);
 			pthread_mutex_lock(&mt_lock);
 			radix_tree_insert(&mt_tree, 0, p);
 			pthread_mutex_unlock(&mt_lock);
 
-			p = page_alloc();
+			p = page_alloc(1);
 			pthread_mutex_lock(&mt_lock);
 			radix_tree_insert(&mt_tree, 1, p);
 			pthread_mutex_unlock(&mt_lock);
-- 
cgit 


From e21a29552fa3f44ea41c53488875015ae70fd7f8 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Wed, 22 Nov 2017 08:36:00 -0500
Subject: shmem: Convert find_swap_entry to XArray

This is a 1:1 conversion.  The major part of this patch is converting
the test framework from userspace to kernel space and mirroring the
algorithm now used in find_swap_entry().

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 lib/test_xarray.c               | 56 +++++++++++++++++++++++++++++++++++++
 mm/shmem.c                      | 27 +++++++-----------
 tools/testing/radix-tree/main.c | 61 -----------------------------------------
 tools/testing/radix-tree/test.c | 22 ---------------
 tools/testing/radix-tree/test.h |  1 -
 5 files changed, 66 insertions(+), 101 deletions(-)

(limited to 'tools/testing')

diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index 128c6489082f..815daffdd8c9 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -631,6 +631,61 @@ static noinline void check_find(struct xarray *xa)
 	check_multi_find_2(xa);
 }
 
+/* See find_swap_entry() in mm/shmem.c */
+static noinline unsigned long xa_find_entry(struct xarray *xa, void *item)
+{
+	XA_STATE(xas, xa, 0);
+	unsigned int checked = 0;
+	void *entry;
+
+	rcu_read_lock();
+	xas_for_each(&xas, entry, ULONG_MAX) {
+		if (xas_retry(&xas, entry))
+			continue;
+		if (entry == item)
+			break;
+		checked++;
+		if ((checked % 4) != 0)
+			continue;
+		xas_pause(&xas);
+	}
+	rcu_read_unlock();
+
+	return entry ? xas.xa_index : -1;
+}
+
+static noinline void check_find_entry(struct xarray *xa)
+{
+#ifdef CONFIG_XARRAY_MULTI
+	unsigned int order;
+	unsigned long offset, index;
+
+	for (order = 0; order < 20; order++) {
+		for (offset = 0; offset < (1UL << (order + 3));
+		     offset += (1UL << order)) {
+			for (index = 0; index < (1UL << (order + 5));
+			     index += (1UL << order)) {
+				xa_store_order(xa, index, order,
+						xa_mk_value(index), GFP_KERNEL);
+				XA_BUG_ON(xa, xa_load(xa, index) !=
+						xa_mk_value(index));
+				XA_BUG_ON(xa, xa_find_entry(xa,
+						xa_mk_value(index)) != index);
+			}
+			XA_BUG_ON(xa, xa_find_entry(xa, xa) != -1);
+			xa_destroy(xa);
+		}
+	}
+#endif
+
+	XA_BUG_ON(xa, xa_find_entry(xa, xa) != -1);
+	xa_store_index(xa, ULONG_MAX, GFP_KERNEL);
+	XA_BUG_ON(xa, xa_find_entry(xa, xa) != -1);
+	XA_BUG_ON(xa, xa_find_entry(xa, xa_mk_value(LONG_MAX)) != -1);
+	xa_erase_index(xa, ULONG_MAX);
+	XA_BUG_ON(xa, !xa_empty(xa));
+}
+
 static noinline void check_move_small(struct xarray *xa, unsigned long idx)
 {
 	XA_STATE(xas, xa, 0);
@@ -972,6 +1027,7 @@ static int xarray_checks(void)
 	check_multi_store(&array);
 	check_xa_alloc();
 	check_find(&array);
+	check_find_entry(&array);
 	check_destroy(&array);
 	check_move(&array);
 	check_create_range(&array);
diff --git a/mm/shmem.c b/mm/shmem.c
index ce91569426f3..a305529d6b89 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1100,34 +1100,27 @@ static void shmem_evict_inode(struct inode *inode)
 	clear_inode(inode);
 }
 
-static unsigned long find_swap_entry(struct radix_tree_root *root, void *item)
+static unsigned long find_swap_entry(struct xarray *xa, void *item)
 {
-	struct radix_tree_iter iter;
-	void __rcu **slot;
-	unsigned long found = -1;
+	XA_STATE(xas, xa, 0);
 	unsigned int checked = 0;
+	void *entry;
 
 	rcu_read_lock();
-	radix_tree_for_each_slot(slot, root, &iter, 0) {
-		void *entry = radix_tree_deref_slot(slot);
-
-		if (radix_tree_deref_retry(entry)) {
-			slot = radix_tree_iter_retry(&iter);
+	xas_for_each(&xas, entry, ULONG_MAX) {
+		if (xas_retry(&xas, entry))
 			continue;
-		}
-		if (entry == item) {
-			found = iter.index;
+		if (entry == item)
 			break;
-		}
 		checked++;
-		if ((checked % 4096) != 0)
+		if ((checked % XA_CHECK_SCHED) != 0)
 			continue;
-		slot = radix_tree_iter_resume(slot, &iter);
+		xas_pause(&xas);
 		cond_resched_rcu();
 	}
-
 	rcu_read_unlock();
-	return found;
+
+	return entry ? xas.xa_index : -1;
 }
 
 /*
diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c
index 09deaf4f0959..79589ea570ab 100644
--- a/tools/testing/radix-tree/main.c
+++ b/tools/testing/radix-tree/main.c
@@ -236,63 +236,6 @@ void copy_tag_check(void)
 	item_kill_tree(&tree);
 }
 
-static void __locate_check(struct radix_tree_root *tree, unsigned long index,
-			unsigned order)
-{
-	struct item *item;
-	unsigned long index2;
-
-	item_insert_order(tree, index, order);
-	item = item_lookup(tree, index);
-	index2 = find_item(tree, item);
-	if (index != index2) {
-		printv(2, "index %ld order %d inserted; found %ld\n",
-			index, order, index2);
-		abort();
-	}
-}
-
-static void __order_0_locate_check(void)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-	int i;
-
-	for (i = 0; i < 50; i++)
-		__locate_check(&tree, rand() % INT_MAX, 0);
-
-	item_kill_tree(&tree);
-}
-
-static void locate_check(void)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-	unsigned order;
-	unsigned long offset, index;
-
-	__order_0_locate_check();
-
-	for (order = 0; order < 20; order++) {
-		for (offset = 0; offset < (1 << (order + 3));
-		     offset += (1UL << order)) {
-			for (index = 0; index < (1UL << (order + 5));
-			     index += (1UL << order)) {
-				__locate_check(&tree, index + offset, order);
-			}
-			if (find_item(&tree, &tree) != -1)
-				abort();
-
-			item_kill_tree(&tree);
-		}
-	}
-
-	if (find_item(&tree, &tree) != -1)
-		abort();
-	__locate_check(&tree, -1, 0);
-	if (find_item(&tree, &tree) != -1)
-		abort();
-	item_kill_tree(&tree);
-}
-
 static void single_thread_tests(bool long_run)
 {
 	int i;
@@ -303,10 +246,6 @@ static void single_thread_tests(bool long_run)
 	rcu_barrier();
 	printv(2, "after multiorder_check: %d allocated, preempt %d\n",
 		nr_allocated, preempt_count);
-	locate_check();
-	rcu_barrier();
-	printv(2, "after locate_check: %d allocated, preempt %d\n",
-		nr_allocated, preempt_count);
 	tag_check();
 	rcu_barrier();
 	printv(2, "after tag_check: %d allocated, preempt %d\n",
diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index 70ddf964d51c..470419bfd49d 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -209,28 +209,6 @@ int tag_tagged_items(struct radix_tree_root *root, pthread_mutex_t *lock,
 	return tagged;
 }
 
-/* Use the same pattern as find_swap_entry() in mm/shmem.c */
-unsigned long find_item(struct radix_tree_root *root, void *item)
-{
-	struct radix_tree_iter iter;
-	void **slot;
-	unsigned long found = -1;
-	unsigned long checked = 0;
-
-	radix_tree_for_each_slot(slot, root, &iter, 0) {
-		if (*slot == item) {
-			found = iter.index;
-			break;
-		}
-		checked++;
-		if ((checked % 4) != 0)
-			continue;
-		slot = radix_tree_iter_resume(slot, &iter);
-	}
-
-	return found;
-}
-
 static int verify_node(struct radix_tree_node *slot, unsigned int tag,
 			int tagged)
 {
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index e3dc7a16f09b..9532c18c6cb1 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -32,7 +32,6 @@ void item_kill_tree(struct radix_tree_root *root);
 int tag_tagged_items(struct radix_tree_root *, pthread_mutex_t *,
 			unsigned long start, unsigned long end, unsigned batch,
 			unsigned iftag, unsigned thentag);
-unsigned long find_item(struct radix_tree_root *, void *item);
 
 void xarray_tests(void);
 void tag_check(void);
-- 
cgit 


From 1cf56f9d670b88b2e947a7ccdb8ba32e6477915d Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Mon, 9 Apr 2018 16:24:45 -0400
Subject: radix tree: Remove radix_tree_update_node_t

The only user of this functionality was the workingset code, and it's
now been converted to the XArray.  Remove __radix_tree_delete_node()
entirely as it was also only used by the workingset code.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 include/linux/radix-tree.h            |  7 +-----
 lib/idr.c                             |  2 +-
 lib/radix-tree.c                      | 42 +++++++----------------------------
 tools/testing/radix-tree/multiorder.c |  2 +-
 4 files changed, 11 insertions(+), 42 deletions(-)

(limited to 'tools/testing')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 8a4280bc350f..7513d0df984b 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -242,17 +242,12 @@ void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index,
 void *radix_tree_lookup(const struct radix_tree_root *, unsigned long);
 void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *,
 					unsigned long index);
-typedef void (*radix_tree_update_node_t)(struct radix_tree_node *);
 void __radix_tree_replace(struct radix_tree_root *, struct radix_tree_node *,
-			  void __rcu **slot, void *entry,
-			  radix_tree_update_node_t update_node);
+			  void __rcu **slot, void *entry);
 void radix_tree_iter_replace(struct radix_tree_root *,
 		const struct radix_tree_iter *, void __rcu **slot, void *entry);
 void radix_tree_replace_slot(struct radix_tree_root *,
 			     void __rcu **slot, void *entry);
-void __radix_tree_delete_node(struct radix_tree_root *,
-			      struct radix_tree_node *,
-			      radix_tree_update_node_t update_node);
 void radix_tree_iter_delete(struct radix_tree_root *,
 			struct radix_tree_iter *iter, void __rcu **slot);
 void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *);
diff --git a/lib/idr.c b/lib/idr.c
index 3c20ad9b0463..cb1db9b8d3f6 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -297,7 +297,7 @@ void *idr_replace(struct idr *idr, void *ptr, unsigned long id)
 	if (!slot || radix_tree_tag_get(&idr->idr_rt, id, IDR_FREE))
 		return ERR_PTR(-ENOENT);
 
-	__radix_tree_replace(&idr->idr_rt, node, slot, ptr, NULL);
+	__radix_tree_replace(&idr->idr_rt, node, slot, ptr);
 
 	return entry;
 }
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 2f9c0e45eeb7..c4c252185734 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -562,8 +562,7 @@ out:
  *	radix_tree_shrink    -    shrink radix tree to minimum height
  *	@root		radix tree root
  */
-static inline bool radix_tree_shrink(struct radix_tree_root *root,
-				     radix_tree_update_node_t update_node)
+static inline bool radix_tree_shrink(struct radix_tree_root *root)
 {
 	bool shrunk = false;
 
@@ -631,8 +630,6 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root,
 		node->count = 0;
 		if (!radix_tree_is_internal_node(child)) {
 			node->slots[0] = (void __rcu *)RADIX_TREE_RETRY;
-			if (update_node)
-				update_node(node);
 		}
 
 		WARN_ON_ONCE(!list_empty(&node->private_list));
@@ -644,8 +641,7 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root,
 }
 
 static bool delete_node(struct radix_tree_root *root,
-			struct radix_tree_node *node,
-			radix_tree_update_node_t update_node)
+			struct radix_tree_node *node)
 {
 	bool deleted = false;
 
@@ -655,7 +651,7 @@ static bool delete_node(struct radix_tree_root *root,
 		if (node->count) {
 			if (node_to_entry(node) ==
 					rcu_dereference_raw(root->xa_head))
-				deleted |= radix_tree_shrink(root, update_node);
+				deleted |= radix_tree_shrink(root);
 			return deleted;
 		}
 
@@ -1059,15 +1055,13 @@ static int calculate_count(struct radix_tree_root *root,
  * @node:		pointer to tree node
  * @slot:		pointer to slot in @node
  * @item:		new item to store in the slot.
- * @update_node:	callback for changing leaf nodes
  *
  * For use with __radix_tree_lookup().  Caller must hold tree write locked
  * across slot lookup and replacement.
  */
 void __radix_tree_replace(struct radix_tree_root *root,
 			  struct radix_tree_node *node,
-			  void __rcu **slot, void *item,
-			  radix_tree_update_node_t update_node)
+			  void __rcu **slot, void *item)
 {
 	void *old = rcu_dereference_raw(*slot);
 	int values = !!xa_is_value(item) - !!xa_is_value(old);
@@ -1085,10 +1079,7 @@ void __radix_tree_replace(struct radix_tree_root *root,
 	if (!node)
 		return;
 
-	if (update_node)
-		update_node(node);
-
-	delete_node(root, node, update_node);
+	delete_node(root, node);
 }
 
 /**
@@ -1110,7 +1101,7 @@ void __radix_tree_replace(struct radix_tree_root *root,
 void radix_tree_replace_slot(struct radix_tree_root *root,
 			     void __rcu **slot, void *item)
 {
-	__radix_tree_replace(root, NULL, slot, item, NULL);
+	__radix_tree_replace(root, NULL, slot, item);
 }
 EXPORT_SYMBOL(radix_tree_replace_slot);
 
@@ -1127,7 +1118,7 @@ void radix_tree_iter_replace(struct radix_tree_root *root,
 				const struct radix_tree_iter *iter,
 				void __rcu **slot, void *item)
 {
-	__radix_tree_replace(root, iter->node, slot, item, NULL);
+	__radix_tree_replace(root, iter->node, slot, item);
 }
 
 #ifdef CONFIG_RADIX_TREE_MULTIORDER
@@ -1807,23 +1798,6 @@ radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *root,
 }
 EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot);
 
-/**
- *	__radix_tree_delete_node    -    try to free node after clearing a slot
- *	@root:		radix tree root
- *	@node:		node containing @index
- *	@update_node:	callback for changing leaf nodes
- *
- *	After clearing the slot at @index in @node from radix tree
- *	rooted at @root, call this function to attempt freeing the
- *	node and shrinking the tree.
- */
-void __radix_tree_delete_node(struct radix_tree_root *root,
-			      struct radix_tree_node *node,
-			      radix_tree_update_node_t update_node)
-{
-	delete_node(root, node, update_node);
-}
-
 static bool __radix_tree_delete(struct radix_tree_root *root,
 				struct radix_tree_node *node, void __rcu **slot)
 {
@@ -1839,7 +1813,7 @@ static bool __radix_tree_delete(struct radix_tree_root *root,
 			node_tag_clear(root, node, tag, offset);
 
 	replace_slot(slot, NULL, node, -1, values);
-	return node && delete_node(root, node, NULL);
+	return node && delete_node(root, node);
 }
 
 /**
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 60786fa55302..0e0ff26c9bcb 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -618,7 +618,7 @@ static void multiorder_account(void)
 	__radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5));
 	__radix_tree_lookup(&tree, 1 << 5, &node, &slot);
 	assert(node->count == node->nr_values * 2);
-	__radix_tree_replace(&tree, node, slot, NULL, NULL);
+	__radix_tree_replace(&tree, node, slot, NULL);
 	assert(node->nr_values == 0);
 
 	item_kill_tree(&tree);
-- 
cgit 


From 2956c6644bfd9aab9f6b21a12e1bd75876d9dd73 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Sat, 19 May 2018 16:47:47 -0400
Subject: radix tree: Remove split/join code

radix_tree_split and radix_tree_join were never used upstream.  Remove
them; if they're needed in future they will be replaced by XArray
equivalents.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 include/linux/radix-tree.h            |   6 -
 lib/radix-tree.c                      | 171 +----------------------
 tools/testing/radix-tree/benchmark.c  |  91 -------------
 tools/testing/radix-tree/multiorder.c | 247 ----------------------------------
 4 files changed, 2 insertions(+), 513 deletions(-)

(limited to 'tools/testing')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 7513d0df984b..44f9abdcb5ab 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -284,12 +284,6 @@ static inline void radix_tree_preload_end(void)
 	preempt_enable();
 }
 
-int radix_tree_split_preload(unsigned old_order, unsigned new_order, gfp_t);
-int radix_tree_split(struct radix_tree_root *, unsigned long index,
-			unsigned new_order);
-int radix_tree_join(struct radix_tree_root *, unsigned long index,
-			unsigned new_order, void *);
-
 void __rcu **idr_get_free(struct radix_tree_root *root,
 			      struct radix_tree_iter *iter, gfp_t gfp,
 			      unsigned long max);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index c4c252185734..c52e0bef5264 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -415,28 +415,6 @@ int radix_tree_maybe_preload(gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(radix_tree_maybe_preload);
 
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-/*
- * Preload with enough objects to ensure that we can split a single entry
- * of order @old_order into many entries of size @new_order
- */
-int radix_tree_split_preload(unsigned int old_order, unsigned int new_order,
-							gfp_t gfp_mask)
-{
-	unsigned top = 1 << (old_order % RADIX_TREE_MAP_SHIFT);
-	unsigned layers = (old_order / RADIX_TREE_MAP_SHIFT) -
-				(new_order / RADIX_TREE_MAP_SHIFT);
-	unsigned nr = 0;
-
-	WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask));
-	BUG_ON(new_order >= old_order);
-
-	while (layers--)
-		nr = nr * RADIX_TREE_MAP_SIZE + 1;
-	return __radix_tree_preload(gfp_mask, top * nr);
-}
-#endif
-
 /*
  * The same as function above, but preload number of nodes required to insert
  * (1 << order) continuous naturally-aligned elements.
@@ -1111,8 +1089,8 @@ EXPORT_SYMBOL(radix_tree_replace_slot);
  * @slot:	pointer to slot
  * @item:	new item to store in the slot.
  *
- * For use with radix_tree_split() and radix_tree_for_each_slot().
- * Caller must hold tree write locked across split and replacement.
+ * For use with radix_tree_for_each_slot().
+ * Caller must hold tree write locked.
  */
 void radix_tree_iter_replace(struct radix_tree_root *root,
 				const struct radix_tree_iter *iter,
@@ -1121,151 +1099,6 @@ void radix_tree_iter_replace(struct radix_tree_root *root,
 	__radix_tree_replace(root, iter->node, slot, item);
 }
 
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-/**
- * radix_tree_join - replace multiple entries with one multiorder entry
- * @root: radix tree root
- * @index: an index inside the new entry
- * @order: order of the new entry
- * @item: new entry
- *
- * Call this function to replace several entries with one larger entry.
- * The existing entries are presumed to not need freeing as a result of
- * this call.
- *
- * The replacement entry will have all the tags set on it that were set
- * on any of the entries it is replacing.
- */
-int radix_tree_join(struct radix_tree_root *root, unsigned long index,
-			unsigned order, void *item)
-{
-	struct radix_tree_node *node;
-	void __rcu **slot;
-	int error;
-
-	BUG_ON(radix_tree_is_internal_node(item));
-
-	error = __radix_tree_create(root, index, order, &node, &slot);
-	if (!error)
-		error = insert_entries(node, slot, item, order, true);
-	if (error > 0)
-		error = 0;
-
-	return error;
-}
-
-/**
- * radix_tree_split - Split an entry into smaller entries
- * @root: radix tree root
- * @index: An index within the large entry
- * @order: Order of new entries
- *
- * Call this function as the first step in replacing a multiorder entry
- * with several entries of lower order.  After this function returns,
- * loop over the relevant portion of the tree using radix_tree_for_each_slot()
- * and call radix_tree_iter_replace() to set up each new entry.
- *
- * The tags from this entry are replicated to all the new entries.
- *
- * The radix tree should be locked against modification during the entire
- * replacement operation.  Lock-free lookups will see RADIX_TREE_RETRY which
- * should prompt RCU walkers to restart the lookup from the root.
- */
-int radix_tree_split(struct radix_tree_root *root, unsigned long index,
-				unsigned order)
-{
-	struct radix_tree_node *parent, *node, *child;
-	void __rcu **slot;
-	unsigned int offset, end;
-	unsigned n, tag, tags = 0;
-	gfp_t gfp = root_gfp_mask(root);
-
-	if (!__radix_tree_lookup(root, index, &parent, &slot))
-		return -ENOENT;
-	if (!parent)
-		return -ENOENT;
-
-	offset = get_slot_offset(parent, slot);
-
-	for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
-		if (tag_get(parent, tag, offset))
-			tags |= 1 << tag;
-
-	for (end = offset + 1; end < RADIX_TREE_MAP_SIZE; end++) {
-		if (!xa_is_sibling(rcu_dereference_raw(parent->slots[end])))
-			break;
-		for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
-			if (tags & (1 << tag))
-				tag_set(parent, tag, end);
-		/* rcu_assign_pointer ensures tags are set before RETRY */
-		rcu_assign_pointer(parent->slots[end], RADIX_TREE_RETRY);
-	}
-	rcu_assign_pointer(parent->slots[offset], RADIX_TREE_RETRY);
-	parent->nr_values -= (end - offset);
-
-	if (order == parent->shift)
-		return 0;
-	if (order > parent->shift) {
-		while (offset < end)
-			offset += insert_entries(parent, &parent->slots[offset],
-					RADIX_TREE_RETRY, order, true);
-		return 0;
-	}
-
-	node = parent;
-
-	for (;;) {
-		if (node->shift > order) {
-			child = radix_tree_node_alloc(gfp, node, root,
-					node->shift - RADIX_TREE_MAP_SHIFT,
-					offset, 0, 0);
-			if (!child)
-				goto nomem;
-			if (node != parent) {
-				node->count++;
-				rcu_assign_pointer(node->slots[offset],
-							node_to_entry(child));
-				for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
-					if (tags & (1 << tag))
-						tag_set(node, tag, offset);
-			}
-
-			node = child;
-			offset = 0;
-			continue;
-		}
-
-		n = insert_entries(node, &node->slots[offset],
-					RADIX_TREE_RETRY, order, false);
-		BUG_ON(n > RADIX_TREE_MAP_SIZE);
-
-		for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
-			if (tags & (1 << tag))
-				tag_set(node, tag, offset);
-		offset += n;
-
-		while (offset == RADIX_TREE_MAP_SIZE) {
-			if (node == parent)
-				break;
-			offset = node->offset;
-			child = node;
-			node = node->parent;
-			rcu_assign_pointer(node->slots[offset],
-						node_to_entry(child));
-			offset++;
-		}
-		if ((node == parent) && (offset == end))
-			return 0;
-	}
-
- nomem:
-	/* Shouldn't happen; did user forget to preload? */
-	/* TODO: free all the allocated nodes */
-	WARN_ON(1);
-	return -ENOMEM;
-}
-#endif
-
 static void node_tag_set(struct radix_tree_root *root,
 				struct radix_tree_node *node,
 				unsigned int tag, unsigned int offset)
diff --git a/tools/testing/radix-tree/benchmark.c b/tools/testing/radix-tree/benchmark.c
index 99c40f3ed133..35741b9c2a4a 100644
--- a/tools/testing/radix-tree/benchmark.c
+++ b/tools/testing/radix-tree/benchmark.c
@@ -146,90 +146,6 @@ static void benchmark_size(unsigned long size, unsigned long step, int order)
 	rcu_barrier();
 }
 
-static long long  __benchmark_split(unsigned long index,
-				    int old_order, int new_order)
-{
-	struct timespec start, finish;
-	long long nsec;
-	RADIX_TREE(tree, GFP_ATOMIC);
-
-	item_insert_order(&tree, index, old_order);
-
-	clock_gettime(CLOCK_MONOTONIC, &start);
-	radix_tree_split(&tree, index, new_order);
-	clock_gettime(CLOCK_MONOTONIC, &finish);
-	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
-	       (finish.tv_nsec - start.tv_nsec);
-
-	item_kill_tree(&tree);
-
-	return nsec;
-
-}
-
-static void benchmark_split(unsigned long size, unsigned long step)
-{
-	int i, j, idx;
-	long long nsec = 0;
-
-
-	for (idx = 0; idx < size; idx += step) {
-		for (i = 3; i < 11; i++) {
-			for (j = 0; j < i; j++) {
-				nsec += __benchmark_split(idx, i, j);
-			}
-		}
-	}
-
-	printv(2, "Size %8ld, step %8ld, split time %10lld ns\n",
-			size, step, nsec);
-
-}
-
-static long long  __benchmark_join(unsigned long index,
-			     unsigned order1, unsigned order2)
-{
-	unsigned long loc;
-	struct timespec start, finish;
-	long long nsec;
-	void *item, *item2 = item_create(index + 1, order1);
-	RADIX_TREE(tree, GFP_KERNEL);
-
-	item_insert_order(&tree, index, order2);
-	item = radix_tree_lookup(&tree, index);
-
-	clock_gettime(CLOCK_MONOTONIC, &start);
-	radix_tree_join(&tree, index + 1, order1, item2);
-	clock_gettime(CLOCK_MONOTONIC, &finish);
-	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
-		(finish.tv_nsec - start.tv_nsec);
-
-	loc = find_item(&tree, item);
-	if (loc == -1)
-		free(item);
-
-	item_kill_tree(&tree);
-
-	return nsec;
-}
-
-static void benchmark_join(unsigned long step)
-{
-	int i, j, idx;
-	long long nsec = 0;
-
-	for (idx = 0; idx < 1 << 10; idx += step) {
-		for (i = 1; i < 15; i++) {
-			for (j = 0; j < i; j++) {
-				nsec += __benchmark_join(idx, i, j);
-			}
-		}
-	}
-
-	printv(2, "Size %8d, step %8ld, join time %10lld ns\n",
-			1 << 10, step, nsec);
-}
-
 void benchmark(void)
 {
 	unsigned long size[] = {1 << 10, 1 << 20, 0};
@@ -247,11 +163,4 @@ void benchmark(void)
 	for (c = 0; size[c]; c++)
 		for (s = 0; step[s]; s++)
 			benchmark_size(size[c], step[s] << 9, 9);
-
-	for (c = 0; size[c]; c++)
-		for (s = 0; step[s]; s++)
-			benchmark_split(size[c], step[s]);
-
-	for (s = 0; step[s]; s++)
-		benchmark_join(step[s]);
 }
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 0e0ff26c9bcb..221e042d1b89 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -356,251 +356,6 @@ void multiorder_tagged_iteration(void)
 	item_kill_tree(&tree);
 }
 
-/*
- * Basic join checks: make sure we can't find an entry in the tree after
- * a larger entry has replaced it
- */
-static void multiorder_join1(unsigned long index,
-				unsigned order1, unsigned order2)
-{
-	unsigned long loc;
-	void *item, *item2 = item_create(index + 1, order1);
-	RADIX_TREE(tree, GFP_KERNEL);
-
-	item_insert_order(&tree, index, order2);
-	item = radix_tree_lookup(&tree, index);
-	radix_tree_join(&tree, index + 1, order1, item2);
-	loc = find_item(&tree, item);
-	if (loc == -1)
-		free(item);
-	item = radix_tree_lookup(&tree, index + 1);
-	assert(item == item2);
-	item_kill_tree(&tree);
-}
-
-/*
- * Check that the accounting of value entries is handled correctly
- * by joining a value entry to a normal pointer.
- */
-static void multiorder_join2(unsigned order1, unsigned order2)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-	struct radix_tree_node *node;
-	void *item1 = item_create(0, order1);
-	void *item2;
-
-	item_insert_order(&tree, 0, order2);
-	radix_tree_insert(&tree, 1 << order2, xa_mk_value(5));
-	item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL);
-	assert(item2 == xa_mk_value(5));
-	assert(node->nr_values == 1);
-
-	item2 = radix_tree_lookup(&tree, 0);
-	free(item2);
-
-	radix_tree_join(&tree, 0, order1, item1);
-	item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL);
-	assert(item2 == item1);
-	assert(node->nr_values == 0);
-	item_kill_tree(&tree);
-}
-
-/*
- * This test revealed an accounting bug for value entries at one point.
- * Nodes were being freed back into the pool with an elevated exception count
- * by radix_tree_join() and then radix_tree_split() was failing to zero the
- * count of value entries.
- */
-static void multiorder_join3(unsigned int order)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-	struct radix_tree_node *node;
-	void **slot;
-	struct radix_tree_iter iter;
-	unsigned long i;
-
-	for (i = 0; i < (1 << order); i++) {
-		radix_tree_insert(&tree, i, xa_mk_value(5));
-	}
-
-	radix_tree_join(&tree, 0, order, xa_mk_value(7));
-	rcu_barrier();
-
-	radix_tree_split(&tree, 0, 0);
-
-	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-		radix_tree_iter_replace(&tree, &iter, slot, xa_mk_value(5));
-	}
-
-	__radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(node->nr_values == node->count);
-
-	item_kill_tree(&tree);
-}
-
-static void multiorder_join(void)
-{
-	int i, j, idx;
-
-	for (idx = 0; idx < 1024; idx = idx * 2 + 3) {
-		for (i = 1; i < 15; i++) {
-			for (j = 0; j < i; j++) {
-				multiorder_join1(idx, i, j);
-			}
-		}
-	}
-
-	for (i = 1; i < 15; i++) {
-		for (j = 0; j < i; j++) {
-			multiorder_join2(i, j);
-		}
-	}
-
-	for (i = 3; i < 10; i++) {
-		multiorder_join3(i);
-	}
-}
-
-static void check_mem(unsigned old_order, unsigned new_order, unsigned alloc)
-{
-	struct radix_tree_preload *rtp = &radix_tree_preloads;
-	if (rtp->nr != 0)
-		printv(2, "split(%u %u) remaining %u\n", old_order, new_order,
-							rtp->nr);
-	/*
-	 * Can't check for equality here as some nodes may have been
-	 * RCU-freed while we ran.  But we should never finish with more
-	 * nodes allocated since they should have all been preloaded.
-	 */
-	if (nr_allocated > alloc)
-		printv(2, "split(%u %u) allocated %u %u\n", old_order, new_order,
-							alloc, nr_allocated);
-}
-
-static void __multiorder_split(int old_order, int new_order)
-{
-	RADIX_TREE(tree, GFP_ATOMIC);
-	void **slot;
-	struct radix_tree_iter iter;
-	unsigned alloc;
-	struct item *item;
-
-	radix_tree_preload(GFP_KERNEL);
-	assert(item_insert_order(&tree, 0, old_order) == 0);
-	radix_tree_preload_end();
-
-	/* Wipe out the preloaded cache or it'll confuse check_mem() */
-	radix_tree_cpu_dead(0);
-
-	item = radix_tree_tag_set(&tree, 0, 2);
-
-	radix_tree_split_preload(old_order, new_order, GFP_KERNEL);
-	alloc = nr_allocated;
-	radix_tree_split(&tree, 0, new_order);
-	check_mem(old_order, new_order, alloc);
-	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-		radix_tree_iter_replace(&tree, &iter, slot,
-					item_create(iter.index, new_order));
-	}
-	radix_tree_preload_end();
-
-	item_kill_tree(&tree);
-	free(item);
-}
-
-static void __multiorder_split2(int old_order, int new_order)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-	void **slot;
-	struct radix_tree_iter iter;
-	struct radix_tree_node *node;
-	void *item;
-
-	__radix_tree_insert(&tree, 0, old_order, xa_mk_value(5));
-
-	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item == xa_mk_value(5));
-	assert(node->nr_values > 0);
-
-	radix_tree_split(&tree, 0, new_order);
-	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-		radix_tree_iter_replace(&tree, &iter, slot,
-					item_create(iter.index, new_order));
-	}
-
-	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item != xa_mk_value(5));
-	assert(node->nr_values == 0);
-
-	item_kill_tree(&tree);
-}
-
-static void __multiorder_split3(int old_order, int new_order)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-	void **slot;
-	struct radix_tree_iter iter;
-	struct radix_tree_node *node;
-	void *item;
-
-	__radix_tree_insert(&tree, 0, old_order, xa_mk_value(5));
-
-	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item == xa_mk_value(5));
-	assert(node->nr_values > 0);
-
-	radix_tree_split(&tree, 0, new_order);
-	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-		radix_tree_iter_replace(&tree, &iter, slot, xa_mk_value(7));
-	}
-
-	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item == xa_mk_value(7));
-	assert(node->nr_values > 0);
-
-	item_kill_tree(&tree);
-
-	__radix_tree_insert(&tree, 0, old_order, xa_mk_value(5));
-
-	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item == xa_mk_value(5));
-	assert(node->nr_values > 0);
-
-	radix_tree_split(&tree, 0, new_order);
-	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-		if (iter.index == (1 << new_order))
-			radix_tree_iter_replace(&tree, &iter, slot,
-						xa_mk_value(7));
-		else
-			radix_tree_iter_replace(&tree, &iter, slot, NULL);
-	}
-
-	item = __radix_tree_lookup(&tree, 1 << new_order, &node, NULL);
-	assert(item == xa_mk_value(7));
-	assert(node->count == node->nr_values);
-	do {
-		node = node->parent;
-		if (!node)
-			break;
-		assert(node->count == 1);
-		assert(node->nr_values == 0);
-	} while (1);
-
-	item_kill_tree(&tree);
-}
-
-static void multiorder_split(void)
-{
-	int i, j;
-
-	for (i = 3; i < 11; i++)
-		for (j = 0; j < i; j++) {
-			__multiorder_split(i, j);
-			__multiorder_split2(i, j);
-			__multiorder_split3(i, j);
-		}
-}
-
 static void multiorder_account(void)
 {
 	RADIX_TREE(tree, GFP_KERNEL);
@@ -702,8 +457,6 @@ void multiorder_checks(void)
 	multiorder_tag_tests();
 	multiorder_iteration();
 	multiorder_tagged_iteration();
-	multiorder_join();
-	multiorder_split();
 	multiorder_account();
 	multiorder_iteration_race();
 
-- 
cgit 


From adb9d9c4ccb1ff0bf1d376e65f36aa5573c75c1a Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Mon, 9 Apr 2018 16:52:21 -0400
Subject: radix tree: Remove radix_tree_clear_tags

The page cache was the only user of this interface and it has now
been converted to the XArray.  Transform the test into a test of
xas_init_marks().

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 include/linux/radix-tree.h           |  2 --
 lib/radix-tree.c                     | 13 ------------
 lib/test_xarray.c                    | 40 ++++++++++++++++++++++++++++++++++++
 tools/testing/radix-tree/tag_check.c | 29 --------------------------
 4 files changed, 40 insertions(+), 44 deletions(-)

(limited to 'tools/testing')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 664d50c5c2ff..7b009af3bb1e 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -252,8 +252,6 @@ void radix_tree_iter_delete(struct radix_tree_root *,
 			struct radix_tree_iter *iter, void __rcu **slot);
 void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *);
 void *radix_tree_delete(struct radix_tree_root *, unsigned long);
-void radix_tree_clear_tags(struct radix_tree_root *, struct radix_tree_node *,
-			   void __rcu **slot);
 unsigned int radix_tree_gang_lookup(const struct radix_tree_root *,
 			void **results, unsigned long first_index,
 			unsigned int max_items);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index b57ddc3dbbbd..e92f2b6ae9c5 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -1670,19 +1670,6 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
 }
 EXPORT_SYMBOL(radix_tree_delete);
 
-void radix_tree_clear_tags(struct radix_tree_root *root,
-			   struct radix_tree_node *node,
-			   void __rcu **slot)
-{
-	if (node) {
-		unsigned int tag, offset = get_slot_offset(node, slot);
-		for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
-			node_tag_clear(root, node, tag, offset);
-	} else {
-		root_tag_clear_all(root);
-	}
-}
-
 /**
  *	radix_tree_tagged - test whether any items in the tree are tagged
  *	@root:		radix tree root
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index 815daffdd8c9..ca86141641cb 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -213,12 +213,52 @@ static noinline void check_xa_mark_1(struct xarray *xa, unsigned long index)
 	XA_BUG_ON(xa, !xa_empty(xa));
 }
 
+static noinline void check_xa_mark_2(struct xarray *xa)
+{
+	XA_STATE(xas, xa, 0);
+	unsigned long index;
+	unsigned int count = 0;
+	void *entry;
+
+	xa_store_index(xa, 0, GFP_KERNEL);
+	xa_set_mark(xa, 0, XA_MARK_0);
+	xas_lock(&xas);
+	xas_load(&xas);
+	xas_init_marks(&xas);
+	xas_unlock(&xas);
+	XA_BUG_ON(xa, !xa_get_mark(xa, 0, XA_MARK_0) == 0);
+
+	for (index = 3500; index < 4500; index++) {
+		xa_store_index(xa, index, GFP_KERNEL);
+		xa_set_mark(xa, index, XA_MARK_0);
+	}
+
+	xas_reset(&xas);
+	rcu_read_lock();
+	xas_for_each_marked(&xas, entry, ULONG_MAX, XA_MARK_0)
+		count++;
+	rcu_read_unlock();
+	XA_BUG_ON(xa, count != 1000);
+
+	xas_lock(&xas);
+	xas_for_each(&xas, entry, ULONG_MAX) {
+		xas_init_marks(&xas);
+		XA_BUG_ON(xa, !xa_get_mark(xa, xas.xa_index, XA_MARK_0));
+		XA_BUG_ON(xa, !xas_get_mark(&xas, XA_MARK_0));
+	}
+	xas_unlock(&xas);
+
+	xa_destroy(xa);
+}
+
 static noinline void check_xa_mark(struct xarray *xa)
 {
 	unsigned long index;
 
 	for (index = 0; index < 16384; index += 4)
 		check_xa_mark_1(xa, index);
+
+	check_xa_mark_2(xa);
 }
 
 static noinline void check_xa_shrink(struct xarray *xa)
diff --git a/tools/testing/radix-tree/tag_check.c b/tools/testing/radix-tree/tag_check.c
index 543181e4847b..56a42f1c5ab0 100644
--- a/tools/testing/radix-tree/tag_check.c
+++ b/tools/testing/radix-tree/tag_check.c
@@ -331,34 +331,6 @@ static void single_check(void)
 	item_kill_tree(&tree);
 }
 
-void radix_tree_clear_tags_test(void)
-{
-	unsigned long index;
-	struct radix_tree_node *node;
-	struct radix_tree_iter iter;
-	void **slot;
-
-	RADIX_TREE(tree, GFP_KERNEL);
-
-	item_insert(&tree, 0);
-	item_tag_set(&tree, 0, 0);
-	__radix_tree_lookup(&tree, 0, &node, &slot);
-	radix_tree_clear_tags(&tree, node, slot);
-	assert(item_tag_get(&tree, 0, 0) == 0);
-
-	for (index = 0; index < 1000; index++) {
-		item_insert(&tree, index);
-		item_tag_set(&tree, index, 0);
-	}
-
-	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-		radix_tree_clear_tags(&tree, iter.node, slot);
-		assert(item_tag_get(&tree, iter.index, 0) == 0);
-	}
-
-	item_kill_tree(&tree);
-}
-
 void tag_check(void)
 {
 	single_check();
@@ -376,5 +348,4 @@ void tag_check(void)
 	thrash_tags();
 	rcu_barrier();
 	printv(2, "after thrash_tags: %d allocated\n", nr_allocated);
-	radix_tree_clear_tags_test();
 }
-- 
cgit 


From 372266ba0267803564824b1c09f1bb7f3f3fc761 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Sat, 18 Aug 2018 07:09:22 -0400
Subject: radix tree test suite: Convert tag_tagged_items to XArray

The tag_tagged_items() function is supposed to test the page-writeback
tagging code.  Since that has been converted to the XArray, there's
not much point in testing the radix tree's tagging code.  This requires
using the pthread mutex embedded in the xarray instead of an external
lock, so remove the pthread mutexes which protect xarrays/radix trees.
Also remove radix_tree_iter_tag_set() as this was the last user.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 include/linux/radix-tree.h                 |  2 --
 lib/radix-tree.c                           | 12 ----------
 tools/testing/radix-tree/iteration_check.c | 16 ++++++-------
 tools/testing/radix-tree/main.c            |  4 ++--
 tools/testing/radix-tree/multiorder.c      | 12 +++++-----
 tools/testing/radix-tree/regression1.c     | 17 +++++++-------
 tools/testing/radix-tree/regression2.c     |  8 +++----
 tools/testing/radix-tree/tag_check.c       |  4 ++--
 tools/testing/radix-tree/test.c            | 37 ++++++++++++------------------
 tools/testing/radix-tree/test.h            |  5 ++--
 10 files changed, 46 insertions(+), 71 deletions(-)

(limited to 'tools/testing')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 7b009af3bb1e..9a1460488163 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -264,8 +264,6 @@ void *radix_tree_tag_clear(struct radix_tree_root *,
 			unsigned long index, unsigned int tag);
 int radix_tree_tag_get(const struct radix_tree_root *,
 			unsigned long index, unsigned int tag);
-void radix_tree_iter_tag_set(struct radix_tree_root *,
-		const struct radix_tree_iter *iter, unsigned int tag);
 void radix_tree_iter_tag_clear(struct radix_tree_root *,
 		const struct radix_tree_iter *iter, unsigned int tag);
 unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *,
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index e92f2b6ae9c5..f107dd2698e3 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -1108,18 +1108,6 @@ void *radix_tree_tag_set(struct radix_tree_root *root,
 }
 EXPORT_SYMBOL(radix_tree_tag_set);
 
-/**
- * radix_tree_iter_tag_set - set a tag on the current iterator entry
- * @root:	radix tree root
- * @iter:	iterator state
- * @tag:	tag to set
- */
-void radix_tree_iter_tag_set(struct radix_tree_root *root,
-			const struct radix_tree_iter *iter, unsigned int tag)
-{
-	node_tag_set(root, iter->node, tag, iter_offset(iter));
-}
-
 static void node_tag_clear(struct radix_tree_root *root,
 				struct radix_tree_node *node,
 				unsigned int tag, unsigned int offset)
diff --git a/tools/testing/radix-tree/iteration_check.c b/tools/testing/radix-tree/iteration_check.c
index a92bab513701..d047327bb9ef 100644
--- a/tools/testing/radix-tree/iteration_check.c
+++ b/tools/testing/radix-tree/iteration_check.c
@@ -18,10 +18,9 @@
 
 #define NUM_THREADS	5
 #define MAX_IDX		100
-#define TAG		0
-#define NEW_TAG		1
+#define TAG		XA_MARK_0
+#define NEW_TAG		XA_MARK_1
 
-static pthread_mutex_t tree_lock = PTHREAD_MUTEX_INITIALIZER;
 static pthread_t threads[NUM_THREADS];
 static unsigned int seeds[3];
 static RADIX_TREE(tree, GFP_KERNEL);
@@ -38,7 +37,7 @@ static void *add_entries_fn(void *arg)
 		int order;
 
 		for (pgoff = 0; pgoff < MAX_IDX; pgoff++) {
-			pthread_mutex_lock(&tree_lock);
+			xa_lock(&tree);
 			for (order = max_order; order >= 0; order--) {
 				if (item_insert_order(&tree, pgoff, order)
 						== 0) {
@@ -46,7 +45,7 @@ static void *add_entries_fn(void *arg)
 					break;
 				}
 			}
-			pthread_mutex_unlock(&tree_lock);
+			xa_unlock(&tree);
 		}
 	}
 
@@ -150,9 +149,9 @@ static void *remove_entries_fn(void *arg)
 
 		pgoff = rand_r(&seeds[2]) % MAX_IDX;
 
-		pthread_mutex_lock(&tree_lock);
+		xa_lock(&tree);
 		item_delete(&tree, pgoff);
-		pthread_mutex_unlock(&tree_lock);
+		xa_unlock(&tree);
 	}
 
 	rcu_unregister_thread();
@@ -165,8 +164,7 @@ static void *tag_entries_fn(void *arg)
 	rcu_register_thread();
 
 	while (!test_complete) {
-		tag_tagged_items(&tree, &tree_lock, 0, MAX_IDX, 10, TAG,
-					NEW_TAG);
+		tag_tagged_items(&tree, 0, MAX_IDX, 10, TAG, NEW_TAG);
 	}
 	rcu_unregister_thread();
 	return NULL;
diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c
index 79589ea570ab..77a44c54998f 100644
--- a/tools/testing/radix-tree/main.c
+++ b/tools/testing/radix-tree/main.c
@@ -214,7 +214,7 @@ void copy_tag_check(void)
 	}
 
 //	printf("\ncopying tags...\n");
-	tagged = tag_tagged_items(&tree, NULL, start, end, ITEMS, 0, 1);
+	tagged = tag_tagged_items(&tree, start, end, ITEMS, XA_MARK_0, XA_MARK_1);
 
 //	printf("checking copied tags\n");
 	assert(tagged == count);
@@ -223,7 +223,7 @@ void copy_tag_check(void)
 	/* Copy tags in several rounds */
 //	printf("\ncopying tags...\n");
 	tmp = rand() % (count / 10 + 2);
-	tagged = tag_tagged_items(&tree, NULL, start, end, tmp, 0, 2);
+	tagged = tag_tagged_items(&tree, start, end, tmp, XA_MARK_0, XA_MARK_2);
 	assert(tagged == count);
 
 //	printf("%lu %lu %lu\n", tagged, tmp, count);
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 221e042d1b89..0436554a099a 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -59,7 +59,7 @@ static void __multiorder_tag_test(int index, int order)
 		assert(!radix_tree_tag_get(&tree, i, 1));
 	}
 
-	assert(tag_tagged_items(&tree, NULL, 0, ~0UL, 10, 0, 1) == 1);
+	assert(tag_tagged_items(&tree, 0, ~0UL, 10, XA_MARK_0, XA_MARK_1) == 1);
 	assert(radix_tree_tag_clear(&tree, index, 0));
 
 	for_each_index(i, base, order) {
@@ -87,7 +87,7 @@ static void __multiorder_tag_test2(unsigned order, unsigned long index2)
 	assert(radix_tree_tag_set(&tree, 0, 0));
 	assert(radix_tree_tag_set(&tree, index2, 0));
 
-	assert(tag_tagged_items(&tree, NULL, 0, ~0UL, 10, 0, 1) == 2);
+	assert(tag_tagged_items(&tree, 0, ~0UL, 10, XA_MARK_0, XA_MARK_1) == 2);
 
 	item_kill_tree(&tree);
 }
@@ -318,8 +318,8 @@ void multiorder_tagged_iteration(void)
 		}
 	}
 
-	assert(tag_tagged_items(&tree, NULL, 0, ~0UL, TAG_ENTRIES, 1, 2) ==
-				TAG_ENTRIES);
+	assert(tag_tagged_items(&tree, 0, ~0UL, TAG_ENTRIES, XA_MARK_1,
+				XA_MARK_2) == TAG_ENTRIES);
 
 	for (j = 0; j < 256; j++) {
 		int mask, k;
@@ -345,8 +345,8 @@ void multiorder_tagged_iteration(void)
 		}
 	}
 
-	assert(tag_tagged_items(&tree, NULL, 1, ~0UL, MT_NUM_ENTRIES * 2, 1, 0)
-			== TAG_ENTRIES);
+	assert(tag_tagged_items(&tree, 1, ~0UL, MT_NUM_ENTRIES * 2, XA_MARK_1,
+				XA_MARK_0) == TAG_ENTRIES);
 	i = 0;
 	radix_tree_for_each_tagged(slot, &tree, &iter, 0, 0) {
 		assert(iter.index == tag_index[i]);
diff --git a/tools/testing/radix-tree/regression1.c b/tools/testing/radix-tree/regression1.c
index b4a4a7168986..a61c7bcbc72d 100644
--- a/tools/testing/radix-tree/regression1.c
+++ b/tools/testing/radix-tree/regression1.c
@@ -44,7 +44,6 @@
 #include "regression.h"
 
 static RADIX_TREE(mt_tree, GFP_KERNEL);
-static pthread_mutex_t mt_lock = PTHREAD_MUTEX_INITIALIZER;
 
 struct page {
 	pthread_mutex_t lock;
@@ -126,29 +125,29 @@ static void *regression1_fn(void *arg)
 			struct page *p;
 
 			p = page_alloc(0);
-			pthread_mutex_lock(&mt_lock);
+			xa_lock(&mt_tree);
 			radix_tree_insert(&mt_tree, 0, p);
-			pthread_mutex_unlock(&mt_lock);
+			xa_unlock(&mt_tree);
 
 			p = page_alloc(1);
-			pthread_mutex_lock(&mt_lock);
+			xa_lock(&mt_tree);
 			radix_tree_insert(&mt_tree, 1, p);
-			pthread_mutex_unlock(&mt_lock);
+			xa_unlock(&mt_tree);
 
-			pthread_mutex_lock(&mt_lock);
+			xa_lock(&mt_tree);
 			p = radix_tree_delete(&mt_tree, 1);
 			pthread_mutex_lock(&p->lock);
 			p->count--;
 			pthread_mutex_unlock(&p->lock);
-			pthread_mutex_unlock(&mt_lock);
+			xa_unlock(&mt_tree);
 			page_free(p);
 
-			pthread_mutex_lock(&mt_lock);
+			xa_lock(&mt_tree);
 			p = radix_tree_delete(&mt_tree, 0);
 			pthread_mutex_lock(&p->lock);
 			p->count--;
 			pthread_mutex_unlock(&p->lock);
-			pthread_mutex_unlock(&mt_lock);
+			xa_unlock(&mt_tree);
 			page_free(p);
 		}
 	} else {
diff --git a/tools/testing/radix-tree/regression2.c b/tools/testing/radix-tree/regression2.c
index 424b91c77831..f2c7e640a919 100644
--- a/tools/testing/radix-tree/regression2.c
+++ b/tools/testing/radix-tree/regression2.c
@@ -53,9 +53,9 @@
 #include "regression.h"
 #include "test.h"
 
-#define PAGECACHE_TAG_DIRTY     0
-#define PAGECACHE_TAG_WRITEBACK 1
-#define PAGECACHE_TAG_TOWRITE   2
+#define PAGECACHE_TAG_DIRTY     XA_MARK_0
+#define PAGECACHE_TAG_WRITEBACK XA_MARK_1
+#define PAGECACHE_TAG_TOWRITE   XA_MARK_2
 
 static RADIX_TREE(mt_tree, GFP_KERNEL);
 unsigned long page_count = 0;
@@ -92,7 +92,7 @@ void regression2_test(void)
 	/* 1. */
 	start = 0;
 	end = max_slots - 2;
-	tag_tagged_items(&mt_tree, NULL, start, end, 1,
+	tag_tagged_items(&mt_tree, start, end, 1,
 				PAGECACHE_TAG_DIRTY, PAGECACHE_TAG_TOWRITE);
 
 	/* 2. */
diff --git a/tools/testing/radix-tree/tag_check.c b/tools/testing/radix-tree/tag_check.c
index 56a42f1c5ab0..f898957b1a19 100644
--- a/tools/testing/radix-tree/tag_check.c
+++ b/tools/testing/radix-tree/tag_check.c
@@ -24,7 +24,7 @@ __simple_checks(struct radix_tree_root *tree, unsigned long index, int tag)
 	item_tag_set(tree, index, tag);
 	ret = item_tag_get(tree, index, tag);
 	assert(ret != 0);
-	ret = tag_tagged_items(tree, NULL, first, ~0UL, 10, tag, !tag);
+	ret = tag_tagged_items(tree, first, ~0UL, 10, tag, !tag);
 	assert(ret == 1);
 	ret = item_tag_get(tree, index, !tag);
 	assert(ret != 0);
@@ -321,7 +321,7 @@ static void single_check(void)
 	assert(ret == 0);
 	verify_tag_consistency(&tree, 0);
 	verify_tag_consistency(&tree, 1);
-	ret = tag_tagged_items(&tree, NULL, first, 10, 10, 0, 1);
+	ret = tag_tagged_items(&tree, first, 10, 10, XA_MARK_0, XA_MARK_1);
 	assert(ret == 1);
 	ret = radix_tree_gang_lookup_tag(&tree, (void **)items, 0, BATCH, 1);
 	assert(ret == 1);
diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index 470419bfd49d..d70adcd03d35 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -176,35 +176,28 @@ void item_full_scan(struct radix_tree_root *root, unsigned long start,
 }
 
 /* Use the same pattern as tag_pages_for_writeback() in mm/page-writeback.c */
-int tag_tagged_items(struct radix_tree_root *root, pthread_mutex_t *lock,
-			unsigned long start, unsigned long end, unsigned batch,
-			unsigned iftag, unsigned thentag)
+int tag_tagged_items(struct xarray *xa, unsigned long start, unsigned long end,
+		unsigned batch, xa_mark_t iftag, xa_mark_t thentag)
 {
-	unsigned long tagged = 0;
-	struct radix_tree_iter iter;
-	void **slot;
+	XA_STATE(xas, xa, start);
+	unsigned int tagged = 0;
+	struct item *item;
 
 	if (batch == 0)
 		batch = 1;
 
-	if (lock)
-		pthread_mutex_lock(lock);
-	radix_tree_for_each_tagged(slot, root, &iter, start, iftag) {
-		if (iter.index > end)
-			break;
-		radix_tree_iter_tag_set(root, &iter, thentag);
-		tagged++;
-		if ((tagged % batch) != 0)
+	xas_lock_irq(&xas);
+	xas_for_each_marked(&xas, item, end, iftag) {
+		xas_set_mark(&xas, thentag);
+		if (++tagged % batch)
 			continue;
-		slot = radix_tree_iter_resume(slot, &iter);
-		if (lock) {
-			pthread_mutex_unlock(lock);
-			rcu_barrier();
-			pthread_mutex_lock(lock);
-		}
+
+		xas_pause(&xas);
+		xas_unlock_irq(&xas);
+		rcu_barrier();
+		xas_lock_irq(&xas);
 	}
-	if (lock)
-		pthread_mutex_unlock(lock);
+	xas_unlock_irq(&xas);
 
 	return tagged;
 }
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index 9532c18c6cb1..100e9a456f91 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -29,9 +29,8 @@ void item_full_scan(struct radix_tree_root *root, unsigned long start,
 			unsigned long nr, int chunk);
 void item_kill_tree(struct radix_tree_root *root);
 
-int tag_tagged_items(struct radix_tree_root *, pthread_mutex_t *,
-			unsigned long start, unsigned long end, unsigned batch,
-			unsigned iftag, unsigned thentag);
+int tag_tagged_items(struct xarray *, unsigned long start, unsigned long end,
+		unsigned batch, xa_mark_t iftag, xa_mark_t thentag);
 
 void xarray_tests(void);
 void tag_check(void);
-- 
cgit 


From 47e0fab2b15155e33fdff777c791bebfd5855bbc Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Mon, 20 Aug 2018 15:48:46 -0400
Subject: radix tree test suite: Convert iteration test to XArray

With no code left in the kernel using the multiorder radix tree, convert
the iteration test from the radix tree to the XArray.  It's unlikely to
suffer the same bug as the radix tree, but this test will prevent that
bug from ever creeping into the XArray implementation.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 tools/testing/radix-tree/iteration_check.c | 103 ++++++++++++++---------------
 tools/testing/radix-tree/test.c            |  17 +++--
 tools/testing/radix-tree/test.h            |   1 +
 3 files changed, 63 insertions(+), 58 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/radix-tree/iteration_check.c b/tools/testing/radix-tree/iteration_check.c
index d047327bb9ef..238db187aa15 100644
--- a/tools/testing/radix-tree/iteration_check.c
+++ b/tools/testing/radix-tree/iteration_check.c
@@ -1,5 +1,5 @@
 /*
- * iteration_check.c: test races having to do with radix tree iteration
+ * iteration_check.c: test races having to do with xarray iteration
  * Copyright (c) 2016 Intel Corporation
  * Author: Ross Zwisler <ross.zwisler@linux.intel.com>
  *
@@ -12,7 +12,6 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  */
-#include <linux/radix-tree.h>
 #include <pthread.h>
 #include "test.h"
 
@@ -23,29 +22,44 @@
 
 static pthread_t threads[NUM_THREADS];
 static unsigned int seeds[3];
-static RADIX_TREE(tree, GFP_KERNEL);
+static DEFINE_XARRAY(array);
 static bool test_complete;
 static int max_order;
 
-/* relentlessly fill the tree with tagged entries */
+void my_item_insert(struct xarray *xa, unsigned long index)
+{
+	XA_STATE(xas, xa, index);
+	struct item *item = item_create(index, 0);
+	int order;
+
+retry:
+	xas_lock(&xas);
+	for (order = max_order; order >= 0; order--) {
+		xas_set_order(&xas, index, order);
+		item->order = order;
+		if (xas_find_conflict(&xas))
+			continue;
+		xas_store(&xas, item);
+		xas_set_mark(&xas, TAG);
+		break;
+	}
+	xas_unlock(&xas);
+	if (xas_nomem(&xas, GFP_KERNEL))
+		goto retry;
+	if (order < 0)
+		free(item);
+}
+
+/* relentlessly fill the array with tagged entries */
 static void *add_entries_fn(void *arg)
 {
 	rcu_register_thread();
 
 	while (!test_complete) {
 		unsigned long pgoff;
-		int order;
 
 		for (pgoff = 0; pgoff < MAX_IDX; pgoff++) {
-			xa_lock(&tree);
-			for (order = max_order; order >= 0; order--) {
-				if (item_insert_order(&tree, pgoff, order)
-						== 0) {
-					item_tag_set(&tree, pgoff, TAG);
-					break;
-				}
-			}
-			xa_unlock(&tree);
+			my_item_insert(&array, pgoff);
 		}
 	}
 
@@ -55,33 +69,25 @@ static void *add_entries_fn(void *arg)
 }
 
 /*
- * Iterate over the tagged entries, doing a radix_tree_iter_retry() as we find
- * things that have been removed and randomly resetting our iteration to the
- * next chunk with radix_tree_iter_resume().  Both radix_tree_iter_retry() and
- * radix_tree_iter_resume() cause radix_tree_next_slot() to be called with a
- * NULL 'slot' variable.
+ * Iterate over tagged entries, retrying when we find ourselves in a deleted
+ * node and randomly pausing the iteration.
  */
 static void *tagged_iteration_fn(void *arg)
 {
-	struct radix_tree_iter iter;
-	void **slot;
+	XA_STATE(xas, &array, 0);
+	void *entry;
 
 	rcu_register_thread();
 
 	while (!test_complete) {
+		xas_set(&xas, 0);
 		rcu_read_lock();
-		radix_tree_for_each_tagged(slot, &tree, &iter, 0, TAG) {
-			void *entry = radix_tree_deref_slot(slot);
-			if (unlikely(!entry))
+		xas_for_each_marked(&xas, entry, ULONG_MAX, TAG) {
+			if (xas_retry(&xas, entry))
 				continue;
 
-			if (radix_tree_deref_retry(entry)) {
-				slot = radix_tree_iter_retry(&iter);
-				continue;
-			}
-
 			if (rand_r(&seeds[0]) % 50 == 0) {
-				slot = radix_tree_iter_resume(slot, &iter);
+				xas_pause(&xas);
 				rcu_read_unlock();
 				rcu_barrier();
 				rcu_read_lock();
@@ -96,33 +102,25 @@ static void *tagged_iteration_fn(void *arg)
 }
 
 /*
- * Iterate over the entries, doing a radix_tree_iter_retry() as we find things
- * that have been removed and randomly resetting our iteration to the next
- * chunk with radix_tree_iter_resume().  Both radix_tree_iter_retry() and
- * radix_tree_iter_resume() cause radix_tree_next_slot() to be called with a
- * NULL 'slot' variable.
+ * Iterate over the entries, retrying when we find ourselves in a deleted
+ * node and randomly pausing the iteration.
  */
 static void *untagged_iteration_fn(void *arg)
 {
-	struct radix_tree_iter iter;
-	void **slot;
+	XA_STATE(xas, &array, 0);
+	void *entry;
 
 	rcu_register_thread();
 
 	while (!test_complete) {
+		xas_set(&xas, 0);
 		rcu_read_lock();
-		radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-			void *entry = radix_tree_deref_slot(slot);
-			if (unlikely(!entry))
+		xas_for_each(&xas, entry, ULONG_MAX) {
+			if (xas_retry(&xas, entry))
 				continue;
 
-			if (radix_tree_deref_retry(entry)) {
-				slot = radix_tree_iter_retry(&iter);
-				continue;
-			}
-
 			if (rand_r(&seeds[1]) % 50 == 0) {
-				slot = radix_tree_iter_resume(slot, &iter);
+				xas_pause(&xas);
 				rcu_read_unlock();
 				rcu_barrier();
 				rcu_read_lock();
@@ -137,7 +135,7 @@ static void *untagged_iteration_fn(void *arg)
 }
 
 /*
- * Randomly remove entries to help induce radix_tree_iter_retry() calls in the
+ * Randomly remove entries to help induce retries in the
  * two iteration functions.
  */
 static void *remove_entries_fn(void *arg)
@@ -146,12 +144,13 @@ static void *remove_entries_fn(void *arg)
 
 	while (!test_complete) {
 		int pgoff;
+		struct item *item;
 
 		pgoff = rand_r(&seeds[2]) % MAX_IDX;
 
-		xa_lock(&tree);
-		item_delete(&tree, pgoff);
-		xa_unlock(&tree);
+		item = xa_erase(&array, pgoff);
+		if (item)
+			item_free(item, pgoff);
 	}
 
 	rcu_unregister_thread();
@@ -164,7 +163,7 @@ static void *tag_entries_fn(void *arg)
 	rcu_register_thread();
 
 	while (!test_complete) {
-		tag_tagged_items(&tree, 0, MAX_IDX, 10, TAG, NEW_TAG);
+		tag_tagged_items(&array, 0, MAX_IDX, 10, TAG, NEW_TAG);
 	}
 	rcu_unregister_thread();
 	return NULL;
@@ -215,5 +214,5 @@ void iteration_test(unsigned order, unsigned test_duration)
 		}
 	}
 
-	item_kill_tree(&tree);
+	item_kill_tree(&array);
 }
diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index d70adcd03d35..32973dd51ec5 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -63,16 +63,21 @@ void item_sanity(struct item *item, unsigned long index)
 	assert((item->index | mask) == (index | mask));
 }
 
+void item_free(struct item *item, unsigned long index)
+{
+	item_sanity(item, index);
+	free(item);
+}
+
 int item_delete(struct radix_tree_root *root, unsigned long index)
 {
 	struct item *item = radix_tree_delete(root, index);
 
-	if (item) {
-		item_sanity(item, index);
-		free(item);
-		return 1;
-	}
-	return 0;
+	if (!item)
+		return 0;
+
+	item_free(item, index);
+	return 1;
 }
 
 static void item_free_rcu(struct rcu_head *head)
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index 100e9a456f91..a2f53c889a31 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -14,6 +14,7 @@ struct item *item_create(unsigned long index, unsigned int order);
 int __item_insert(struct radix_tree_root *root, struct item *item);
 int item_insert(struct radix_tree_root *root, unsigned long index);
 void item_sanity(struct item *item, unsigned long index);
+void item_free(struct item *item, unsigned long index);
 int item_insert_order(struct radix_tree_root *root, unsigned long index,
 			unsigned order);
 int item_delete(struct radix_tree_root *root, unsigned long index);
-- 
cgit 


From d6427f8179b5dd65eb468c61fc8cc24657c336c9 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Tue, 28 Aug 2018 16:13:16 -0400
Subject: xarray: Move multiorder account test in-kernel

Move this test to the in-kernel test suite, and enhance it to test
several different orders.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 lib/test_xarray.c                     | 32 ++++++++++++++++++++++++++++++++
 tools/testing/radix-tree/multiorder.c | 24 ------------------------
 2 files changed, 32 insertions(+), 24 deletions(-)

(limited to 'tools/testing')

diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index ca86141641cb..38cab4ccb24e 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -1019,6 +1019,37 @@ static noinline void check_workingset(struct xarray *xa, unsigned long index)
 	XA_BUG_ON(xa, !xa_empty(xa));
 }
 
+/*
+ * Check that the pointer / value / sibling entries are accounted the
+ * way we expect them to be.
+ */
+static noinline void check_account(struct xarray *xa)
+{
+#ifdef CONFIG_XARRAY_MULTI
+	unsigned int order;
+
+	for (order = 1; order < 12; order++) {
+		XA_STATE(xas, xa, 1 << order);
+
+		xa_store_order(xa, 0, order, xa, GFP_KERNEL);
+		xas_load(&xas);
+		XA_BUG_ON(xa, xas.xa_node->count == 0);
+		XA_BUG_ON(xa, xas.xa_node->count > (1 << order));
+		XA_BUG_ON(xa, xas.xa_node->nr_values != 0);
+
+		xa_store_order(xa, 1 << order, order, xa_mk_value(1 << order),
+				GFP_KERNEL);
+		XA_BUG_ON(xa, xas.xa_node->count != xas.xa_node->nr_values * 2);
+
+		xa_erase(xa, 1 << order);
+		XA_BUG_ON(xa, xas.xa_node->nr_values != 0);
+
+		xa_erase(xa, 0);
+		XA_BUG_ON(xa, !xa_empty(xa));
+	}
+#endif
+}
+
 static noinline void check_destroy(struct xarray *xa)
 {
 	unsigned long index;
@@ -1068,6 +1099,7 @@ static int xarray_checks(void)
 	check_xa_alloc();
 	check_find(&array);
 	check_find_entry(&array);
+	check_account(&array);
 	check_destroy(&array);
 	check_move(&array);
 	check_create_range(&array);
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 0436554a099a..dc27a3da210a 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -356,29 +356,6 @@ void multiorder_tagged_iteration(void)
 	item_kill_tree(&tree);
 }
 
-static void multiorder_account(void)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-	struct radix_tree_node *node;
-	void **slot;
-
-	item_insert_order(&tree, 0, 5);
-
-	__radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5));
-	__radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(node->count == node->nr_values * 2);
-	radix_tree_delete(&tree, 1 << 5);
-	assert(node->nr_values == 0);
-
-	__radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5));
-	__radix_tree_lookup(&tree, 1 << 5, &node, &slot);
-	assert(node->count == node->nr_values * 2);
-	__radix_tree_replace(&tree, node, slot, NULL);
-	assert(node->nr_values == 0);
-
-	item_kill_tree(&tree);
-}
-
 bool stop_iteration = false;
 
 static void *creator_func(void *ptr)
@@ -457,7 +434,6 @@ void multiorder_checks(void)
 	multiorder_tag_tests();
 	multiorder_iteration();
 	multiorder_tagged_iteration();
-	multiorder_account();
 	multiorder_iteration_race();
 
 	radix_tree_cpu_dead(0);
-- 
cgit 


From 93eb07f72c8d86f8fe5e90907df1cc037f6ffbb7 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Sat, 8 Sep 2018 12:09:52 -0400
Subject: xarray: Move multiorder_shrink to kernel tests

Test this functionality inside the kernel as well as in userspace.
Also remove insert_bug() as there's no comparable thing to test
in the XArray code.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 lib/test_xarray.c                     |  37 ++++++++
 tools/testing/radix-tree/multiorder.c | 173 ----------------------------------
 2 files changed, 37 insertions(+), 173 deletions(-)

(limited to 'tools/testing')

diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index 38cab4ccb24e..ff94b54a926d 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -199,9 +199,25 @@ static noinline void check_xa_mark_1(struct xarray *xa, unsigned long index)
 		xa_store_order(xa, index, order, xa_mk_value(index),
 				GFP_KERNEL);
 		for (i = base; i < next; i++) {
+			XA_STATE(xas, xa, i);
+			unsigned int seen = 0;
+			void *entry;
+
 			XA_BUG_ON(xa, !xa_get_mark(xa, i, XA_MARK_0));
 			XA_BUG_ON(xa, !xa_get_mark(xa, i, XA_MARK_1));
 			XA_BUG_ON(xa, xa_get_mark(xa, i, XA_MARK_2));
+
+			/* We should see two elements in the array */
+			xas_for_each(&xas, entry, ULONG_MAX)
+				seen++;
+			XA_BUG_ON(xa, seen != 2);
+
+			/* One of which is marked */
+			xas_set(&xas, 0);
+			seen = 0;
+			xas_for_each_marked(&xas, entry, ULONG_MAX, XA_MARK_0)
+				seen++;
+			XA_BUG_ON(xa, seen != 1);
 		}
 		XA_BUG_ON(xa, xa_get_mark(xa, next, XA_MARK_0));
 		XA_BUG_ON(xa, xa_get_mark(xa, next, XA_MARK_1));
@@ -265,6 +281,8 @@ static noinline void check_xa_shrink(struct xarray *xa)
 {
 	XA_STATE(xas, xa, 1);
 	struct xa_node *node;
+	unsigned int order;
+	unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 15 : 1;
 
 	XA_BUG_ON(xa, !xa_empty(xa));
 	XA_BUG_ON(xa, xa_store_index(xa, 0, GFP_KERNEL) != NULL);
@@ -287,6 +305,25 @@ static noinline void check_xa_shrink(struct xarray *xa)
 	XA_BUG_ON(xa, xa_load(xa, 0) != xa_mk_value(0));
 	xa_erase_index(xa, 0);
 	XA_BUG_ON(xa, !xa_empty(xa));
+
+	for (order = 0; order < max_order; order++) {
+		unsigned long max = (1UL << order) - 1;
+		xa_store_order(xa, 0, order, xa_mk_value(0), GFP_KERNEL);
+		XA_BUG_ON(xa, xa_load(xa, max) != xa_mk_value(0));
+		XA_BUG_ON(xa, xa_load(xa, max + 1) != NULL);
+		rcu_read_lock();
+		node = xa_head(xa);
+		rcu_read_unlock();
+		XA_BUG_ON(xa, xa_store_index(xa, ULONG_MAX, GFP_KERNEL) !=
+				NULL);
+		rcu_read_lock();
+		XA_BUG_ON(xa, xa_head(xa) == node);
+		rcu_read_unlock();
+		XA_BUG_ON(xa, xa_load(xa, max + 1) != NULL);
+		xa_erase_index(xa, ULONG_MAX);
+		XA_BUG_ON(xa, xa->xa_head != node);
+		xa_erase_index(xa, 0);
+	}
 }
 
 static noinline void check_cmpxchg(struct xarray *xa)
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index dc27a3da210a..a60c03287e9c 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -20,127 +20,6 @@
 
 #include "test.h"
 
-#define for_each_index(i, base, order) \
-	for (i = base; i < base + (1 << order); i++)
-
-static void __multiorder_tag_test(int index, int order)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-	int base, err, i;
-
-	/* our canonical entry */
-	base = index & ~((1 << order) - 1);
-
-	printv(2, "Multiorder tag test with index %d, canonical entry %d\n",
-			index, base);
-
-	err = item_insert_order(&tree, index, order);
-	assert(!err);
-
-	/*
-	 * Verify we get collisions for covered indices.  We try and fail to
-	 * insert a value entry so we don't leak memory via
-	 * item_insert_order().
-	 */
-	for_each_index(i, base, order) {
-		err = __radix_tree_insert(&tree, i, order, xa_mk_value(0xA0));
-		assert(err == -EEXIST);
-	}
-
-	for_each_index(i, base, order) {
-		assert(!radix_tree_tag_get(&tree, i, 0));
-		assert(!radix_tree_tag_get(&tree, i, 1));
-	}
-
-	assert(radix_tree_tag_set(&tree, index, 0));
-
-	for_each_index(i, base, order) {
-		assert(radix_tree_tag_get(&tree, i, 0));
-		assert(!radix_tree_tag_get(&tree, i, 1));
-	}
-
-	assert(tag_tagged_items(&tree, 0, ~0UL, 10, XA_MARK_0, XA_MARK_1) == 1);
-	assert(radix_tree_tag_clear(&tree, index, 0));
-
-	for_each_index(i, base, order) {
-		assert(!radix_tree_tag_get(&tree, i, 0));
-		assert(radix_tree_tag_get(&tree, i, 1));
-	}
-
-	assert(radix_tree_tag_clear(&tree, index, 1));
-
-	assert(!radix_tree_tagged(&tree, 0));
-	assert(!radix_tree_tagged(&tree, 1));
-
-	item_kill_tree(&tree);
-}
-
-static void __multiorder_tag_test2(unsigned order, unsigned long index2)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-	unsigned long index = (1 << order);
-	index2 += index;
-
-	assert(item_insert_order(&tree, 0, order) == 0);
-	assert(item_insert(&tree, index2) == 0);
-
-	assert(radix_tree_tag_set(&tree, 0, 0));
-	assert(radix_tree_tag_set(&tree, index2, 0));
-
-	assert(tag_tagged_items(&tree, 0, ~0UL, 10, XA_MARK_0, XA_MARK_1) == 2);
-
-	item_kill_tree(&tree);
-}
-
-static void multiorder_tag_tests(void)
-{
-	int i, j;
-
-	/* test multi-order entry for indices 0-7 with no sibling pointers */
-	__multiorder_tag_test(0, 3);
-	__multiorder_tag_test(5, 3);
-
-	/* test multi-order entry for indices 8-15 with no sibling pointers */
-	__multiorder_tag_test(8, 3);
-	__multiorder_tag_test(15, 3);
-
-	/*
-	 * Our order 5 entry covers indices 0-31 in a tree with height=2.
-	 * This is broken up as follows:
-	 * 0-7:		canonical entry
-	 * 8-15:	sibling 1
-	 * 16-23:	sibling 2
-	 * 24-31:	sibling 3
-	 */
-	__multiorder_tag_test(0, 5);
-	__multiorder_tag_test(29, 5);
-
-	/* same test, but with indices 32-63 */
-	__multiorder_tag_test(32, 5);
-	__multiorder_tag_test(44, 5);
-
-	/*
-	 * Our order 8 entry covers indices 0-255 in a tree with height=3.
-	 * This is broken up as follows:
-	 * 0-63:	canonical entry
-	 * 64-127:	sibling 1
-	 * 128-191:	sibling 2
-	 * 192-255:	sibling 3
-	 */
-	__multiorder_tag_test(0, 8);
-	__multiorder_tag_test(190, 8);
-
-	/* same test, but with indices 256-511 */
-	__multiorder_tag_test(256, 8);
-	__multiorder_tag_test(300, 8);
-
-	__multiorder_tag_test(0x12345678UL, 8);
-
-	for (i = 1; i < 10; i++)
-		for (j = 0; j < (10 << i); j++)
-			__multiorder_tag_test2(i, j);
-}
-
 static void multiorder_check(unsigned long index, int order)
 {
 	unsigned long i;
@@ -181,53 +60,6 @@ static void multiorder_check(unsigned long index, int order)
 		item_check_absent(&tree, i);
 }
 
-static void multiorder_shrink(unsigned long index, int order)
-{
-	unsigned long i;
-	unsigned long max = 1 << order;
-	RADIX_TREE(tree, GFP_KERNEL);
-	struct radix_tree_node *node;
-
-	printv(2, "Multiorder shrink index %ld, order %d\n", index, order);
-
-	assert(item_insert_order(&tree, 0, order) == 0);
-
-	node = tree.xa_head;
-
-	assert(item_insert(&tree, index) == 0);
-	assert(node != tree.xa_head);
-
-	assert(item_delete(&tree, index) != 0);
-	assert(node == tree.xa_head);
-
-	for (i = 0; i < max; i++) {
-		struct item *item = item_lookup(&tree, i);
-		assert(item != 0);
-		assert(item->index == 0);
-	}
-	for (i = max; i < 2*max; i++)
-		item_check_absent(&tree, i);
-
-	if (!item_delete(&tree, 0)) {
-		printv(2, "failed to delete index %ld (order %d)\n", index, order);
-		abort();
-	}
-
-	for (i = 0; i < 2*max; i++)
-		item_check_absent(&tree, i);
-}
-
-static void multiorder_insert_bug(void)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-
-	item_insert(&tree, 0);
-	radix_tree_tag_set(&tree, 0, 0);
-	item_insert_order(&tree, 3 << 6, 6);
-
-	item_kill_tree(&tree);
-}
-
 void multiorder_iteration(void)
 {
 	RADIX_TREE(tree, GFP_KERNEL);
@@ -427,11 +259,6 @@ void multiorder_checks(void)
 		multiorder_check((1UL << i) + 1, i);
 	}
 
-	for (i = 0; i < 15; i++)
-		multiorder_shrink((1UL << (i + RADIX_TREE_MAP_SHIFT)), i);
-
-	multiorder_insert_bug();
-	multiorder_tag_tests();
 	multiorder_iteration();
 	multiorder_tagged_iteration();
 	multiorder_iteration_race();
-- 
cgit 


From 4f06d6302da682157890f72c0573e12a73536814 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Sun, 9 Sep 2018 01:52:17 -0400
Subject: xarray: Move multiorder_check to in-kernel tests

This version is a little less thorough in order to be a little quicker,
but tests the important edge cases.  Also test adding a multiorder entry
at a non-canonical index, and erasing it.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 lib/test_xarray.c                     | 44 ++++++++++++++++++++++++++++++++
 tools/testing/radix-tree/multiorder.c | 48 -----------------------------------
 2 files changed, 44 insertions(+), 48 deletions(-)

(limited to 'tools/testing')

diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index ff94b54a926d..0f06a93b4d0e 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -422,6 +422,43 @@ static noinline void check_xas_erase(struct xarray *xa)
 	}
 }
 
+#ifdef CONFIG_XARRAY_MULTI
+static noinline void check_multi_store_1(struct xarray *xa, unsigned long index,
+		unsigned int order)
+{
+	XA_STATE(xas, xa, index);
+	unsigned long min = index & ~((1UL << order) - 1);
+	unsigned long max = min + (1UL << order);
+
+	xa_store_order(xa, index, order, xa_mk_value(index), GFP_KERNEL);
+	XA_BUG_ON(xa, xa_load(xa, min) != xa_mk_value(index));
+	XA_BUG_ON(xa, xa_load(xa, max - 1) != xa_mk_value(index));
+	XA_BUG_ON(xa, xa_load(xa, max) != NULL);
+	XA_BUG_ON(xa, xa_load(xa, min - 1) != NULL);
+
+	XA_BUG_ON(xa, xas_store(&xas, xa_mk_value(min)) != xa_mk_value(index));
+	XA_BUG_ON(xa, xa_load(xa, min) != xa_mk_value(min));
+	XA_BUG_ON(xa, xa_load(xa, max - 1) != xa_mk_value(min));
+	XA_BUG_ON(xa, xa_load(xa, max) != NULL);
+	XA_BUG_ON(xa, xa_load(xa, min - 1) != NULL);
+
+	xa_erase_index(xa, min);
+	XA_BUG_ON(xa, !xa_empty(xa));
+}
+
+static noinline void check_multi_store_2(struct xarray *xa, unsigned long index,
+		unsigned int order)
+{
+	XA_STATE(xas, xa, index);
+	xa_store_order(xa, index, order, xa_mk_value(0), GFP_KERNEL);
+
+	XA_BUG_ON(xa, xas_store(&xas, xa_mk_value(1)) != xa_mk_value(0));
+	XA_BUG_ON(xa, xas.xa_index != index);
+	XA_BUG_ON(xa, xas_store(&xas, NULL) != xa_mk_value(1));
+	XA_BUG_ON(xa, !xa_empty(xa));
+}
+#endif
+
 static noinline void check_multi_store(struct xarray *xa)
 {
 #ifdef CONFIG_XARRAY_MULTI
@@ -487,6 +524,13 @@ static noinline void check_multi_store(struct xarray *xa)
 			XA_BUG_ON(xa, !xa_empty(xa));
 		}
 	}
+
+	for (i = 0; i < 20; i++) {
+		check_multi_store_1(xa, 200, i);
+		check_multi_store_1(xa, 0, i);
+		check_multi_store_1(xa, (1UL << i) + 1, i);
+	}
+	check_multi_store_2(xa, 4095, 9);
 #endif
 }
 
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index a60c03287e9c..6e8d66c2aa89 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -20,46 +20,6 @@
 
 #include "test.h"
 
-static void multiorder_check(unsigned long index, int order)
-{
-	unsigned long i;
-	unsigned long min = index & ~((1UL << order) - 1);
-	unsigned long max = min + (1UL << order);
-	void **slot;
-	struct item *item2 = item_create(min, order);
-	RADIX_TREE(tree, GFP_KERNEL);
-
-	printv(2, "Multiorder index %ld, order %d\n", index, order);
-
-	assert(item_insert_order(&tree, index, order) == 0);
-
-	for (i = min; i < max; i++) {
-		struct item *item = item_lookup(&tree, i);
-		assert(item != 0);
-		assert(item->index == index);
-	}
-	for (i = 0; i < min; i++)
-		item_check_absent(&tree, i);
-	for (i = max; i < 2*max; i++)
-		item_check_absent(&tree, i);
-	for (i = min; i < max; i++)
-		assert(radix_tree_insert(&tree, i, item2) == -EEXIST);
-
-	slot = radix_tree_lookup_slot(&tree, index);
-	free(*slot);
-	radix_tree_replace_slot(&tree, slot, item2);
-	for (i = min; i < max; i++) {
-		struct item *item = item_lookup(&tree, i);
-		assert(item != 0);
-		assert(item->index == min);
-	}
-
-	assert(item_delete(&tree, min) != 0);
-
-	for (i = 0; i < 2*max; i++)
-		item_check_absent(&tree, i);
-}
-
 void multiorder_iteration(void)
 {
 	RADIX_TREE(tree, GFP_KERNEL);
@@ -251,14 +211,6 @@ static void multiorder_iteration_race(void)
 
 void multiorder_checks(void)
 {
-	int i;
-
-	for (i = 0; i < 20; i++) {
-		multiorder_check(200, i);
-		multiorder_check(0, i);
-		multiorder_check((1UL << i) + 1, i);
-	}
-
 	multiorder_iteration();
 	multiorder_tagged_iteration();
 	multiorder_iteration_race();
-- 
cgit 


From 9076b33d7dad8e316c90918845417e85347f682c Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Wed, 12 Sep 2018 12:52:45 -0400
Subject: radix tree test suite: Remove __item_insert

Inline it into its one caller

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 tools/testing/radix-tree/test.c | 7 +------
 tools/testing/radix-tree/test.h | 1 -
 2 files changed, 1 insertion(+), 7 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index 32973dd51ec5..5991cfd34f2b 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -25,11 +25,6 @@ int item_tag_get(struct radix_tree_root *root, unsigned long index, int tag)
 	return radix_tree_tag_get(root, index, tag);
 }
 
-int __item_insert(struct radix_tree_root *root, struct item *item)
-{
-	return __radix_tree_insert(root, item->index, item->order, item);
-}
-
 struct item *item_create(unsigned long index, unsigned int order)
 {
 	struct item *ret = malloc(sizeof(*ret));
@@ -43,7 +38,7 @@ int item_insert_order(struct radix_tree_root *root, unsigned long index,
 			unsigned order)
 {
 	struct item *item = item_create(index, order);
-	int err = __item_insert(root, item);
+	int err = __radix_tree_insert(root, item->index, item->order, item);
 	if (err)
 		free(item);
 	return err;
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index a2f53c889a31..28961a08828e 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -11,7 +11,6 @@ struct item {
 };
 
 struct item *item_create(unsigned long index, unsigned int order);
-int __item_insert(struct radix_tree_root *root, struct item *item);
 int item_insert(struct radix_tree_root *root, unsigned long index);
 void item_sanity(struct item *item, unsigned long index);
 void item_free(struct item *item, unsigned long index);
-- 
cgit 


From 879a9ae7b5bc046f195a725d62bbc96258e5d0c8 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Wed, 12 Sep 2018 23:12:47 -0400
Subject: radix tree test suite: Remove multiorder benchmarking

The multiorder radix tree code is being removed, so remove the
benchmarking of its performance.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 tools/testing/radix-tree/benchmark.c | 50 +++++++++++++++---------------------
 1 file changed, 21 insertions(+), 29 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/radix-tree/benchmark.c b/tools/testing/radix-tree/benchmark.c
index 35741b9c2a4a..7e195ed8e92d 100644
--- a/tools/testing/radix-tree/benchmark.c
+++ b/tools/testing/radix-tree/benchmark.c
@@ -17,9 +17,6 @@
 #include <time.h>
 #include "test.h"
 
-#define for_each_index(i, base, order) \
-	        for (i = base; i < base + (1 << order); i++)
-
 #define NSEC_PER_SEC	1000000000L
 
 static long long benchmark_iter(struct radix_tree_root *root, bool tagged)
@@ -61,7 +58,7 @@ again:
 }
 
 static void benchmark_insert(struct radix_tree_root *root,
-			     unsigned long size, unsigned long step, int order)
+			     unsigned long size, unsigned long step)
 {
 	struct timespec start, finish;
 	unsigned long index;
@@ -70,19 +67,19 @@ static void benchmark_insert(struct radix_tree_root *root,
 	clock_gettime(CLOCK_MONOTONIC, &start);
 
 	for (index = 0 ; index < size ; index += step)
-		item_insert_order(root, index, order);
+		item_insert(root, index);
 
 	clock_gettime(CLOCK_MONOTONIC, &finish);
 
 	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
 	       (finish.tv_nsec - start.tv_nsec);
 
-	printv(2, "Size: %8ld, step: %8ld, order: %d, insertion: %15lld ns\n",
-		size, step, order, nsec);
+	printv(2, "Size: %8ld, step: %8ld, insertion: %15lld ns\n",
+		size, step, nsec);
 }
 
 static void benchmark_tagging(struct radix_tree_root *root,
-			     unsigned long size, unsigned long step, int order)
+			     unsigned long size, unsigned long step)
 {
 	struct timespec start, finish;
 	unsigned long index;
@@ -98,49 +95,48 @@ static void benchmark_tagging(struct radix_tree_root *root,
 	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
 	       (finish.tv_nsec - start.tv_nsec);
 
-	printv(2, "Size: %8ld, step: %8ld, order: %d, tagging: %17lld ns\n",
-		size, step, order, nsec);
+	printv(2, "Size: %8ld, step: %8ld, tagging: %17lld ns\n",
+		size, step, nsec);
 }
 
 static void benchmark_delete(struct radix_tree_root *root,
-			     unsigned long size, unsigned long step, int order)
+			     unsigned long size, unsigned long step)
 {
 	struct timespec start, finish;
-	unsigned long index, i;
+	unsigned long index;
 	long long nsec;
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
 
 	for (index = 0 ; index < size ; index += step)
-		for_each_index(i, index, order)
-			item_delete(root, i);
+		item_delete(root, index);
 
 	clock_gettime(CLOCK_MONOTONIC, &finish);
 
 	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
 	       (finish.tv_nsec - start.tv_nsec);
 
-	printv(2, "Size: %8ld, step: %8ld, order: %d, deletion: %16lld ns\n",
-		size, step, order, nsec);
+	printv(2, "Size: %8ld, step: %8ld, deletion: %16lld ns\n",
+		size, step, nsec);
 }
 
-static void benchmark_size(unsigned long size, unsigned long step, int order)
+static void benchmark_size(unsigned long size, unsigned long step)
 {
 	RADIX_TREE(tree, GFP_KERNEL);
 	long long normal, tagged;
 
-	benchmark_insert(&tree, size, step, order);
-	benchmark_tagging(&tree, size, step, order);
+	benchmark_insert(&tree, size, step);
+	benchmark_tagging(&tree, size, step);
 
 	tagged = benchmark_iter(&tree, true);
 	normal = benchmark_iter(&tree, false);
 
-	printv(2, "Size: %8ld, step: %8ld, order: %d, tagged iteration: %8lld ns\n",
-		size, step, order, tagged);
-	printv(2, "Size: %8ld, step: %8ld, order: %d, normal iteration: %8lld ns\n",
-		size, step, order, normal);
+	printv(2, "Size: %8ld, step: %8ld, tagged iteration: %8lld ns\n",
+		size, step, tagged);
+	printv(2, "Size: %8ld, step: %8ld, normal iteration: %8lld ns\n",
+		size, step, normal);
 
-	benchmark_delete(&tree, size, step, order);
+	benchmark_delete(&tree, size, step);
 
 	item_kill_tree(&tree);
 	rcu_barrier();
@@ -158,9 +154,5 @@ void benchmark(void)
 
 	for (c = 0; size[c]; c++)
 		for (s = 0; step[s]; s++)
-			benchmark_size(size[c], step[s], 0);
-
-	for (c = 0; size[c]; c++)
-		for (s = 0; step[s]; s++)
-			benchmark_size(size[c], step[s] << 9, 9);
+			benchmark_size(size[c], step[s]);
 }
-- 
cgit 


From 4bb53bdda0d1e061035774ed4868bdeb4d889044 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Wed, 12 Sep 2018 23:29:32 -0400
Subject: radix tree tests: Move item_insert_order

The remaining tests are not suitable for moving in-kernel, so move
item_insert_order() into multiorder.c, make it static and make it use
the XArray.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 tools/testing/radix-tree/multiorder.c | 19 +++++++++++++++++++
 tools/testing/radix-tree/test.c       | 12 +++---------
 tools/testing/radix-tree/test.h       |  2 --
 3 files changed, 22 insertions(+), 11 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 6e8d66c2aa89..8c41dca272b1 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -20,6 +20,25 @@
 
 #include "test.h"
 
+static int item_insert_order(struct xarray *xa, unsigned long index,
+			unsigned order)
+{
+	XA_STATE_ORDER(xas, xa, index, order);
+	struct item *item = item_create(index, order);
+
+	do {
+		xas_lock(&xas);
+		xas_store(&xas, item);
+		xas_unlock(&xas);
+	} while (xas_nomem(&xas, GFP_KERNEL));
+
+	if (!xas_error(&xas))
+		return 0;
+
+	free(item);
+	return xas_error(&xas);
+}
+
 void multiorder_iteration(void)
 {
 	RADIX_TREE(tree, GFP_KERNEL);
diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index 5991cfd34f2b..5376b8c5d8d6 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -34,21 +34,15 @@ struct item *item_create(unsigned long index, unsigned int order)
 	return ret;
 }
 
-int item_insert_order(struct radix_tree_root *root, unsigned long index,
-			unsigned order)
+int item_insert(struct radix_tree_root *root, unsigned long index)
 {
-	struct item *item = item_create(index, order);
-	int err = __radix_tree_insert(root, item->index, item->order, item);
+	struct item *item = item_create(index, 0);
+	int err = radix_tree_insert(root, item->index, item);
 	if (err)
 		free(item);
 	return err;
 }
 
-int item_insert(struct radix_tree_root *root, unsigned long index)
-{
-	return item_insert_order(root, index, 0);
-}
-
 void item_sanity(struct item *item, unsigned long index)
 {
 	unsigned long mask;
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index 28961a08828e..e259c0839d5d 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -14,8 +14,6 @@ struct item *item_create(unsigned long index, unsigned int order);
 int item_insert(struct radix_tree_root *root, unsigned long index);
 void item_sanity(struct item *item, unsigned long index);
 void item_free(struct item *item, unsigned long index);
-int item_insert_order(struct radix_tree_root *root, unsigned long index,
-			unsigned order);
 int item_delete(struct radix_tree_root *root, unsigned long index);
 int item_delete_rcu(struct radix_tree_root *root, unsigned long index);
 struct item *item_lookup(struct radix_tree_root *root, unsigned long index);
-- 
cgit 


From ccc89e30fac790e3a175dbfc863c67286fce96b0 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Thu, 13 Sep 2018 10:15:41 -0400
Subject: radix tree tests: Convert item_kill_tree to XArray

In preparation for the removal of the multiorder radix tree code,
convert item_kill_tree() to use the XArray so it can still be called
for XArrays containing multi-index entries.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 tools/testing/radix-tree/test.c | 30 +++++++++---------------------
 1 file changed, 9 insertions(+), 21 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index 5376b8c5d8d6..19045ce3bd23 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -252,31 +252,19 @@ void verify_tag_consistency(struct radix_tree_root *root, unsigned int tag)
 	verify_node(node, tag, !!root_tag_get(root, tag));
 }
 
-void item_kill_tree(struct radix_tree_root *root)
+void item_kill_tree(struct xarray *xa)
 {
-	struct radix_tree_iter iter;
-	void **slot;
-	struct item *items[32];
-	int nfound;
-
-	radix_tree_for_each_slot(slot, root, &iter, 0) {
-		if (xa_is_value(*slot))
-			radix_tree_delete(root, iter.index);
-	}
-
-	while ((nfound = radix_tree_gang_lookup(root, (void **)items, 0, 32))) {
-		int i;
-
-		for (i = 0; i < nfound; i++) {
-			void *ret;
+	XA_STATE(xas, xa, 0);
+	void *entry;
 
-			ret = radix_tree_delete(root, items[i]->index);
-			assert(ret == items[i]);
-			free(items[i]);
+	xas_for_each(&xas, entry, ULONG_MAX) {
+		if (!xa_is_value(entry)) {
+			item_free(entry, xas.xa_index);
 		}
+		xas_store(&xas, NULL);
 	}
-	assert(radix_tree_gang_lookup(root, (void **)items, 0, 32) == 0);
-	assert(root->xa_head == NULL);
+
+	assert(xa_empty(xa));
 }
 
 void tree_verify_min_height(struct radix_tree_root *root, int maxindex)
-- 
cgit 


From b66b5a48b8a0e43dc114573da11c1a9c586a2d4f Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Sat, 22 Sep 2018 15:34:28 -0400
Subject: radix tree tests: Convert item_delete_rcu to XArray

In preparation for the removal of the multiorder radix tree code,
convert item_delete_rcu() to use the XArray so it can still be called
for XArrays containing multi-index entries.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 tools/testing/radix-tree/test.c | 4 ++--
 tools/testing/radix-tree/test.h | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index 19045ce3bd23..a15d0512e633 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -76,9 +76,9 @@ static void item_free_rcu(struct rcu_head *head)
 	free(item);
 }
 
-int item_delete_rcu(struct radix_tree_root *root, unsigned long index)
+int item_delete_rcu(struct xarray *xa, unsigned long index)
 {
-	struct item *item = radix_tree_delete(root, index);
+	struct item *item = xa_erase(xa, index);
 
 	if (item) {
 		item_sanity(item, index);
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index e259c0839d5d..1ee4b2c0ad10 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -15,7 +15,7 @@ int item_insert(struct radix_tree_root *root, unsigned long index);
 void item_sanity(struct item *item, unsigned long index);
 void item_free(struct item *item, unsigned long index);
 int item_delete(struct radix_tree_root *root, unsigned long index);
-int item_delete_rcu(struct radix_tree_root *root, unsigned long index);
+int item_delete_rcu(struct xarray *xa, unsigned long index);
 struct item *item_lookup(struct radix_tree_root *root, unsigned long index);
 
 void item_check_present(struct radix_tree_root *root, unsigned long index);
-- 
cgit 


From 542980aa9318edcfb68aa7bf6eacf2814dc137dd Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Sat, 22 Sep 2018 16:12:41 -0400
Subject: radix tree test: Convert multiorder tests to XArray

This is the last remaining user of the multiorder functionality of the
radix tree.  Test the XArray instead.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 tools/testing/radix-tree/multiorder.c | 105 ++++++++++++++++------------------
 1 file changed, 49 insertions(+), 56 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 8c41dca272b1..ff27a74d9762 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -39,21 +39,20 @@ static int item_insert_order(struct xarray *xa, unsigned long index,
 	return xas_error(&xas);
 }
 
-void multiorder_iteration(void)
+void multiorder_iteration(struct xarray *xa)
 {
-	RADIX_TREE(tree, GFP_KERNEL);
-	struct radix_tree_iter iter;
-	void **slot;
+	XA_STATE(xas, xa, 0);
+	struct item *item;
 	int i, j, err;
 
-	printv(1, "Multiorder iteration test\n");
-
 #define NUM_ENTRIES 11
 	int index[NUM_ENTRIES] = {0, 2, 4, 8, 16, 32, 34, 36, 64, 72, 128};
 	int order[NUM_ENTRIES] = {1, 1, 2, 3,  4,  1,  0,  1,  3,  0, 7};
 
+	printv(1, "Multiorder iteration test\n");
+
 	for (i = 0; i < NUM_ENTRIES; i++) {
-		err = item_insert_order(&tree, index[i], order[i]);
+		err = item_insert_order(xa, index[i], order[i]);
 		assert(!err);
 	}
 
@@ -62,14 +61,14 @@ void multiorder_iteration(void)
 			if (j <= (index[i] | ((1 << order[i]) - 1)))
 				break;
 
-		radix_tree_for_each_slot(slot, &tree, &iter, j) {
-			int height = order[i] / RADIX_TREE_MAP_SHIFT;
-			int shift = height * RADIX_TREE_MAP_SHIFT;
+		xas_set(&xas, j);
+		xas_for_each(&xas, item, ULONG_MAX) {
+			int height = order[i] / XA_CHUNK_SHIFT;
+			int shift = height * XA_CHUNK_SHIFT;
 			unsigned long mask = (1UL << order[i]) - 1;
-			struct item *item = *slot;
 
-			assert((iter.index | mask) == (index[i] | mask));
-			assert(iter.shift == shift);
+			assert((xas.xa_index | mask) == (index[i] | mask));
+			assert(xas.xa_node->shift == shift);
 			assert(!radix_tree_is_internal_node(item));
 			assert((item->index | mask) == (index[i] | mask));
 			assert(item->order == order[i]);
@@ -77,18 +76,15 @@ void multiorder_iteration(void)
 		}
 	}
 
-	item_kill_tree(&tree);
+	item_kill_tree(xa);
 }
 
-void multiorder_tagged_iteration(void)
+void multiorder_tagged_iteration(struct xarray *xa)
 {
-	RADIX_TREE(tree, GFP_KERNEL);
-	struct radix_tree_iter iter;
-	void **slot;
+	XA_STATE(xas, xa, 0);
+	struct item *item;
 	int i, j;
 
-	printv(1, "Multiorder tagged iteration test\n");
-
 #define MT_NUM_ENTRIES 9
 	int index[MT_NUM_ENTRIES] = {0, 2, 4, 16, 32, 40, 64, 72, 128};
 	int order[MT_NUM_ENTRIES] = {1, 0, 2, 4,  3,  1,  3,  0,   7};
@@ -96,13 +92,15 @@ void multiorder_tagged_iteration(void)
 #define TAG_ENTRIES 7
 	int tag_index[TAG_ENTRIES] = {0, 4, 16, 40, 64, 72, 128};
 
+	printv(1, "Multiorder tagged iteration test\n");
+
 	for (i = 0; i < MT_NUM_ENTRIES; i++)
-		assert(!item_insert_order(&tree, index[i], order[i]));
+		assert(!item_insert_order(xa, index[i], order[i]));
 
-	assert(!radix_tree_tagged(&tree, 1));
+	assert(!xa_marked(xa, XA_MARK_1));
 
 	for (i = 0; i < TAG_ENTRIES; i++)
-		assert(radix_tree_tag_set(&tree, tag_index[i], 1));
+		xa_set_mark(xa, tag_index[i], XA_MARK_1);
 
 	for (j = 0; j < 256; j++) {
 		int k;
@@ -114,22 +112,22 @@ void multiorder_tagged_iteration(void)
 				break;
 		}
 
-		radix_tree_for_each_tagged(slot, &tree, &iter, j, 1) {
+		xas_set(&xas, j);
+		xas_for_each_marked(&xas, item, ULONG_MAX, XA_MARK_1) {
 			unsigned long mask;
-			struct item *item = *slot;
 			for (k = i; index[k] < tag_index[i]; k++)
 				;
 			mask = (1UL << order[k]) - 1;
 
-			assert((iter.index | mask) == (tag_index[i] | mask));
-			assert(!radix_tree_is_internal_node(item));
+			assert((xas.xa_index | mask) == (tag_index[i] | mask));
+			assert(!xa_is_internal(item));
 			assert((item->index | mask) == (tag_index[i] | mask));
 			assert(item->order == order[k]);
 			i++;
 		}
 	}
 
-	assert(tag_tagged_items(&tree, 0, ~0UL, TAG_ENTRIES, XA_MARK_1,
+	assert(tag_tagged_items(xa, 0, ULONG_MAX, TAG_ENTRIES, XA_MARK_1,
 				XA_MARK_2) == TAG_ENTRIES);
 
 	for (j = 0; j < 256; j++) {
@@ -142,29 +140,31 @@ void multiorder_tagged_iteration(void)
 				break;
 		}
 
-		radix_tree_for_each_tagged(slot, &tree, &iter, j, 2) {
-			struct item *item = *slot;
+		xas_set(&xas, j);
+		xas_for_each_marked(&xas, item, ULONG_MAX, XA_MARK_2) {
 			for (k = i; index[k] < tag_index[i]; k++)
 				;
 			mask = (1 << order[k]) - 1;
 
-			assert((iter.index | mask) == (tag_index[i] | mask));
-			assert(!radix_tree_is_internal_node(item));
+			assert((xas.xa_index | mask) == (tag_index[i] | mask));
+			assert(!xa_is_internal(item));
 			assert((item->index | mask) == (tag_index[i] | mask));
 			assert(item->order == order[k]);
 			i++;
 		}
 	}
 
-	assert(tag_tagged_items(&tree, 1, ~0UL, MT_NUM_ENTRIES * 2, XA_MARK_1,
+	assert(tag_tagged_items(xa, 1, ULONG_MAX, MT_NUM_ENTRIES * 2, XA_MARK_1,
 				XA_MARK_0) == TAG_ENTRIES);
 	i = 0;
-	radix_tree_for_each_tagged(slot, &tree, &iter, 0, 0) {
-		assert(iter.index == tag_index[i]);
+	xas_set(&xas, 0);
+	xas_for_each_marked(&xas, item, ULONG_MAX, XA_MARK_0) {
+		assert(xas.xa_index == tag_index[i]);
 		i++;
 	}
+	assert(i == TAG_ENTRIES);
 
-	item_kill_tree(&tree);
+	item_kill_tree(xa);
 }
 
 bool stop_iteration = false;
@@ -187,52 +187,45 @@ static void *creator_func(void *ptr)
 
 static void *iterator_func(void *ptr)
 {
-	struct radix_tree_root *tree = ptr;
-	struct radix_tree_iter iter;
+	XA_STATE(xas, ptr, 0);
 	struct item *item;
-	void **slot;
 
 	while (!stop_iteration) {
 		rcu_read_lock();
-		radix_tree_for_each_slot(slot, tree, &iter, 0) {
-			item = radix_tree_deref_slot(slot);
-
-			if (!item)
+		xas_for_each(&xas, item, ULONG_MAX) {
+			if (xas_retry(&xas, item))
 				continue;
-			if (radix_tree_deref_retry(item)) {
-				slot = radix_tree_iter_retry(&iter);
-				continue;
-			}
 
-			item_sanity(item, iter.index);
+			item_sanity(item, xas.xa_index);
 		}
 		rcu_read_unlock();
 	}
 	return NULL;
 }
 
-static void multiorder_iteration_race(void)
+static void multiorder_iteration_race(struct xarray *xa)
 {
 	const int num_threads = sysconf(_SC_NPROCESSORS_ONLN);
 	pthread_t worker_thread[num_threads];
-	RADIX_TREE(tree, GFP_KERNEL);
 	int i;
 
-	pthread_create(&worker_thread[0], NULL, &creator_func, &tree);
+	pthread_create(&worker_thread[0], NULL, &creator_func, xa);
 	for (i = 1; i < num_threads; i++)
-		pthread_create(&worker_thread[i], NULL, &iterator_func, &tree);
+		pthread_create(&worker_thread[i], NULL, &iterator_func, xa);
 
 	for (i = 0; i < num_threads; i++)
 		pthread_join(worker_thread[i], NULL);
 
-	item_kill_tree(&tree);
+	item_kill_tree(xa);
 }
 
+static DEFINE_XARRAY(array);
+
 void multiorder_checks(void)
 {
-	multiorder_iteration();
-	multiorder_tagged_iteration();
-	multiorder_iteration_race();
+	multiorder_iteration(&array);
+	multiorder_tagged_iteration(&array);
+	multiorder_iteration_race(&array);
 
 	radix_tree_cpu_dead(0);
 }
-- 
cgit 


From 3a08cd52c37c793ffc199f6fc2ecfc368e284b2d Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Sat, 22 Sep 2018 16:14:30 -0400
Subject: radix tree: Remove multiorder support

All users have now been converted to the XArray.  Removing the support
reduces code size and ensures new users will use the XArray instead.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 include/linux/radix-tree.h                    |  40 +----
 lib/Kconfig                                   |   4 -
 lib/radix-tree.c                              | 215 ++------------------------
 mm/Kconfig                                    |   4 +-
 tools/testing/radix-tree/generated/autoconf.h |   1 -
 5 files changed, 19 insertions(+), 245 deletions(-)

(limited to 'tools/testing')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 9a1460488163..06c4c7a6c09c 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -96,7 +96,6 @@ static inline bool radix_tree_empty(const struct radix_tree_root *root)
  * @next_index:	one beyond the last index for this chunk
  * @tags:	bit-mask for tag-iterating
  * @node:	node that contains current slot
- * @shift:	shift for the node that holds our slots
  *
  * This radix tree iterator works in terms of "chunks" of slots.  A chunk is a
  * subinterval of slots contained within one radix tree leaf node.  It is
@@ -110,20 +109,8 @@ struct radix_tree_iter {
 	unsigned long	next_index;
 	unsigned long	tags;
 	struct radix_tree_node *node;
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-	unsigned int	shift;
-#endif
 };
 
-static inline unsigned int iter_shift(const struct radix_tree_iter *iter)
-{
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-	return iter->shift;
-#else
-	return 0;
-#endif
-}
-
 /**
  * Radix-tree synchronization
  *
@@ -230,13 +217,8 @@ static inline int radix_tree_exception(void *arg)
 	return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK);
 }
 
-int __radix_tree_insert(struct radix_tree_root *, unsigned long index,
-			unsigned order, void *);
-static inline int radix_tree_insert(struct radix_tree_root *root,
-			unsigned long index, void *entry)
-{
-	return __radix_tree_insert(root, index, 0, entry);
-}
+int radix_tree_insert(struct radix_tree_root *, unsigned long index,
+			void *);
 void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index,
 			  struct radix_tree_node **nodep, void __rcu ***slotp);
 void *radix_tree_lookup(const struct radix_tree_root *, unsigned long);
@@ -384,7 +366,7 @@ void __rcu **radix_tree_iter_retry(struct radix_tree_iter *iter)
 static inline unsigned long
 __radix_tree_iter_add(struct radix_tree_iter *iter, unsigned long slots)
 {
-	return iter->index + (slots << iter_shift(iter));
+	return iter->index + slots;
 }
 
 /**
@@ -409,20 +391,8 @@ void __rcu **__must_check radix_tree_iter_resume(void __rcu **slot,
 static __always_inline long
 radix_tree_chunk_size(struct radix_tree_iter *iter)
 {
-	return (iter->next_index - iter->index) >> iter_shift(iter);
-}
-
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-void __rcu **__radix_tree_next_slot(void __rcu **slot,
-				struct radix_tree_iter *iter, unsigned flags);
-#else
-/* Can't happen without sibling entries, but the compiler can't tell that */
-static inline void __rcu **__radix_tree_next_slot(void __rcu **slot,
-				struct radix_tree_iter *iter, unsigned flags)
-{
-	return slot;
+	return iter->next_index - iter->index;
 }
-#endif
 
 /**
  * radix_tree_next_slot - find next slot in chunk
@@ -482,8 +452,6 @@ static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot,
 	return NULL;
 
  found:
-	if (unlikely(radix_tree_is_internal_node(rcu_dereference_raw(*slot))))
-		return __radix_tree_next_slot(slot, iter, flags);
 	return slot;
 }
 
diff --git a/lib/Kconfig b/lib/Kconfig
index 40bfa6ccd294..a9965f4af4dd 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -405,10 +405,6 @@ config XARRAY_MULTI
 	  Support entries which occupy multiple consecutive indices in the
 	  XArray.
 
-config RADIX_TREE_MULTIORDER
-	bool
-	select XARRAY_MULTI
-
 config ASSOCIATIVE_ARRAY
 	bool
 	help
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index f107dd2698e3..1106bb6aa01e 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -110,11 +110,6 @@ static unsigned int radix_tree_descend(const struct radix_tree_node *parent,
 	unsigned int offset = (index >> parent->shift) & RADIX_TREE_MAP_MASK;
 	void __rcu **entry = rcu_dereference_raw(parent->slots[offset]);
 
-	if (xa_is_sibling(entry)) {
-		offset = xa_to_sibling(entry);
-		entry = rcu_dereference_raw(parent->slots[offset]);
-	}
-
 	*nodep = (void *)entry;
 	return offset;
 }
@@ -229,7 +224,7 @@ radix_tree_find_next_bit(struct radix_tree_node *node, unsigned int tag,
 
 static unsigned int iter_offset(const struct radix_tree_iter *iter)
 {
-	return (iter->index >> iter_shift(iter)) & RADIX_TREE_MAP_MASK;
+	return iter->index & RADIX_TREE_MAP_MASK;
 }
 
 /*
@@ -506,16 +501,13 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root)
 
 		/*
 		 * The candidate node has more than one child, or its child
-		 * is not at the leftmost slot, or the child is a multiorder
-		 * entry, we cannot shrink.
+		 * is not at the leftmost slot, we cannot shrink.
 		 */
 		if (node->count != 1)
 			break;
 		child = rcu_dereference_raw(node->slots[0]);
 		if (!child)
 			break;
-		if (!radix_tree_is_internal_node(child) && node->shift)
-			break;
 
 		/*
 		 * For an IDR, we must not shrink entry 0 into the root in
@@ -613,7 +605,6 @@ static bool delete_node(struct radix_tree_root *root,
  *	__radix_tree_create	-	create a slot in a radix tree
  *	@root:		radix tree root
  *	@index:		index key
- *	@order:		index occupies 2^order aligned slots
  *	@nodep:		returns node
  *	@slotp:		returns slot
  *
@@ -627,21 +618,19 @@ static bool delete_node(struct radix_tree_root *root,
  *	Returns -ENOMEM, or 0 for success.
  */
 static int __radix_tree_create(struct radix_tree_root *root,
-		unsigned long index, unsigned order,
-		struct radix_tree_node **nodep, void __rcu ***slotp)
+		unsigned long index, struct radix_tree_node **nodep,
+		void __rcu ***slotp)
 {
 	struct radix_tree_node *node = NULL, *child;
 	void __rcu **slot = (void __rcu **)&root->xa_head;
 	unsigned long maxindex;
 	unsigned int shift, offset = 0;
-	unsigned long max = index | ((1UL << order) - 1);
+	unsigned long max = index;
 	gfp_t gfp = root_gfp_mask(root);
 
 	shift = radix_tree_load_root(root, &child, &maxindex);
 
 	/* Make sure the tree is high enough.  */
-	if (order > 0 && max == ((1UL << order) - 1))
-		max++;
 	if (max > maxindex) {
 		int error = radix_tree_extend(root, gfp, max, shift);
 		if (error < 0)
@@ -650,7 +639,7 @@ static int __radix_tree_create(struct radix_tree_root *root,
 		child = rcu_dereference_raw(root->xa_head);
 	}
 
-	while (shift > order) {
+	while (shift > 0) {
 		shift -= RADIX_TREE_MAP_SHIFT;
 		if (child == NULL) {
 			/* Have to add a child node.  */
@@ -711,70 +700,8 @@ static void radix_tree_free_nodes(struct radix_tree_node *node)
 	}
 }
 
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-static inline int insert_entries(struct radix_tree_node *node,
-		void __rcu **slot, void *item, unsigned order, bool replace)
-{
-	void *sibling;
-	unsigned i, n, tag, offset, tags = 0;
-
-	if (node) {
-		if (order > node->shift)
-			n = 1 << (order - node->shift);
-		else
-			n = 1;
-		offset = get_slot_offset(node, slot);
-	} else {
-		n = 1;
-		offset = 0;
-	}
-
-	if (n > 1) {
-		offset = offset & ~(n - 1);
-		slot = &node->slots[offset];
-	}
-	sibling = xa_mk_sibling(offset);
-
-	for (i = 0; i < n; i++) {
-		if (slot[i]) {
-			if (replace) {
-				node->count--;
-				for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
-					if (tag_get(node, tag, offset + i))
-						tags |= 1 << tag;
-			} else
-				return -EEXIST;
-		}
-	}
-
-	for (i = 0; i < n; i++) {
-		struct radix_tree_node *old = rcu_dereference_raw(slot[i]);
-		if (i) {
-			rcu_assign_pointer(slot[i], sibling);
-			for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
-				if (tags & (1 << tag))
-					tag_clear(node, tag, offset + i);
-		} else {
-			rcu_assign_pointer(slot[i], item);
-			for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
-				if (tags & (1 << tag))
-					tag_set(node, tag, offset);
-		}
-		if (xa_is_node(old))
-			radix_tree_free_nodes(old);
-		if (xa_is_value(old))
-			node->nr_values--;
-	}
-	if (node) {
-		node->count += n;
-		if (xa_is_value(item))
-			node->nr_values += n;
-	}
-	return n;
-}
-#else
 static inline int insert_entries(struct radix_tree_node *node,
-		void __rcu **slot, void *item, unsigned order, bool replace)
+		void __rcu **slot, void *item, bool replace)
 {
 	if (*slot)
 		return -EEXIST;
@@ -786,19 +713,17 @@ static inline int insert_entries(struct radix_tree_node *node,
 	}
 	return 1;
 }
-#endif
 
 /**
  *	__radix_tree_insert    -    insert into a radix tree
  *	@root:		radix tree root
  *	@index:		index key
- *	@order:		key covers the 2^order indices around index
  *	@item:		item to insert
  *
  *	Insert an item into the radix tree at position @index.
  */
-int __radix_tree_insert(struct radix_tree_root *root, unsigned long index,
-			unsigned order, void *item)
+int radix_tree_insert(struct radix_tree_root *root, unsigned long index,
+			void *item)
 {
 	struct radix_tree_node *node;
 	void __rcu **slot;
@@ -806,11 +731,11 @@ int __radix_tree_insert(struct radix_tree_root *root, unsigned long index,
 
 	BUG_ON(radix_tree_is_internal_node(item));
 
-	error = __radix_tree_create(root, index, order, &node, &slot);
+	error = __radix_tree_create(root, index, &node, &slot);
 	if (error)
 		return error;
 
-	error = insert_entries(node, slot, item, order, false);
+	error = insert_entries(node, slot, item, false);
 	if (error < 0)
 		return error;
 
@@ -825,7 +750,7 @@ int __radix_tree_insert(struct radix_tree_root *root, unsigned long index,
 
 	return 0;
 }
-EXPORT_SYMBOL(__radix_tree_insert);
+EXPORT_SYMBOL(radix_tree_insert);
 
 /**
  *	__radix_tree_lookup	-	lookup an item in a radix tree
@@ -917,32 +842,12 @@ void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index)
 }
 EXPORT_SYMBOL(radix_tree_lookup);
 
-static inline void replace_sibling_entries(struct radix_tree_node *node,
-				void __rcu **slot, int count, int values)
-{
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-	unsigned offset = get_slot_offset(node, slot);
-	void *ptr = xa_mk_sibling(offset);
-
-	while (++offset < RADIX_TREE_MAP_SIZE) {
-		if (rcu_dereference_raw(node->slots[offset]) != ptr)
-			break;
-		if (count < 0) {
-			node->slots[offset] = NULL;
-			node->count--;
-		}
-		node->nr_values += values;
-	}
-#endif
-}
-
 static void replace_slot(void __rcu **slot, void *item,
 		struct radix_tree_node *node, int count, int values)
 {
 	if (node && (count || values)) {
 		node->count += count;
 		node->nr_values += values;
-		replace_sibling_entries(node, slot, count, values);
 	}
 
 	rcu_assign_pointer(*slot, item);
@@ -1223,14 +1128,6 @@ int radix_tree_tag_get(const struct radix_tree_root *root,
 }
 EXPORT_SYMBOL(radix_tree_tag_get);
 
-static inline void __set_iter_shift(struct radix_tree_iter *iter,
-					unsigned int shift)
-{
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-	iter->shift = shift;
-#endif
-}
-
 /* Construct iter->tags bit-mask from node->tags[tag] array */
 static void set_iter_tags(struct radix_tree_iter *iter,
 				struct radix_tree_node *node, unsigned offset,
@@ -1257,92 +1154,11 @@ static void set_iter_tags(struct radix_tree_iter *iter,
 	}
 }
 
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-static void __rcu **skip_siblings(struct radix_tree_node **nodep,
-			void __rcu **slot, struct radix_tree_iter *iter)
-{
-	while (iter->index < iter->next_index) {
-		*nodep = rcu_dereference_raw(*slot);
-		if (*nodep && !xa_is_sibling(*nodep))
-			return slot;
-		slot++;
-		iter->index = __radix_tree_iter_add(iter, 1);
-		iter->tags >>= 1;
-	}
-
-	*nodep = NULL;
-	return NULL;
-}
-
-void __rcu **__radix_tree_next_slot(void __rcu **slot,
-				struct radix_tree_iter *iter, unsigned flags)
-{
-	unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK;
-	struct radix_tree_node *node;
-
-	slot = skip_siblings(&node, slot, iter);
-
-	while (radix_tree_is_internal_node(node)) {
-		unsigned offset;
-		unsigned long next_index;
-
-		if (node == RADIX_TREE_RETRY)
-			return slot;
-		node = entry_to_node(node);
-		iter->node = node;
-		iter->shift = node->shift;
-
-		if (flags & RADIX_TREE_ITER_TAGGED) {
-			offset = radix_tree_find_next_bit(node, tag, 0);
-			if (offset == RADIX_TREE_MAP_SIZE)
-				return NULL;
-			slot = &node->slots[offset];
-			iter->index = __radix_tree_iter_add(iter, offset);
-			set_iter_tags(iter, node, offset, tag);
-			node = rcu_dereference_raw(*slot);
-		} else {
-			offset = 0;
-			slot = &node->slots[0];
-			for (;;) {
-				node = rcu_dereference_raw(*slot);
-				if (node)
-					break;
-				slot++;
-				offset++;
-				if (offset == RADIX_TREE_MAP_SIZE)
-					return NULL;
-			}
-			iter->index = __radix_tree_iter_add(iter, offset);
-		}
-		if ((flags & RADIX_TREE_ITER_CONTIG) && (offset > 0))
-			goto none;
-		next_index = (iter->index | shift_maxindex(iter->shift)) + 1;
-		if (next_index < iter->next_index)
-			iter->next_index = next_index;
-	}
-
-	return slot;
- none:
-	iter->next_index = 0;
-	return NULL;
-}
-EXPORT_SYMBOL(__radix_tree_next_slot);
-#else
-static void __rcu **skip_siblings(struct radix_tree_node **nodep,
-			void __rcu **slot, struct radix_tree_iter *iter)
-{
-	return slot;
-}
-#endif
-
 void __rcu **radix_tree_iter_resume(void __rcu **slot,
 					struct radix_tree_iter *iter)
 {
-	struct radix_tree_node *node;
-
 	slot++;
 	iter->index = __radix_tree_iter_add(iter, 1);
-	skip_siblings(&node, slot, iter);
 	iter->next_index = iter->index;
 	iter->tags = 0;
 	return NULL;
@@ -1393,7 +1209,6 @@ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root,
 		iter->next_index = maxindex + 1;
 		iter->tags = 1;
 		iter->node = NULL;
-		__set_iter_shift(iter, 0);
 		return (void __rcu **)&root->xa_head;
 	}
 
@@ -1414,8 +1229,6 @@ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root,
 				while (++offset	< RADIX_TREE_MAP_SIZE) {
 					void *slot = rcu_dereference_raw(
 							node->slots[offset]);
-					if (xa_is_sibling(slot))
-						continue;
 					if (slot)
 						break;
 				}
@@ -1436,10 +1249,9 @@ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root,
 	} while (node->shift && radix_tree_is_internal_node(child));
 
 	/* Update the iterator state */
-	iter->index = (index &~ node_maxindex(node)) | (offset << node->shift);
+	iter->index = (index &~ node_maxindex(node)) | offset;
 	iter->next_index = (index | node_maxindex(node)) + 1;
 	iter->node = node;
-	__set_iter_shift(iter, node->shift);
 
 	if (flags & RADIX_TREE_ITER_TAGGED)
 		set_iter_tags(iter, node, offset, tag);
@@ -1750,7 +1562,6 @@ void __rcu **idr_get_free(struct radix_tree_root *root,
 	else
 		iter->next_index = 1;
 	iter->node = node;
-	__set_iter_shift(iter, shift);
 	set_iter_tags(iter, node, offset, IDR_FREE);
 
 	return slot;
diff --git a/mm/Kconfig b/mm/Kconfig
index de64ea658716..02301a89089e 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -379,7 +379,7 @@ config TRANSPARENT_HUGEPAGE
 	bool "Transparent Hugepage Support"
 	depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select COMPACTION
-	select RADIX_TREE_MULTIORDER
+	select XARRAY_MULTI
 	help
 	  Transparent Hugepages allows the kernel to use huge pages and
 	  huge tlb transparently to the applications whenever possible.
@@ -671,7 +671,7 @@ config ZONE_DEVICE
 	depends on MEMORY_HOTREMOVE
 	depends on SPARSEMEM_VMEMMAP
 	depends on ARCH_HAS_ZONE_DEVICE
-	select RADIX_TREE_MULTIORDER
+	select XARRAY_MULTI
 
 	help
 	  Device memory hotplug support allows for establishing pmem,
diff --git a/tools/testing/radix-tree/generated/autoconf.h b/tools/testing/radix-tree/generated/autoconf.h
index ca8e03ad19ac..2218b3cc184e 100644
--- a/tools/testing/radix-tree/generated/autoconf.h
+++ b/tools/testing/radix-tree/generated/autoconf.h
@@ -1,2 +1 @@
-#define CONFIG_RADIX_TREE_MULTIORDER 1
 #define CONFIG_XARRAY_MULTI 1
-- 
cgit 


From 88c2e3b4a97277399ceb80d630e9838330b2146a Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Sat, 20 Oct 2018 23:33:09 +0200
Subject: tc-tests: test denial of 'goto chain' on 'random' traffic in
 gact.json

add test to verify if act_gact forbids 'goto chain' control actions on
'random' traffic in gact.json.

Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../tc-testing/tc-tests/actions/gact.json          | 24 ++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
index 68c91023cdb9..89189a03ce3d 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
@@ -536,5 +536,29 @@
         "matchPattern": "^[ \t]+index [0-9]+ ref",
         "matchCount": "0",
         "teardown": []
+    },
+    {
+        "id": "8e47",
+        "name": "Add gact action with random determ goto chain control action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action pass random determ goto chain 1 2 index 90",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action pass random type determ goto chain 1 val 2.*index 90 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
     }
 ]
-- 
cgit 


From 246e886d22e2a8ceceec1f4f66138f93eafddbaa Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Sat, 20 Oct 2018 23:33:10 +0200
Subject: tc-tests: test denial of 'goto chain' for exceed traffic in
 police.json

add test to verify if act_police forbids 'goto chain' control actions for
'exceed' traffic.

Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../tc-testing/tc-tests/actions/police.json        | 24 ++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
index 30f9b54bd666..4086a50a670e 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
@@ -715,5 +715,29 @@
         "teardown": [
             "$TC actions flush action police"
         ]
+    },
+    {
+        "id": "b48b",
+        "name": "Add police action with exceed goto chain control action",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 1mbit burst 1k conform-exceed pass / goto chain 42",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 1Mbit burst 1Kb mtu 2Kb action pass/goto chain 42",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
     }
 ]
-- 
cgit 


From 9d954f9519707bc0af29ead8b1dedc660306da1b Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:12:55 +0900
Subject: selftests/ftrace: Add --stop-fail hidden option for debug

Add --stop-fail option for debugging the ftracetest.

With this option, ftracetest stops right after a testcase
fails instead of finish running all testcases.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/ftracetest | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index f9a9d424c980..c9c7fa8dc440 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -69,6 +69,10 @@ parse_opts() { # opts
       DEBUG=1
       shift 1
     ;;
+    --stop-fail)
+      STOP_FAILURE=1
+      shift 1
+    ;;
     --fail-unsupported)
       UNSUPPORTED_RESULT=1
       shift 1
@@ -117,6 +121,7 @@ KEEP_LOG=0
 DEBUG=0
 VERBOSE=0
 UNSUPPORTED_RESULT=0
+STOP_FAILURE=0
 # Parse command-line options
 parse_opts $*
 
@@ -304,6 +309,10 @@ run_test() { # testfile
 # Main loop
 for t in $TEST_CASES; do
   run_test $t
+  if [ $STOP_FAILURE -ne 0 -a $TOTAL_RESULT -ne 0 ]; then
+    echo "A failure detected. Stop test."
+    exit 1
+  fi
 done
 
 # Test on instance loop
@@ -315,6 +324,10 @@ for t in $TEST_CASES; do
   run_test $t
   rmdir $TRACING_DIR
   TRACING_DIR=$SAVED_TRACING_DIR
+  if [ $STOP_FAILURE -ne 0 -a $TOTAL_RESULT -ne 0 ]; then
+    echo "A failure detected. Stop test."
+    exit 1
+  fi
 done
 
 prlog ""
-- 
cgit 


From 5d1c6580d616dfc864ffdec587e645e50a21c072 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:13:23 +0900
Subject: selftests/ftrace: Add --console hidden option

Add --console hidden option for debug test cases.

This option allows to put "sh" or something else
when the test case hits a bug.

For example, if you find a testcase which doesn't
pass, you can insert sh for interactive debug as below

  -----
  #!/bin/sh
  # description: sample test case

  good-command
  suspicious-wrong-command
  sh # <- add this for interactive debug
  -----

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/ftracetest | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index c9c7fa8dc440..8debd37038e4 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -60,11 +60,21 @@ parse_opts() { # opts
       shift 1
     ;;
     --verbose|-v|-vv|-vvv)
+      if [ $VERBOSE -eq -1 ]; then
+	usage "--console can not use with --verbose"
+      fi
       VERBOSE=$((VERBOSE + 1))
       [ $1 = '-vv' ] && VERBOSE=$((VERBOSE + 1))
       [ $1 = '-vvv' ] && VERBOSE=$((VERBOSE + 2))
       shift 1
     ;;
+    --console)
+      if [ $VERBOSE -ne 0 ]; then
+	usage "--console can not use with --verbose"
+      fi
+      VERBOSE=-1
+      shift 1
+    ;;
     --debug|-d)
       DEBUG=1
       shift 1
@@ -283,7 +293,9 @@ run_test() { # testfile
   testcase $1
   echo "execute$INSTANCE: "$1 > $testlog
   SIG_RESULT=0
-  if [ -z "$LOG_FILE" ]; then
+  if [ $VERBOSE -eq -1 ]; then
+    __run_test $1
+  elif [ -z "$LOG_FILE" ]; then
     __run_test $1 2>&1
   elif [ $VERBOSE -ge 3 ]; then
     __run_test $1 | tee -a $testlog 2>&1
-- 
cgit 


From 7d0abba4293e555a5b1a6ea060cddd05f4ee357f Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:13:51 +0900
Subject: selftests/ftrace: Add case number prefix to logfile

Add a case number prefix to each logfile. This makes
it easier to find which logfile is corresponding
to which failure.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/ftracetest | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index 8debd37038e4..3ca596255eff 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -284,13 +284,13 @@ __run_test() { # testfile
 # Run one test case
 run_test() { # testfile
   local testname=`basename $1`
+  testcase $1
   if [ ! -z "$LOG_FILE" ] ; then
-    local testlog=`mktemp $LOG_DIR/${testname}-log.XXXXXX`
+    local testlog=`mktemp $LOG_DIR/${CASENO}-${testname}-log.XXXXXX`
   else
     local testlog=/proc/self/fd/1
   fi
   export TMPDIR=`mktemp -d /tmp/ftracetest-dir.XXXXXX`
-  testcase $1
   echo "execute$INSTANCE: "$1 > $testlog
   SIG_RESULT=0
   if [ $VERBOSE -eq -1 ]; then
-- 
cgit 


From 7590472e78c8fbe1383aba30450655fd6415fa7b Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:14:19 +0900
Subject: selftests/ftrace: More initialize features in initialize_ftrace

Clear pid filter, synthetic_events, snapshots,
ftrace filter, and trace log in initialize_ftrace(),
since those are used in test cases.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/test.d/functions | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions
index e4645d5e3126..b2bfa4dd43f7 100644
--- a/tools/testing/selftests/ftrace/test.d/functions
+++ b/tools/testing/selftests/ftrace/test.d/functions
@@ -89,12 +89,17 @@ initialize_ftrace() { # Reset ftrace to initial-state
     reset_tracer
     reset_trigger
     reset_events_filter
+    reset_ftrace_filter
     disable_events
     echo > set_event_pid	# event tracer is always on
+    echo > set_ftrace_pid
     [ -f set_ftrace_filter ] && echo | tee set_ftrace_*
     [ -f set_graph_function ] && echo | tee set_graph_*
     [ -f stack_trace_filter ] && echo > stack_trace_filter
     [ -f kprobe_events ] && echo > kprobe_events
     [ -f uprobe_events ] && echo > uprobe_events
+    [ -f synthetic_events ] && echo > synthetic_events
+    [ -f snapshot ] && echo 0 > snapshot
+    clear_trace
     enable_tracing
 }
-- 
cgit 


From 3a96a9d0a4e985e80280357393d86ff4401eeff7 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:14:48 +0900
Subject: selftests/ftrace: Add SPDX License Identifier to template

Add SPDX License Identifier line to template file so
that someone who makes new testcase from the template
does not forgot it.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/test.d/template | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/template b/tools/testing/selftests/ftrace/test.d/template
index 5c39ceb18a0d..799da7e0b3c9 100644
--- a/tools/testing/selftests/ftrace/test.d/template
+++ b/tools/testing/selftests/ftrace/test.d/template
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL2.0
 # description: %HERE DESCRIBE WHAT THIS DOES%
 # you have to add ".tc" extention for your testcase file
 # Note that all tests are run with "errexit" option.
-- 
cgit 


From 9768cc46d39a029f7da47beea449d023b377103d Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:15:16 +0900
Subject: selftests/ftrace: Cleanup ftrace after running test

Cleanup ftrace by initialize_ftrace() after running
all test cases. This means we also don't need cleanup
ftrace on each test case, except for some special
options.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/ftracetest | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index 3ca596255eff..5c71d58febb2 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -341,6 +341,7 @@ for t in $TEST_CASES; do
     exit 1
   fi
 done
+(cd $TRACING_DIR; initialize_ftrace) # for cleanup
 
 prlog ""
 prlog "# of passed: " `echo $PASSED_CASES | wc -w`
-- 
cgit 


From e527c47081c7e2795ffc3201809de9545cc25830 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:15:44 +0900
Subject: selftests/ftrace: Remove unneeded per-test init/cleanup ftrace

Since ftracetest framework calls initialize_ftrace() right before
each test and after all tests, we don't need to init/cleanup
ftrace for each test case.
Just remove such unneeded init/cleanup code because it can
increase logfile size.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../selftests/ftrace/test.d/event/event-enable.tc        |  6 ------
 tools/testing/selftests/ftrace/test.d/event/event-pid.tc |  3 +--
 .../selftests/ftrace/test.d/event/subsystem-enable.tc    |  6 ------
 .../selftests/ftrace/test.d/event/toplevel-enable.tc     |  6 ------
 .../ftrace/test.d/ftrace/fgraph-filter-stack.tc          |  4 ----
 .../selftests/ftrace/test.d/ftrace/fgraph-filter.tc      |  9 ---------
 .../selftests/ftrace/test.d/ftrace/func-filter-pid.tc    |  6 ------
 .../ftrace/test.d/ftrace/func_event_triggers.tc          |  3 ---
 .../selftests/ftrace/test.d/ftrace/func_profiler.tc      |  4 ----
 .../ftrace/test.d/ftrace/func_set_ftrace_file.tc         | 13 -------------
 .../ftrace/test.d/ftrace/func_traceonoff_triggers.tc     | 11 -----------
 .../selftests/ftrace/test.d/kprobe/add_and_remove.tc     |  3 ---
 .../testing/selftests/ftrace/test.d/kprobe/busy_check.tc |  3 ---
 .../selftests/ftrace/test.d/kprobe/kprobe_args.tc        |  2 --
 .../selftests/ftrace/test.d/kprobe/kprobe_args_string.tc |  5 -----
 .../selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc |  5 -----
 .../selftests/ftrace/test.d/kprobe/kprobe_args_type.tc   |  4 ----
 .../selftests/ftrace/test.d/kprobe/kprobe_eventname.tc   |  5 -----
 .../selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc      |  9 ---------
 .../selftests/ftrace/test.d/kprobe/kprobe_module.tc      |  5 -----
 .../selftests/ftrace/test.d/kprobe/kretprobe_args.tc     |  2 --
 .../ftrace/test.d/kprobe/kretprobe_maxactive.tc          |  4 ----
 .../selftests/ftrace/test.d/kprobe/multiple_kprobes.tc   |  5 -----
 .../testing/selftests/ftrace/test.d/kprobe/probepoint.tc |  4 ----
 .../inter-event/trigger-extended-error-support.tc        | 12 ------------
 .../inter-event/trigger-field-variable-support.tc        | 13 -------------
 .../inter-event/trigger-inter-event-combined-hist.tc     | 13 -------------
 .../trigger/inter-event/trigger-multi-actions-accept.tc  | 14 --------------
 .../trigger/inter-event/trigger-onmatch-action-hist.tc   | 13 -------------
 .../inter-event/trigger-onmatch-onmax-action-hist.tc     | 13 -------------
 .../trigger/inter-event/trigger-onmax-action-hist.tc     | 13 -------------
 .../inter-event/trigger-synthetic-event-createremove.tc  | 12 ------------
 .../ftrace/test.d/trigger/trigger-eventonoff.tc          | 12 ------------
 .../selftests/ftrace/test.d/trigger/trigger-filter.tc    | 14 --------------
 .../selftests/ftrace/test.d/trigger/trigger-hist-mod.tc  | 12 ------------
 .../selftests/ftrace/test.d/trigger/trigger-hist.tc      | 12 ------------
 .../selftests/ftrace/test.d/trigger/trigger-multihist.tc | 16 ----------------
 .../selftests/ftrace/test.d/trigger/trigger-snapshot.tc  | 12 ------------
 .../ftrace/test.d/trigger/trigger-stacktrace.tc          | 12 ------------
 .../ftrace/test.d/trigger/trigger-trace-marker-hist.tc   | 11 -----------
 .../test.d/trigger/trigger-trace-marker-snapshot.tc      | 12 ------------
 .../trigger/trigger-trace-marker-synthetic-kernel.tc     | 12 ------------
 .../test.d/trigger/trigger-trace-marker-synthetic.tc     | 12 ------------
 .../ftrace/test.d/trigger/trigger-traceonoff.tc          | 12 ------------
 44 files changed, 1 insertion(+), 378 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/event/event-enable.tc b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
index 9daf034186f5..386dbddbdc11 100644
--- a/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
@@ -9,7 +9,6 @@ do_reset() {
 }
 
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -23,9 +22,6 @@ if [ ! -f set_event -o ! -d events/sched ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 echo 'sched:sched_switch' > set_event
 
 yield
@@ -57,6 +53,4 @@ if [ $count -ne 0 ]; then
     fail "sched_switch events should not be recorded"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/event/event-pid.tc b/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
index 132478b305c2..6dbf67544fde 100644
--- a/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
@@ -30,8 +30,7 @@ if [ ! -f set_event_pid ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
+echo 0 > options/event-fork
 
 echo 1 > events/sched/sched_switch/enable
 
diff --git a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
index 6a37a8642ee6..10eb17f161b7 100644
--- a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
@@ -9,7 +9,6 @@ do_reset() {
 }
 
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -23,9 +22,6 @@ if [ ! -f set_event -o ! -d events/sched ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 echo 'sched:*' > set_event
 
 yield
@@ -57,6 +53,4 @@ if [ $count -ne 0 ]; then
     fail "any of scheduler events should not be recorded"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
index 4e9b6e2c0219..8d55a233c1a4 100644
--- a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
@@ -8,7 +8,6 @@ do_reset() {
 }
 
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -22,9 +21,6 @@ if [ ! -f available_events -o ! -f set_event -o ! -d events ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 echo '*:*' > set_event
 
 yield
@@ -60,6 +56,4 @@ if [ $count -ne 0 ]; then
     fail "any of events should not be recorded"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc
index 1aec99d108eb..aefab0c66d54 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc
@@ -16,13 +16,9 @@ if [ ! -f set_ftrace_filter ]; then
 fi
 
 do_reset() {
-    reset_tracer
     if [ -e /proc/sys/kernel/stack_tracer_enabled ]; then
 	    echo 0 > /proc/sys/kernel/stack_tracer_enabled
     fi
-    enable_tracing
-    clear_trace
-    echo > set_ftrace_filter
 }
 
 fail() { # msg
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
index 9f8d27ca39cf..c8a5209f2119 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
@@ -9,14 +9,7 @@ if ! grep -q function_graph available_tracers; then
     exit_unsupported
 fi
 
-do_reset() {
-    reset_tracer
-    enable_tracing
-    clear_trace
-}
-
 fail() { # msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -48,6 +41,4 @@ if [ $count -eq 0 ]; then
     fail "No schedule traces found?"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
index 524ce24b3c22..970903cb7834 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
@@ -35,12 +35,6 @@ if [ $do_function_fork -eq 1 ]; then
 fi
 
 do_reset() {
-    reset_tracer
-    clear_trace
-    enable_tracing
-    echo > set_ftrace_filter
-    echo > set_ftrace_pid
-
     if [ $do_function_fork -eq 0 ]; then
 	return
     fi
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc
index 6fed4cf2db81..ca2ffd7957f9 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc
@@ -25,15 +25,12 @@ do_reset() {
 }
 
 fail() { # mesg
-    do_reset
     echo $1
     exit_fail
 }
 
 SLEEP_TIME=".1"
 
-do_reset
-
 echo "Testing function probes with events:"
 
 EVENT="sched:sched_switch"
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
index b2d5a8febfe8..dfbae637c60c 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
@@ -29,8 +29,6 @@ if [ ! -f function_profile_enabled ]; then
 fi
 
 fail() { # mesg
-    reset_tracer
-    echo > set_ftrace_filter
     echo $1
     exit_fail
 }
@@ -76,6 +74,4 @@ if ! grep -v -e '^#' -e 'schedule' trace > /dev/null; then
 	fail "no other functions besides schedule was found"
 fi
 
-reset_tracer
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
index 68e7a48f5828..51f6e6146bd9 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
@@ -15,22 +15,11 @@ if [ ! -f set_ftrace_filter ]; then
     exit_unsupported
 fi
 
-do_reset() {
-    reset_tracer
-    reset_ftrace_filter
-    disable_events
-    clear_trace
-    enable_tracing
-}
-
 fail() { # mesg
-    do_reset
     echo $1
     exit_fail
 }
 
-do_reset
-
 FILTER=set_ftrace_filter
 FUNC1="schedule"
 FUNC2="do_softirq"
@@ -165,6 +154,4 @@ test_actual
 rm $TMPDIR/expected
 rm $TMPDIR/actual
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc
index f6d9ac73268a..0c04282d33dd 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc
@@ -16,24 +16,13 @@ if [ ! -f set_ftrace_filter ]; then
     exit_unsupported
 fi
 
-do_reset() {
-    reset_ftrace_filter
-    reset_tracer
-    disable_events
-    clear_trace
-    enable_tracing
-}
-
 fail() { # mesg
-    do_reset
     echo $1
     exit_fail
 }
 
 SLEEP_TIME=".1"
 
-do_reset
-
 echo "Testing function probes with enabling disabling tracing:"
 
 cnt_trace() {
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
index 4604d2103c89..bb1eb5a7c64e 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
@@ -4,10 +4,7 @@
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 
-echo 0 > events/enable
-echo > kprobe_events
 echo p:myevent _do_fork > kprobe_events
 grep myevent kprobe_events
 test -d events/kprobes/myevent
 echo > kprobe_events
-clear_trace
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
index bbc443a9190c..442c1a8c5edf 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
@@ -4,12 +4,9 @@
 
 [ -f kprobe_events ] || exit_unsupported
 
-echo 0 > events/enable
-echo > kprobe_events
 echo p:myevent _do_fork > kprobe_events
 test -d events/kprobes/myevent
 echo 1 > events/kprobes/myevent/enable
 echo > kprobe_events && exit_fail # this must fail
 echo 0 > events/kprobes/myevent/enable
 echo > kprobe_events # this must succeed
-clear_trace
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
index 8b43c6804fc3..9578535ccd67 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
@@ -4,8 +4,6 @@
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 
-echo 0 > events/enable
-echo > kprobe_events
 echo 'p:testprobe _do_fork $stack $stack0 +0($stack)' > kprobe_events
 grep testprobe kprobe_events
 test -d events/kprobes/testprobe
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc
index 1ad70cdaf442..46e7744f8358 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc
@@ -4,9 +4,6 @@
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 
-echo 0 > events/enable
-echo > kprobe_events
-
 case `uname -m` in
 x86_64)
   ARG1=%di
@@ -44,5 +41,3 @@ echo 1 > events/kprobes/testprobe/enable
 echo "p:test _do_fork" >> kprobe_events
 grep -qe "testprobe.* arg1=\"test\" arg2=\"test\"" trace
 
-echo 0 > events/enable
-echo > kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc
index d026ff4e562f..d783a8ce0692 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc
@@ -6,9 +6,6 @@
 
 grep "x8/16/32/64" README > /dev/null || exit_unsupported # version issue
 
-echo 0 > events/enable
-echo > kprobe_events
-
 PROBEFUNC="vfs_read"
 GOODREG=
 BADREG=
@@ -100,5 +97,3 @@ test_badarg "${GOODREG}::${GOODTYPE}" "${GOODREG}:${BADTYPE}" \
 
 test_goodarg "\$comm:string" "+0(\$stack):string"
 test_badarg "\$comm:x64" "\$stack:string" "${GOODREG}:string"
-
-echo > kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
index 2a1755bfc290..37443dd23d15 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
@@ -6,10 +6,6 @@
 
 grep "x8/16/32/64" README > /dev/null || exit_unsupported # version issue
 
-echo 0 > events/enable
-echo > kprobe_events
-enable_tracing
-
 echo 'p:testprobe _do_fork $stack0:s32 $stack0:u32 $stack0:x32 $stack0:b8@4/32' > kprobe_events
 grep testprobe kprobe_events
 test -d events/kprobes/testprobe
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc
index 2724a1068cb1..3fb70e01b1fe 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc
@@ -4,9 +4,6 @@
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 
-disable_events
-echo > kprobe_events
-
 :;: "Add an event on function without name" ;:
 
 FUNC=`grep " [tT] .*vfs_read$" /proc/kallsyms | tail -n 1 | cut -f 3 -d " "`
@@ -33,5 +30,3 @@ echo "p $FUNC" > kprobe_events
 EVENT=`grep $FUNC kprobe_events | cut -f 1 -d " " | cut -f 2 -d:`
 [ "x" != "x$EVENT" ] || exit_failure
 test -d events/$EVENT || exit_failure
-
-echo > kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
index cc4cac0e60f2..492426e95e09 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
@@ -8,8 +8,6 @@ grep function available_tracers || exit_unsupported # this is configurable
 # prepare
 echo nop > current_tracer
 echo _do_fork > set_ftrace_filter
-echo 0 > events/enable
-echo > kprobe_events
 echo 'p:testprobe _do_fork' > kprobe_events
 
 # kprobe on / ftrace off
@@ -47,10 +45,3 @@ echo > trace
 ( echo "forked")
 grep testprobe trace
 ! grep '_do_fork <-' trace
-
-# cleanup
-echo nop > current_tracer
-echo > set_ftrace_filter
-echo 0 > events/kprobes/testprobe/enable
-echo > kprobe_events
-echo > trace
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc
index 1e9f75f7a30f..ec6c5fffef1e 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc
@@ -4,9 +4,6 @@
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 
-disable_events
-echo > kprobe_events
-
 :;: "Add an event on a module function without specifying event name" ;:
 
 MOD=`lsmod | head -n 2 | tail -n 1 | cut -f1 -d" "`
@@ -25,5 +22,3 @@ test -d events/kprobes/event1 || exit_failure
 
 echo "p:kprobes1/event1 $MOD:$FUNC" > kprobe_events
 test -d events/kprobes1/event1 || exit_failure
-
-echo > kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
index 321954683aaa..4c6b21e30b02 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
@@ -4,8 +4,6 @@
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 
-echo 0 > events/enable
-echo > kprobe_events
 echo 'r:testprobe2 _do_fork $retval' > kprobe_events
 grep testprobe2 kprobe_events
 test -d events/kprobes/testprobe2
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_maxactive.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_maxactive.tc
index 7c0290684c43..8e05b178519a 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_maxactive.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_maxactive.tc
@@ -5,8 +5,6 @@
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 grep -q 'r\[maxactive\]' README || exit_unsupported # this is older version
 
-echo > kprobe_events
-
 # Test if we successfully reject unknown messages
 if echo 'a:myprobeaccept inet_csk_accept' > kprobe_events; then false; else true; fi
 
@@ -37,5 +35,3 @@ echo > kprobe_events
 echo 'r10 inet_csk_accept' > kprobe_events
 grep inet_csk_accept kprobe_events
 echo > kprobe_events
-
-clear_trace
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc
index ce361b9d62cf..5862eee91e1d 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc
@@ -12,11 +12,6 @@ case `uname -m` in
   *) OFFS=0;;
 esac
 
-if [ -d events/kprobes ]; then
-  echo 0 > events/kprobes/enable
-  echo > kprobe_events
-fi
-
 N=0
 echo "Setup up kprobes on first available 256 text symbols"
 grep -i " t " /proc/kallsyms | cut -f3 -d" " | grep -v .*\\..* | \
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc b/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc
index 519d2763f5d2..a902aa0aaabc 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc
@@ -30,8 +30,6 @@ if [ `printf "%x" -1 | wc -c` != 9 ]; then
   UINT_TEST=yes
 fi
 
-echo 0 > events/enable
-echo > kprobe_events
 echo "p:testprobe ${TARGET_FUNC}" > kprobe_events
 echo "p:testprobe ${TARGET}" > kprobe_events
 echo "p:testprobe ${TARGET_FUNC}${NEXT}" > kprobe_events
@@ -39,5 +37,3 @@ echo "p:testprobe ${TARGET_FUNC}${NEXT}" > kprobe_events
 if [ "${UINT_TEST}" = yes ]; then
 ! echo "p:testprobe ${TARGET_FUNC}${OVERFLOW}" > kprobe_events
 fi
-echo > kprobe_events
-clear_trace
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc
index 2aabab363cfb..401104344593 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc
@@ -2,14 +2,7 @@
 # description: event trigger - test extended error support
 
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -24,9 +17,6 @@ if [ ! -f synthetic_events ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 echo "Test extended error support"
 echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_wakeup/trigger
 ! echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' >> events/sched/sched_wakeup/trigger 2> /dev/null
@@ -34,6 +24,4 @@ if ! grep -q "ERROR:" events/sched/sched_wakeup/hist; then
     fail "Failed to generate extended error in histogram"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc
index 7fd5b4a8f060..575af23df04e 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc
@@ -1,14 +1,7 @@
 #!/bin/sh
 # description: event trigger - test field variable support
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -23,10 +16,6 @@ if [ ! -f synthetic_events ]; then
     exit_unsupported
 fi
 
-clear_synthetic_events
-reset_tracer
-do_reset
-
 echo "Test field variable support"
 
 echo 'wakeup_latency u64 lat; pid_t pid; int prio; char comm[16]' > synthetic_events
@@ -49,6 +38,4 @@ if grep -q "synthetic_prio=prio" events/sched/sched_waking/hist; then
     fail "Failed to remove histogram with field variable"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
index c93dbe38b5df..92aef26e2631 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
@@ -1,14 +1,7 @@
 #!/bin/sh
 # description: event trigger - test inter-event combined histogram trigger
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -23,10 +16,6 @@ if [ ! -f synthetic_events ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-clear_synthetic_events
-
 echo "Test create synthetic event"
 
 echo 'waking_latency  u64 lat pid_t pid' > synthetic_events
@@ -53,6 +42,4 @@ if ! grep -q "pid:" events/synthetic/waking+wakeup_latency/hist; then
     fail "Failed to create combined histogram"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc
index c193dce611a2..4ddc546771b5 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc
@@ -1,15 +1,7 @@
 #!/bin/sh
 # description: event trigger - test multiple actions on hist trigger
 
-
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -24,10 +16,6 @@ if [ ! -f synthetic_events ]; then
     exit_unsupported
 fi
 
-clear_synthetic_events
-reset_tracer
-do_reset
-
 echo "Test multiple actions on hist trigger"
 echo 'wakeup_latency u64 lat; pid_t pid' >> synthetic_events
 TRIGGER1=events/sched/sched_wakeup/trigger
@@ -39,6 +27,4 @@ echo 'hist:keys=next_pid:onmatch(sched.sched_wakeup).wakeup_latency(sched.sched_
 echo 'hist:keys=next_pid:onmatch(sched.sched_wakeup).wakeup_latency(sched.sched_switch.$wakeup_lat,prev_pid) if next_comm=="cyclictest"' >> $TRIGGER2
 echo 'hist:keys=next_pid if next_comm=="cyclictest"' >> $TRIGGER2
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc
index e84e7d048566..1ef5dd4521f0 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc
@@ -1,14 +1,7 @@
 #!/bin/sh
 # description: event trigger - test inter-event histogram trigger onmatch action
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -23,10 +16,6 @@ if [ ! -f synthetic_events ]; then
     exit_unsupported
 fi
 
-clear_synthetic_events
-reset_tracer
-do_reset
-
 echo "Test create synthetic event"
 
 echo 'wakeup_latency  u64 lat pid_t pid char comm[16]' > synthetic_events
@@ -45,6 +34,4 @@ if ! grep -q "ping" events/synthetic/wakeup_latency/hist; then
     fail "Failed to create onmatch action inter-event histogram"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc
index 7907d8aacde3..7234683ee5e5 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc
@@ -1,14 +1,7 @@
 #!/bin/sh
 # description: event trigger - test inter-event histogram trigger onmatch-onmax action
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -23,10 +16,6 @@ if [ ! -f synthetic_events ]; then
     exit_unsupported
 fi
 
-clear_synthetic_events
-reset_tracer
-do_reset
-
 echo "Test create synthetic event"
 
 echo 'wakeup_latency  u64 lat pid_t pid char comm[16]' > synthetic_events
@@ -45,6 +34,4 @@ if [ ! grep -q "ping" events/synthetic/wakeup_latency/hist -o ! grep -q "max:" e
     fail "Failed to create onmatch-onmax action inter-event histogram"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc
index 38b7ed6242b2..55b9630a1d70 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc
@@ -1,14 +1,7 @@
 #!/bin/sh
 # description: event trigger - test inter-event histogram trigger onmax action
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -23,10 +16,6 @@ if [ ! -f synthetic_events ]; then
     exit_unsupported
 fi
 
-clear_synthetic_events
-reset_tracer
-do_reset
-
 echo "Test create synthetic event"
 
 echo 'wakeup_latency  u64 lat pid_t pid char comm[16]' > synthetic_events
@@ -43,6 +32,4 @@ if ! grep -q "max:" events/sched/sched_switch/hist; then
     fail "Failed to create onmax action inter-event histogram"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc
index cef11377dcbd..8d647fb572dd 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc
@@ -1,13 +1,7 @@
 #!/bin/sh
 # description: event trigger - test synthetic event create remove
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
 
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -22,10 +16,6 @@ if [ ! -f synthetic_events ]; then
     exit_unsupported
 fi
 
-clear_synthetic_events
-reset_tracer
-do_reset
-
 echo "Test create synthetic event"
 
 echo 'wakeup_latency  u64 lat pid_t pid char comm[16]' > synthetic_events
@@ -49,6 +39,4 @@ if [ -d events/synthetic/wakeup_latency ]; then
     fail "Failed to delete wakeup_latency synthetic event"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc
index 28cc355a3a7b..eddb51e1fbf7 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc
@@ -3,14 +3,7 @@
 # description: event trigger - test event enable/disable trigger
 # flags: instance
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -25,9 +18,6 @@ if [ ! -f events/sched/sched_process_fork/trigger ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 FEATURE=`grep enable_event events/sched/sched_process_fork/trigger`
 if [ -z "$FEATURE" ]; then
     echo "event enable/disable trigger is not supported"
@@ -61,6 +51,4 @@ echo 'enable_event:sched:sched_switch' > events/sched/sched_process_fork/trigger
 ! echo 'enable_event:sched:sched_switch' > events/sched/sched_process_fork/trigger
 ! echo 'disable_event:sched:sched_switch' > events/sched/sched_process_fork/trigger
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc
index a48e23eb8a8b..2dcc2296ebdd 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc
@@ -3,14 +3,7 @@
 # description: event trigger - test trigger filter
 # flags: instance
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -25,9 +18,6 @@ if [ ! -f events/sched/sched_process_fork/trigger ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 echo "Test trigger filter"
 echo 1 > tracing_on
 echo 'traceoff if child_pid == 0' > events/sched/sched_process_fork/trigger
@@ -54,8 +44,4 @@ echo '!traceoff' > events/sched/sched_process_fork/trigger
 echo 'traceoff if parent_pid >= 0 || child_pid >= 0' > events/sched/sched_process_fork/trigger
 echo '!traceoff' > events/sched/sched_process_fork/trigger
 
-
-
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
index 8da80efc44d8..fab4431639d3 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
@@ -3,14 +3,7 @@
 # description: event trigger - test histogram modifiers
 # flags: instance
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -30,9 +23,6 @@ if [ ! -f events/sched/sched_process_fork/hist ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 echo "Test histogram with execname modifier"
 
 echo 'hist:keys=common_pid.execname' > events/sched/sched_process_fork/trigger
@@ -71,6 +61,4 @@ for i in `seq 1 10` ; do ( echo "forked" > /dev/null); done
 grep 'bytes_req: ~ 2^[0-9]*' events/kmem/kmalloc/hist > /dev/null || \
     fail "log2 modifier on kmem/kmalloc did not work"
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc
index 449fe9ff91a2..177e8d4c4744 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc
@@ -3,14 +3,7 @@
 # description: event trigger - test histogram trigger
 # flags: instance
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -30,9 +23,6 @@ if [ ! -f events/sched/sched_process_fork/hist ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 echo "Test histogram basic tigger"
 
 echo 'hist:keys=parent_pid:vals=child_pid' > events/sched/sched_process_fork/trigger
@@ -79,6 +69,4 @@ check_inc `grep -o "child_pid:[[:space:]]*[[:digit:]]*" \
     events/sched/sched_process_fork/hist | cut -d: -f2 ` ||
     fail "sort param on sched_process_fork did not work"
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
index c5ef8b9d02b3..18fdaab9f570 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
@@ -3,14 +3,7 @@
 # description: event trigger - test multiple histogram triggers
 # flags: instance
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -30,11 +23,6 @@ if [ ! -f events/sched/sched_process_fork/hist ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
-reset_trigger
-
 echo "Test histogram multiple tiggers"
 
 echo 'hist:keys=parent_pid:vals=child_pid' > events/sched/sched_process_fork/trigger
@@ -67,8 +55,4 @@ grep test_hist events/sched/sched_process_exit/hist > /dev/null || \
 diffs=`diff events/sched/sched_process_exit/hist events/sched/sched_process_fork/hist | wc -l`
 test $diffs -eq 0 || fail "Same name histograms are not same"
 
-reset_trigger
-
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc
index ed38f0050d77..7717c0a09686 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc
@@ -2,14 +2,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # description: event trigger - test snapshot-trigger
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -29,9 +22,6 @@ if [ ! -f snapshot ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 FEATURE=`grep snapshot events/sched/sched_process_fork/trigger`
 if [ -z "$FEATURE" ]; then
     echo "snapshot trigger is not supported"
@@ -57,6 +47,4 @@ echo "Test snapshot semantic errors"
 echo "snapshot" > events/sched/sched_process_fork/trigger
 ! echo "snapshot" > events/sched/sched_process_fork/trigger
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-stacktrace.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-stacktrace.tc
index 3121d795a868..398c05c4d2a7 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-stacktrace.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-stacktrace.tc
@@ -2,14 +2,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # description: event trigger - test stacktrace-trigger
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -24,9 +17,6 @@ if [ ! -f events/sched/sched_process_fork/trigger ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 FEATURE=`grep stacktrace events/sched/sched_process_fork/trigger`
 if [ -z "$FEATURE" ]; then
     echo "stacktrace trigger is not supported"
@@ -49,6 +39,4 @@ echo "Test stacktrace semantic errors"
 echo "stacktrace" > events/sched/sched_process_fork/trigger
 ! echo "stacktrace" > events/sched/sched_process_fork/trigger
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-hist.tc
index 2acbfe2c0c0c..ab6bedb25736 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-hist.tc
@@ -3,14 +3,7 @@
 # description: trace_marker trigger - test histogram trigger
 # flags: instance
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -35,8 +28,6 @@ if [ ! -f events/ftrace/print/hist ]; then
     exit_unsupported
 fi
 
-do_reset
-
 echo "Test histogram trace_marker tigger"
 
 echo 'hist:keys=common_pid' > events/ftrace/print/trigger
@@ -44,6 +35,4 @@ for i in `seq 1 10` ; do echo "hello" > trace_marker; done
 grep 'hitcount: *10$' events/ftrace/print/hist > /dev/null || \
     fail "hist trigger did not trigger correct times on trace_marker"
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc
index 6748e8cb42d0..79ce7d51350b 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc
@@ -3,15 +3,7 @@
 # description: trace_marker trigger - test snapshot trigger
 # flags: instance
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    echo 0 > snapshot
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -54,8 +46,6 @@ test_trace() {
     done
 }
 
-do_reset
-
 echo "Test snapshot trace_marker tigger"
 
 echo 'snapshot' > events/ftrace/print/trigger
@@ -69,6 +59,4 @@ for i in `seq 1 10` ; do echo "hello >$i<" > trace_marker; done
 test_trace trace 1
 test_trace snapshot 2
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic-kernel.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic-kernel.tc
index 0a69c5d1cda8..18b4d1c2807e 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic-kernel.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic-kernel.tc
@@ -3,15 +3,7 @@
 # description: trace_marker trigger - test histogram with synthetic event against kernel event
 # flags:
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    echo > synthetic_events
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -46,8 +38,6 @@ if [ ! -f events/ftrace/print/hist ]; then
     exit_unsupported
 fi
 
-do_reset
-
 echo "Test histogram kernel event to trace_marker latency histogram trigger"
 
 echo 'latency u64 lat' > synthetic_events
@@ -63,6 +53,4 @@ grep 'hitcount: *1$' events/ftrace/print/hist > /dev/null || \
 grep 'hitcount: *1$' events/synthetic/latency/hist > /dev/null || \
     fail "hist trigger did not trigger "
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic.tc
index 3666dd6ab02a..dd262d6d0db6 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic.tc
@@ -3,15 +3,7 @@
 # description: trace_marker trigger - test histogram with synthetic event
 # flags:
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    echo > synthetic_events
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -41,8 +33,6 @@ if [ ! -f events/ftrace/print/hist ]; then
     exit_unsupported
 fi
 
-do_reset
-
 echo "Test histogram trace_marker to trace_marker latency histogram trigger"
 
 echo 'latency u64 lat' > synthetic_events
@@ -61,6 +51,4 @@ fi
 grep 'hitcount: *1$' events/synthetic/latency/hist > /dev/null || \
     fail "hist trigger did not trigger "
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-traceonoff.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-traceonoff.tc
index c59d9eb546da..d5d2dcbc9cab 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-traceonoff.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-traceonoff.tc
@@ -2,14 +2,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # description: event trigger - test traceon/off trigger
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -24,9 +17,6 @@ if [ ! -f events/sched/sched_process_fork/trigger ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 echo "Test traceoff trigger"
 echo 1 > tracing_on
 echo 'traceoff' > events/sched/sched_process_fork/trigger
@@ -54,6 +44,4 @@ echo 'traceon' > events/sched/sched_process_fork/trigger
 ! echo 'traceon' > events/sched/sched_process_fork/trigger
 ! echo 'traceoff' > events/sched/sched_process_fork/trigger
 
-do_reset
-
 exit 0
-- 
cgit 


From 2452c96e617a0ff6fb2692e55217a3fa57a7322c Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:16:13 +0900
Subject: selftests/ftrace: Fix to test kprobe $comm arg only if available

Test $comm in kprobe-event argument syntax testcase
only if it is supported on the kernel because
$comm has been introduced 4.8 kernel.
So on older stable kernel, it should be skipped.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc
index d783a8ce0692..6f0f19953193 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc
@@ -75,8 +75,11 @@ test_badarg "\$stackp" "\$stack0+10" "\$stack1-10"
 echo "r ${PROBEFUNC} \$retval" > kprobe_events
 ! echo "p ${PROBEFUNC} \$retval" > kprobe_events
 
+# $comm was introduced in 4.8, older kernels reject it.
+if grep -A1 "fetcharg:" README | grep -q '\$comm' ; then
 : "Comm access"
 test_goodarg "\$comm"
+fi
 
 : "Indirect memory access"
 test_goodarg "+0(${GOODREG})" "-0(${GOODREG})" "+10(\$stack)" \
-- 
cgit 


From 72ce3daf92ba4f5bae6e91095d40e67b367c6b2f Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:16:41 +0900
Subject: selftests/ftrace: Fix checkbashisms errors

Fix a test case to make checkbashisms clean.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc  | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc
index 79ce7d51350b..df246e505af7 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc
@@ -39,10 +39,10 @@ test_trace() {
 	fi
 	echo "testing $line for >$x<"
 	match=`echo $line | sed -e "s/>$x<//"`
-	if [ "$line" == "$match" ]; then
+	if [ "$line" = "$match" ]; then
 	    fail "$line does not have >$x< in it"
 	fi
-	let x=$x+2
+	x=$((x+2))
     done
 }
 
-- 
cgit 


From cec3adf5f57160d829a033bcb578c3dd0a90c693 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:17:10 +0900
Subject: selftests/ftrace: Use loopback address instead of localhost

Use raw loopback address instead of localhost, because
"localhost" can depend on nsswitch and in some case
we can not resolve the localhost.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/test.d/event/event-enable.tc         | 4 ----
 tools/testing/selftests/ftrace/test.d/event/event-pid.tc            | 4 ----
 tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc     | 4 ----
 tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc      | 4 ----
 tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc     | 4 ----
 tools/testing/selftests/ftrace/test.d/functions                     | 6 ++++++
 .../test.d/trigger/inter-event/trigger-field-variable-support.tc    | 2 +-
 .../test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc | 2 +-
 .../test.d/trigger/inter-event/trigger-onmatch-action-hist.tc       | 3 ++-
 .../test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc | 3 ++-
 .../ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc  | 3 ++-
 11 files changed, 14 insertions(+), 25 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/event/event-enable.tc b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
index 386dbddbdc11..dfb0d5122f7b 100644
--- a/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
@@ -13,10 +13,6 @@ fail() { #msg
     exit_fail
 }
 
-yield() {
-    ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1
-}
-
 if [ ! -f set_event -o ! -d events/sched ]; then
     echo "event tracing is not supported"
     exit_unsupported
diff --git a/tools/testing/selftests/ftrace/test.d/event/event-pid.tc b/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
index 6dbf67544fde..e28897738500 100644
--- a/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
@@ -16,10 +16,6 @@ fail() { #msg
     exit_fail
 }
 
-yield() {
-    ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1
-}
-
 if [ ! -f set_event -o ! -d events/sched ]; then
     echo "event tracing is not supported"
     exit_unsupported
diff --git a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
index 10eb17f161b7..83a8c571e93a 100644
--- a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
@@ -13,10 +13,6 @@ fail() { #msg
     exit_fail
 }
 
-yield() {
-    ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1
-}
-
 if [ ! -f set_event -o ! -d events/sched ]; then
     echo "event tracing is not supported"
     exit_unsupported
diff --git a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
index 8d55a233c1a4..84d7bda08d2a 100644
--- a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
@@ -12,10 +12,6 @@ fail() { #msg
     exit_fail
 }
 
-yield() {
-    ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1
-}
-
 if [ ! -f available_events -o ! -f set_event -o ! -d events ]; then
     echo "event tracing is not supported"
     exit_unsupported
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
index 970903cb7834..64cfcc75e3c1 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
@@ -48,10 +48,6 @@ fail() { # msg
     exit_fail
 }
 
-yield() {
-    ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1
-}
-
 do_test() {
     disable_tracing
 
diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions
index b2bfa4dd43f7..7b96e80e6b8a 100644
--- a/tools/testing/selftests/ftrace/test.d/functions
+++ b/tools/testing/selftests/ftrace/test.d/functions
@@ -103,3 +103,9 @@ initialize_ftrace() { # Reset ftrace to initial-state
     clear_trace
     enable_tracing
 }
+
+LOCALHOST=127.0.0.1
+
+yield() {
+    ping $LOCALHOST -c 1 || sleep .001 || usleep 1 || sleep 1
+}
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc
index 575af23df04e..f59b2a9a1f22 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc
@@ -23,7 +23,7 @@ echo 'hist:keys=comm:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/
 echo 'hist:keys=next_comm:wakeup_lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_waking).wakeup_latency($wakeup_lat,next_pid,sched.sched_waking.prio,next_comm) if next_comm=="ping"' > events/sched/sched_switch/trigger
 echo 'hist:keys=pid,prio,comm:vals=lat:sort=pid,prio' > events/synthetic/wakeup_latency/trigger
 
-ping localhost -c 3
+ping $LOCALHOST -c 3
 if ! grep -q "ping" events/synthetic/wakeup_latency/hist; then
     fail "Failed to create inter-event histogram"
 fi
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
index 92aef26e2631..524d9ce361e2 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
@@ -37,7 +37,7 @@ echo 'waking+wakeup_latency u64 lat; pid_t pid' >> synthetic_events
 echo 'hist:keys=pid,lat:sort=pid,lat:ww_lat=$waking_lat+$wakeup_lat:onmatch(synthetic.wakeup_latency).waking+wakeup_latency($ww_lat,pid)' >> events/synthetic/wakeup_latency/trigger
 echo 'hist:keys=pid,lat:sort=pid,lat' >> events/synthetic/waking+wakeup_latency/trigger
 
-ping localhost -c 3
+ping $LOCALHOST -c 3
 if ! grep -q "pid:" events/synthetic/waking+wakeup_latency/hist; then
     fail "Failed to create combined histogram"
 fi
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc
index 1ef5dd4521f0..39fb65b0cd9f 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc
@@ -29,7 +29,8 @@ echo "Test histogram variables,simple expression support and onmatch action"
 echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_wakeup/trigger
 echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_wakeup).wakeup_latency($wakeup_lat,next_pid,next_comm) if next_comm=="ping"' > events/sched/sched_switch/trigger
 echo 'hist:keys=comm,pid,lat:wakeup_lat=lat:sort=lat' > events/synthetic/wakeup_latency/trigger
-ping localhost -c 5
+
+ping $LOCALHOST -c 5
 if ! grep -q "ping" events/synthetic/wakeup_latency/hist; then
     fail "Failed to create onmatch action inter-event histogram"
 fi
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc
index 7234683ee5e5..81ab3939c96a 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc
@@ -29,7 +29,8 @@ echo "Test histogram variables,simple expression support and onmatch-onmax actio
 echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_wakeup/trigger
 echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_wakeup).wakeup_latency($wakeup_lat,next_pid,next_comm):onmax($wakeup_lat).save(next_comm,prev_pid,prev_prio,prev_comm) if next_comm=="ping"' >> events/sched/sched_switch/trigger
 echo 'hist:keys=comm,pid,lat:wakeup_lat=lat:sort=lat' > events/synthetic/wakeup_latency/trigger
-ping localhost -c 5
+
+ping $LOCALHOST -c 5
 if [ ! grep -q "ping" events/synthetic/wakeup_latency/hist -o ! grep -q "max:" events/sched/sched_switch/hist]; then
     fail "Failed to create onmatch-onmax action inter-event histogram"
 fi
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc
index 55b9630a1d70..1180ab5f0845 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc
@@ -27,7 +27,8 @@ echo "Test onmax action"
 
 echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' >> events/sched/sched_waking/trigger
 echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0:onmax($wakeup_lat).save(next_comm,prev_pid,prev_prio,prev_comm) if next_comm=="ping"' >> events/sched/sched_switch/trigger
-ping localhost -c 3
+
+ping $LOCALHOST -c 3
 if ! grep -q "max:" events/sched/sched_switch/hist; then
     fail "Failed to create onmax action inter-event histogram"
 fi
-- 
cgit 


From af2a0750f374935c07b8beab78d6032b1ca2218d Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:17:38 +0900
Subject: selftests/ftrace: Improve kprobe on module testcase to load/unload
 module

Improve kprobe events on module testcase to check module
load/unload with disabled/enabled events. This also change
the target module to trace_printk.ko, so it depends on
CONFIG_SAMPLE_TRACE_PRINTK=m.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/config              |  4 +++
 .../ftrace/test.d/kprobe/kprobe_module.tc          | 35 ++++++++++++++++++++--
 2 files changed, 36 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/config b/tools/testing/selftests/ftrace/config
index 07db5ab09cc7..32cf61b6bb54 100644
--- a/tools/testing/selftests/ftrace/config
+++ b/tools/testing/selftests/ftrace/config
@@ -7,3 +7,7 @@ CONFIG_HIST_TRIGGERS=y
 CONFIG_PREEMPT_TRACER=y
 CONFIG_IRQSOFF_TRACER=y
 CONFIG_PREEMPTIRQ_DELAY_TEST=m
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SAMPLES=y
+CONFIG_SAMPLE_TRACE_PRINTK=m
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc
index ec6c5fffef1e..d861bd776c5e 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc
@@ -4,11 +4,18 @@
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 
+rmmod trace-printk ||:
+if ! modprobe trace-printk ; then
+  echo "No trace-printk sample module - please make CONFIG_SAMPLE_TRACE_PRINTK=
+m"
+  exit_unresolved;
+fi
+
+MOD=trace_printk
+FUNC=trace_printk_irq_work
+
 :;: "Add an event on a module function without specifying event name" ;:
 
-MOD=`lsmod | head -n 2 | tail -n 1 | cut -f1 -d" "`
-FUNC=`grep -m 1 ".* t .*\\[$MOD\\]" /proc/kallsyms | xargs | cut -f3 -d" "`
-[ "x" != "x$MOD" -a "y" != "y$FUNC" ] || exit_unresolved
 echo "p $MOD:$FUNC" > kprobe_events
 PROBE_NAME=`echo $MOD:$FUNC | tr ".:" "_"`
 test -d events/kprobes/p_${PROBE_NAME}_0 || exit_failure
@@ -22,3 +29,25 @@ test -d events/kprobes/event1 || exit_failure
 
 echo "p:kprobes1/event1 $MOD:$FUNC" > kprobe_events
 test -d events/kprobes1/event1 || exit_failure
+
+:;: "Remove target module, but event still be there" ;:
+if ! rmmod trace-printk ; then
+  echo "Failed to unload module - please enable CONFIG_MODULE_UNLOAD"
+  exit_unresolved;
+fi
+test -d events/kprobes1/event1
+
+:;: "Check posibility to defining events on unloaded module";:
+echo "p:event2 $MOD:$FUNC" >> kprobe_events
+
+:;: "Target is gone, but we can prepare for next time";:
+echo 1 > events/kprobes1/event1/enable
+
+:;: "Load module again, which means the event1 should be recorded";:
+modprobe trace-printk
+grep "event1:" trace
+
+:;: "Remove the module again and check the event is not locked"
+rmmod trace-printk
+echo 0 > events/kprobes1/event1/enable
+echo "-:kprobes1/event1" >> kprobe_events
-- 
cgit 


From e42e5c46b07d09b6b985ceea954eae165103c7ed Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:18:06 +0900
Subject: selftests/ftrace: Improve kprobe testcase to check log data

Improve kprobe testcase to check the log data correctness
and ensure the event definition is corrctly including
argument definition.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
index 9578535ccd67..bcdecf80a8f1 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
@@ -5,10 +5,14 @@
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 
 echo 'p:testprobe _do_fork $stack $stack0 +0($stack)' > kprobe_events
-grep testprobe kprobe_events
+grep testprobe kprobe_events | grep -q 'arg1=\$stack arg2=\$stack0 arg3=+0(\$stack)'
 test -d events/kprobes/testprobe
+
 echo 1 > events/kprobes/testprobe/enable
 ( echo "forked")
+grep testprobe trace | grep '_do_fork' | \
+  grep -q 'arg1=0x[[:xdigit:]]* arg2=0x[[:xdigit:]]* arg3=0x[[:xdigit:]]*$'
+
 echo 0 > events/kprobes/testprobe/enable
 echo "-:testprobe" >> kprobe_events
 clear_trace
-- 
cgit 


From 1e51263ef4e637199b725df6811f0d2bea70156c Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:18:35 +0900
Subject: selftests/ftrace: Improve kretprobe testcase to check log data

Improve kretprobe testcase to check the log data correctness
and ensure the event definition is corrctly including
argument definition.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
index 4c6b21e30b02..ac9ab4a12e53 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
@@ -4,11 +4,16 @@
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 
+# Add new kretprobe event
 echo 'r:testprobe2 _do_fork $retval' > kprobe_events
-grep testprobe2 kprobe_events
+grep testprobe2 kprobe_events | grep -q 'arg1=\$retval'
 test -d events/kprobes/testprobe2
+
 echo 1 > events/kprobes/testprobe2/enable
 ( echo "forked")
+
+cat trace | grep testprobe2 | grep -q '<- _do_fork'
+
 echo 0 > events/kprobes/testprobe2/enable
 echo '-:testprobe2' >> kprobe_events
 clear_trace
-- 
cgit 


From 00b2f2bc3aacb658c44dcb76e004423b6a6380eb Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:19:03 +0900
Subject: selftests/ftrace: Test kprobe-event argument with various bitsize

Improve the kprobe-event with argument types testcase
to test it with various bitsize.
kprobe-event argument can be recorded in given types with
various bitsize (8, 16, 32, 64), thus the type testcase
should test the different bitsize too.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../ftrace/test.d/kprobe/kprobe_args_type.tc       | 48 ++++++++++++++--------
 1 file changed, 32 insertions(+), 16 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
index 37443dd23d15..1bcb67dcae26 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
@@ -6,29 +6,45 @@
 
 grep "x8/16/32/64" README > /dev/null || exit_unsupported # version issue
 
-echo 'p:testprobe _do_fork $stack0:s32 $stack0:u32 $stack0:x32 $stack0:b8@4/32' > kprobe_events
-grep testprobe kprobe_events
-test -d events/kprobes/testprobe
-
-echo 1 > events/kprobes/testprobe/enable
-( echo "forked")
-echo 0 > events/kprobes/testprobe/enable
-ARGS=`tail -n 1 trace | sed -e 's/.* arg1=\(.*\) arg2=\(.*\) arg3=\(.*\) arg4=\(.*\)/\1 \2 \3 \4/'`
+gen_event() { # Bitsize
+  echo "p:testprobe _do_fork \$stack0:s$1 \$stack0:u$1 \$stack0:x$1 \$stack0:b4@4/$1"
+}
 
-check_types() {
-  X1=`printf "%x" $1 | tail -c 8`
+check_types() { # s-type u-type x-type bf-type width
+  test $# -eq 5
+  CW=$5
+  CW=$((CW / 4))
+  X1=`printf "%x" $1 | tail -c ${CW}`
   X2=`printf "%x" $2`
   X3=`printf "%x" $3`
   test $X1 = $X2
   test $X2 = $X3
   test 0x$X3 = $3
 
-  B4=`printf "%02x" $4`
-  B3=`echo -n $X3 | tail -c 3 | head -c 2`
+  B4=`printf "%1x" $4`
+  B3=`printf "%03x" 0x$X3 | tail -c 2 | head -c 1`
   test $B3 = $B4
 }
-check_types $ARGS
 
-echo "-:testprobe" >> kprobe_events
-clear_trace
-test -d events/kprobes/testprobe && exit_fail || exit_pass
+for width in 64 32 16 8; do
+  : "Add new event with basic types"
+  gen_event $width > kprobe_events
+  grep testprobe kprobe_events
+  test -d events/kprobes/testprobe
+
+  : "Trace the event"
+  echo 1 > events/kprobes/testprobe/enable
+  ( echo "forked")
+  echo 0 > events/kprobes/testprobe/enable
+
+  : "Confirm the arguments is recorded in given types correctly"
+  ARGS=`grep "testprobe" trace | sed -e 's/.* arg1=\(.*\) arg2=\(.*\) arg3=\(.*\) arg4=\(.*\)/\1 \2 \3 \4/'`
+  check_types $ARGS $width
+
+  : "Clear event for next loop"
+  echo "-:testprobe" >> kprobe_events
+  clear_trace
+
+done
+
+exit_pass
-- 
cgit 


From ddbc31e63aef5e7d12f28f3ac4742420bd5b274c Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:19:31 +0900
Subject: selftests/ftrace: Check set_event_pid result

Ensure the set_event_pid shows set pid list.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/test.d/event/event-pid.tc | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/event/event-pid.tc b/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
index e28897738500..f9cb214220b1 100644
--- a/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
@@ -42,6 +42,7 @@ do_reset
 read mypid rest < /proc/self/stat
 
 echo $mypid > set_event_pid
+grep -q $mypid set_event_pid
 echo 'sched:sched_switch' > set_event
 
 yield
-- 
cgit 


From b0898e84851c96248c376897c96f3fde3ff7e3b5 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:19:59 +0900
Subject: selftests/ftrace: Add kprobe event with $comm argument testcase

Add kprobe-event with $comm argument testcase to
ftracetest. This not only checks syntax but
also checks log file.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc  | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc
new file mode 100644
index 000000000000..15c1f70fcaf9
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc
@@ -0,0 +1,17 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Kprobe event with comm arguments
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+grep -A1 "fetcharg:" README | grep -q "\$comm" || exit_unsupported # this is too old
+
+echo 'p:testprobe _do_fork comm=$comm ' > kprobe_events
+grep testprobe kprobe_events | grep -q 'comm=$comm'
+test -d events/kprobes/testprobe
+
+echo 1 > events/kprobes/testprobe/enable
+( echo "forked")
+grep testprobe trace | grep -q 'comm=".*"'
+
+exit 0
-- 
cgit 


From 32f6e5da83c7f06db7e4efbdacdbc59c16fd6ecb Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:20:28 +0900
Subject: selftests/ftrace: Add kprobe profile testcase

Add a testcase for testing kprobe_profile interface
which provides per-kprobe event hit/misshit counts.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/test.d/kprobe/profile.tc | 15 +++++++++++++++
 1 file changed, 15 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/kprobe/profile.tc

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/profile.tc b/tools/testing/selftests/ftrace/test.d/kprobe/profile.tc
new file mode 100644
index 000000000000..0384b525cdee
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/profile.tc
@@ -0,0 +1,15 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Kprobe dynamic event - adding and removing
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+! grep -q 'myevent' kprobe_profile
+echo p:myevent _do_fork > kprobe_events
+grep -q 'myevent[[:space:]]*0[[:space:]]*0$' kprobe_profile
+echo 1 > events/kprobes/myevent/enable
+( echo "forked" )
+grep -q 'myevent[[:space:]]*[[:digit:]]*[[:space:]]*0$' kprobe_profile
+echo 0 > events/kprobes/myevent/enable
+echo > kprobe_events
+! grep -q 'myevent' kprobe_profile
-- 
cgit 


From 873b4af2103fbd1bb7895be202a58878254d89bc Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:20:56 +0900
Subject: selftests/ftrace: Add kprobe-event with symbol argument test

Add a testcase for kprobe-event with @symbol argument.
Since @symbol needs to refer the kernel data symbol
(linux_proc_banner), it requires CONFIG_KALLSYMS_ALL.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/config              |  1 +
 .../ftrace/test.d/kprobe/kprobe_args_symbol.tc     | 39 ++++++++++++++++++++++
 2 files changed, 40 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_symbol.tc

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/config b/tools/testing/selftests/ftrace/config
index 32cf61b6bb54..b7ac74fcb0fa 100644
--- a/tools/testing/selftests/ftrace/config
+++ b/tools/testing/selftests/ftrace/config
@@ -11,3 +11,4 @@ CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_SAMPLES=y
 CONFIG_SAMPLE_TRACE_PRINTK=m
+CONFIG_KALLSYMS_ALL=y
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_symbol.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_symbol.tc
new file mode 100644
index 000000000000..2b6dd33f9076
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_symbol.tc
@@ -0,0 +1,39 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Kprobe event symbol argument
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+SYMBOL="linux_proc_banner"
+
+if [ ! -f /proc/kallsyms ]; then
+  echo "Can not check the target symbol - please enable CONFIG_KALLSYMS"
+  exit_unresolved
+elif ! grep "$SYMBOL\$" /proc/kallsyms; then
+  echo "Linux banner is not exported - please enable CONFIG_KALLSYMS_ALL"
+  exit_unresolved
+fi
+
+: "Test get basic types symbol argument"
+echo "p:testprobe_u _do_fork arg1=@linux_proc_banner:u64 arg2=@linux_proc_banner:u32 arg3=@linux_proc_banner:u16 arg4=@linux_proc_banner:u8" > kprobe_events
+echo "p:testprobe_s _do_fork arg1=@linux_proc_banner:s64 arg2=@linux_proc_banner:s32 arg3=@linux_proc_banner:s16 arg4=@linux_proc_banner:s8" >> kprobe_events
+if grep -q "x8/16/32/64" README; then
+  echo "p:testprobe_x _do_fork arg1=@linux_proc_banner:x64 arg2=@linux_proc_banner:x32 arg3=@linux_proc_banner:x16 arg4=@linux_proc_banner:x8" >> kprobe_events
+fi
+echo "p:testprobe_bf _do_fork arg1=@linux_proc_banner:b8@4/32" >> kprobe_events
+echo 1 > events/kprobes/enable
+(echo "forked")
+echo 0 > events/kprobes/enable
+grep "testprobe_[usx]:.* arg1=.* arg2=.* arg3=.* arg4=.*" trace
+grep "testprobe_bf:.* arg1=.*" trace
+
+: "Test get string symbol argument"
+echo "p:testprobe_str _do_fork arg1=@linux_proc_banner:string" > kprobe_events
+echo 1 > events/kprobes/enable
+(echo "forked")
+echo 0 > events/kprobes/enable
+RESULT=`grep "testprobe_str" trace | sed -e 's/.* arg1=\(.*\)/\1/'`
+
+RESULT=`echo $RESULT | sed -e 's/.* \((.*)\) \((.*)\) .*/\1 \2/'`
+ORIG=`cat /proc/version | sed -e 's/.* \((.*)\) \((.*)\) .*/\1 \2/'`
+test "$RESULT" = "$ORIG"
-- 
cgit 


From 4d23e9b4fd2e44f10d22b9d2ba1dfb3fff8cd9d5 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:21:25 +0900
Subject: selftests/ftrace: Add trace_printk sample module test

Add trace_printk sample module test. This requires to
enable trace_printk.ko module for test.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../selftests/ftrace/test.d/event/trace_printk.tc  | 27 ++++++++++++++++++++++
 1 file changed, 27 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/event/trace_printk.tc

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/event/trace_printk.tc b/tools/testing/selftests/ftrace/test.d/event/trace_printk.tc
new file mode 100644
index 000000000000..b02550b42be9
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/event/trace_printk.tc
@@ -0,0 +1,27 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Test trace_printk from module
+
+rmmod trace-printk ||:
+if ! modprobe trace-printk ; then
+  echo "No trace-printk sample module - please make CONFIG_SAMPLE_TRACE_PRINTK=m"
+  exit_unresolved;
+fi
+
+echo "Waiting for irq work"
+sleep 1
+
+grep -q ": This .* trace_bputs" trace
+grep -q ": This .* trace_puts" trace
+grep -q ": This .* trace_bprintk" trace
+grep -q ": This .* trace_printk" trace
+
+grep -q ": (irq) .* trace_bputs" trace
+grep -q ": (irq) .* trace_puts" trace
+grep -q ": (irq) .* trace_bprintk" trace
+grep -q ": (irq) .* trace_printk" trace
+
+grep -q "This is a %s that will use trace_bprintk" printk_formats
+grep -q "(irq) This is a static string that will use trace_bputs" printk_formats
+
+rmmod trace-printk ||:
-- 
cgit 


From c21ceceae94dc22f5b42c8174efa4597a0c990de Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:21:53 +0900
Subject: selftests/ftrace: Add ringbuffer size changing testcase

Add a testcase for changing ringbuffer size. This tests
not only ringbuffer size but also tests the imbalance
per-cpu buffer size change too.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../ftrace/test.d/00basic/ringbuffer_size.tc       | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_size.tc

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_size.tc b/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_size.tc
new file mode 100644
index 000000000000..ab70f0077c35
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_size.tc
@@ -0,0 +1,22 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Change the ringbuffer size
+# flags: instance
+
+rb_size_test() {
+ORIG=`cat buffer_size_kb`
+
+expr $ORIG / 2 > buffer_size_kb
+
+expr $ORIG \* 2 > buffer_size_kb
+
+echo $ORIG > buffer_size_kb
+}
+
+rb_size_test
+
+: "If per-cpu buffer is supported, imbalance it"
+if [ -d per_cpu/cpu0 ]; then
+  cd per_cpu/cpu0
+  rb_size_test
+fi
-- 
cgit 


From 5b56a07b9c461bb4db26797c82d6ac3be0f83a94 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:22:21 +0900
Subject: selftests/ftrace: Add function profiling stat testcase

Add a testcase for function profiling per-cpu statistics
interface. There is already func_profile.tc, but that is
mainly focusing on the combination of function-profiler
and function tracer. This testcase ensures trace_stat
per-cpu function statistics is correctly updated.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../ftrace/test.d/ftrace/func_profile_stat.tc      | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/ftrace/func_profile_stat.tc

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_profile_stat.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_profile_stat.tc
new file mode 100644
index 000000000000..0d501058aa75
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_profile_stat.tc
@@ -0,0 +1,22 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: ftrace - function profiling
+
+[ ! -f function_profile_enabled ] && exit_unsupported
+
+: "Enable function profile"
+echo 1 > function_profile_enabled
+
+: "Profile must be updated"
+cp trace_stat/function0 $TMPDIR/
+( echo "forked"; sleep 1 )
+: "diff returns 0 if there is no difference"
+! diff trace_stat/function0 $TMPDIR/function0
+
+echo 0 > function_profile_enabled
+
+: "Profile must NOT be updated"
+cp trace_stat/function0 $TMPDIR/
+( echo "forked"; sleep 1 )
+: "diff returns 0 if there is no difference"
+diff trace_stat/function0 $TMPDIR/function0
-- 
cgit 


From 47c509d30db4cef11a406f87279633cd21380163 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:22:49 +0900
Subject: selftests/ftrace: Add max stack tracer testcase

Add a testcase for max stack tracer, which checks basic
max stack usage tracing and its filter feature.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../ftrace/test.d/ftrace/func_stack_tracer.tc      | 39 ++++++++++++++++++++++
 1 file changed, 39 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc
new file mode 100644
index 000000000000..b414f0e3c646
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc
@@ -0,0 +1,39 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: ftrace - Max stack tracer
+# Test the basic function of max-stack usage tracing
+
+if [ ! -f stack_trace ]; then
+  echo "Max stack tracer is not supported - please make CONFIG_STACK_TRACER=y"
+  exit_unsupported
+fi
+
+echo > stack_trace_filter
+echo 0 > stack_max_size
+echo 1 > /proc/sys/kernel/stack_tracer_enabled
+
+: "Fork and wait for the first entry become !lock"
+timeout=10
+while [ $timeout -ne 0 ]; do
+  ( echo "forked" )
+  FL=`grep " 0)" stack_trace`
+  echo $FL | grep -q "lock" || break;
+  timeout=$((timeout - 1))
+done
+echo 0 > /proc/sys/kernel/stack_tracer_enabled
+
+echo '*lock*' > stack_trace_filter
+test `cat stack_trace_filter | wc -l` -eq `grep lock stack_trace_filter | wc -l`
+
+echo 0 > stack_max_size
+echo 1 > /proc/sys/kernel/stack_tracer_enabled
+
+: "Fork and always the first entry including lock"
+timeout=10
+while [ $timeout -ne 0 ]; do
+  ( echo "forked" )
+  FL=`grep " 0)" stack_trace`
+  echo $FL | grep -q "lock"
+  timeout=$((timeout - 1))
+done
+echo 0 > /proc/sys/kernel/stack_tracer_enabled
-- 
cgit 


From 7bc026d6c0328f49469a56168b50ff7a498a5810 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:23:18 +0900
Subject: selftests/ftrace: Add function filter on module testcase

Add a testcase for function filter on module.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../ftrace/test.d/ftrace/func_mod_trace.tc         | 24 ++++++++++++++++++++++
 1 file changed, 24 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc
new file mode 100644
index 000000000000..9330c873f9fe
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc
@@ -0,0 +1,24 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: ftrace - function trace on module
+
+[ ! -f set_ftrace_filter ] && exit_unsupported
+
+: "mod: allows to filter a non exist function"
+echo 'non_exist_func:mod:non_exist_module' > set_ftrace_filter
+grep -q "non_exist_func" set_ftrace_filter
+
+: "mod: on exist module"
+echo '*:mod:trace_printk' > set_ftrace_filter
+if ! modprobe trace-printk ; then
+  echo "No trace-printk sample module - please make CONFIG_SAMPLE_TRACE_PRINTK=
+m"
+  exit_unresolved;
+fi
+
+: "Wildcard should be resolved after loading module"
+grep -q "trace_printk_irq_work" set_ftrace_filter
+
+: "After removing the filter becomes empty"
+rmmod trace_printk
+test `cat set_ftrace_filter | wc -l` -eq 0
-- 
cgit 


From 174fd823397a2f19905a20bbcf47907e30e58444 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:23:46 +0900
Subject: selftests/ftrace: Add trace_pipe testcase

Add a simple testcase for trace_pipe which can consume
ringbuffer.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../selftests/ftrace/test.d/00basic/trace_pipe.tc        | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/00basic/trace_pipe.tc

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/00basic/trace_pipe.tc b/tools/testing/selftests/ftrace/test.d/00basic/trace_pipe.tc
new file mode 100644
index 000000000000..5058fbcfd90f
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/00basic/trace_pipe.tc
@@ -0,0 +1,16 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: trace_pipe and trace_marker
+# flags: instance
+
+[ ! -f trace_marker ] && exit_unsupported
+
+echo "test input 1" > trace_marker
+
+: "trace interface never consume the ring buffer"
+grep -q "test input 1" trace
+grep -q "test input 1" trace
+
+: "trace interface never consume the ring buffer"
+head -n 1 trace_pipe | grep -q "test input 1"
+! grep -q "test input 1" trace
-- 
cgit 


From 91ae08a265142d9378f7d972e00de29d5c91a2de Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:24:14 +0900
Subject: selftests/ftrace: Add stacktrace ftrace filter command testcase

Add a test case for stacktrace filter command for ftrace.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc | 12 ++++++++++++
 1 file changed, 12 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc
new file mode 100644
index 000000000000..bf72e783d014
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc
@@ -0,0 +1,12 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL2.0
+# description: ftrace - stacktrace filter command
+# flags: instance
+
+echo _do_fork:stacktrace >> set_ftrace_filter
+
+grep -q "_do_fork:stacktrace:unlimited" set_ftrace_filter
+
+(echo "forked"; sleep 1)
+
+grep -q "<stack trace>" trace
-- 
cgit 


From c1edd060b41383bb6fa76008aacf4b0b3b1c46e7 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:24:42 +0900
Subject: selftests/ftrace: Add wakeup tracer testcase

Add a testcase for wakeup tracer.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/config              |  1 +
 .../selftests/ftrace/test.d/tracer/wakeup.tc       | 25 ++++++++++++++++++++++
 2 files changed, 26 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/tracer/wakeup.tc

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/config b/tools/testing/selftests/ftrace/config
index b7ac74fcb0fa..c2c8de4fafff 100644
--- a/tools/testing/selftests/ftrace/config
+++ b/tools/testing/selftests/ftrace/config
@@ -4,6 +4,7 @@ CONFIG_FUNCTION_PROFILER=y
 CONFIG_TRACER_SNAPSHOT=y
 CONFIG_STACK_TRACER=y
 CONFIG_HIST_TRIGGERS=y
+CONFIG_SCHED_TRACER=y
 CONFIG_PREEMPT_TRACER=y
 CONFIG_IRQSOFF_TRACER=y
 CONFIG_PREEMPTIRQ_DELAY_TEST=m
diff --git a/tools/testing/selftests/ftrace/test.d/tracer/wakeup.tc b/tools/testing/selftests/ftrace/test.d/tracer/wakeup.tc
new file mode 100644
index 000000000000..e3005fa785f0
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/tracer/wakeup.tc
@@ -0,0 +1,25 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL2.0
+# description: Test wakeup tracer
+
+if ! which chrt ; then
+  echo "chrt is not found. This test requires nice command."
+  exit_unresolved
+fi
+
+if ! grep -wq "wakeup" available_tracers ; then
+  echo "wakeup tracer is not supported"
+  exit_unsupported
+fi
+
+echo wakeup > current_tracer
+echo 1 > tracing_on
+echo 0 > tracing_max_latency
+
+: "Wakeup higher priority task"
+chrt -f 5 sleep 1
+
+echo 0 > tracing_on
+grep '+ \[[[:digit:]]*\]' trace
+grep '==> \[[[:digit:]]*\]' trace
+
-- 
cgit 


From c575dea2c1a50306d382615fad06767564734e0b Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:25:11 +0900
Subject: selftests/ftrace: Add wakeup_rt tracer testcase

Add a testcase for wakeup_rt tracer. This requires chrt
command to test.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../selftests/ftrace/test.d/tracer/wakeup_rt.tc    | 25 ++++++++++++++++++++++
 1 file changed, 25 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/tracer/wakeup_rt.tc

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/tracer/wakeup_rt.tc b/tools/testing/selftests/ftrace/test.d/tracer/wakeup_rt.tc
new file mode 100644
index 000000000000..f99b5178e00a
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/tracer/wakeup_rt.tc
@@ -0,0 +1,25 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL2.0
+# description: Test wakeup RT tracer
+
+if ! which chrt ; then
+  echo "chrt is not found. This test requires chrt command."
+  exit_unresolved
+fi
+
+if ! grep -wq "wakeup_rt" available_tracers ; then
+  echo "wakeup_rt tracer is not supported"
+  exit_unsupported
+fi
+
+echo wakeup_rt > current_tracer
+echo 1 > tracing_on
+echo 0 > tracing_max_latency
+
+: "Wakeup a realtime task"
+chrt -f 5 sleep 1
+
+echo 0 > tracing_on
+grep "+ \[[[:digit:]]*\]" trace
+grep "==> \[[[:digit:]]*\]" trace
+
-- 
cgit 


From 8ffade754bdf8350f63792c6125346d77f975b41 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:25:39 +0900
Subject: selftests/ftrace: Add ftrace cpumask testcase

Add a testcase for tracing_cpumask with function tracer.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../selftests/ftrace/test.d/ftrace/func_cpumask.tc | 42 ++++++++++++++++++++++
 1 file changed, 42 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc
new file mode 100644
index 000000000000..0e6810743576
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc
@@ -0,0 +1,42 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL2.0
+# description: ftrace - function trace with cpumask
+
+if ! which nproc ; then
+  nproc() {
+    ls -d /sys/devices/system/cpu/cpu[0-9]* | wc -l
+  }
+fi
+
+NP=`nproc`
+
+if [ $NP -eq 1 ] ;then
+  echo "We can not test cpumask on UP environment"
+  exit_unresolved
+fi
+
+ORIG_CPUMASK=`cat tracing_cpumask`
+
+do_reset() {
+  echo $ORIG_CPUMASK > tracing_cpumask
+}
+
+echo 0 > tracing_on
+echo > trace
+: "Bitmask only record on CPU1"
+echo 2 > tracing_cpumask
+MASK=0x`cat tracing_cpumask`
+test `printf "%d" $MASK` -eq 2 || do_reset
+
+echo function > current_tracer
+echo 1 > tracing_on
+(echo "forked")
+echo 0 > tracing_on
+
+: "Check CPU1 events are recorded"
+grep -q -e "\[001\]" trace || do_reset
+
+: "There should be No other cpu events"
+! grep -qv -e "\[001\]" -e "^#" trace || do_reset
+
+do_reset
-- 
cgit 


From 9a244229a4b850b11952a0df79607c69b18fd8df Mon Sep 17 00:00:00 2001
From: "Shuah Khan (Samsung OSG)" <shuah@kernel.org>
Date: Wed, 26 Sep 2018 13:07:11 -0600
Subject: selftests: watchdog: fix message when /dev/watchdog open fails

When /dev/watchdog open fails, watchdog exits with "watchdog not enabled"
message. This is incorrect when open fails due to insufficient privilege.

Fix message to clearly state the reason when open fails with EACCESS when
a non-root user runs it.

Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/watchdog/watchdog-test.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c
index 6e290874b70e..e029e2017280 100644
--- a/tools/testing/selftests/watchdog/watchdog-test.c
+++ b/tools/testing/selftests/watchdog/watchdog-test.c
@@ -89,7 +89,13 @@ int main(int argc, char *argv[])
 	fd = open("/dev/watchdog", O_WRONLY);
 
 	if (fd == -1) {
-		printf("Watchdog device not enabled.\n");
+		if (errno == ENOENT)
+			printf("Watchdog device not enabled.\n");
+		else if (errno == EACCES)
+			printf("Run watchdog as root.\n");
+		else
+			printf("Watchdog device open failed %s\n",
+				strerror(errno));
 		exit(-1);
 	}
 
-- 
cgit 


From 04d5e4bd37516ad60854eb74592c7dbddd75d277 Mon Sep 17 00:00:00 2001
From: Jerry Hoemann <jerry.hoemann@hpe.com>
Date: Wed, 26 Sep 2018 15:23:08 -0600
Subject: selftests: watchdog: Fix error message.

Printf's say errno but print the string version of error.
Make consistent.

Signed-off-by: Jerry Hoemann <jerry.hoemann@hpe.com>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/watchdog/watchdog-test.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c
index e029e2017280..f1c6e025cbe5 100644
--- a/tools/testing/selftests/watchdog/watchdog-test.c
+++ b/tools/testing/selftests/watchdog/watchdog-test.c
@@ -109,7 +109,7 @@ int main(int argc, char *argv[])
 				printf("Last boot is caused by: %s.\n", (flags != 0) ?
 					"Watchdog" : "Power-On-Reset");
 			else
-				printf("WDIOC_GETBOOTSTATUS errno '%s'\n", strerror(errno));
+				printf("WDIOC_GETBOOTSTATUS error '%s'\n", strerror(errno));
 			break;
 		case 'd':
 			flags = WDIOS_DISABLECARD;
@@ -117,7 +117,7 @@ int main(int argc, char *argv[])
 			if (!ret)
 				printf("Watchdog card disabled.\n");
 			else
-				printf("WDIOS_DISABLECARD errno '%s'\n", strerror(errno));
+				printf("WDIOS_DISABLECARD error '%s'\n", strerror(errno));
 			break;
 		case 'e':
 			flags = WDIOS_ENABLECARD;
@@ -125,7 +125,7 @@ int main(int argc, char *argv[])
 			if (!ret)
 				printf("Watchdog card enabled.\n");
 			else
-				printf("WDIOS_ENABLECARD errno '%s'\n", strerror(errno));
+				printf("WDIOS_ENABLECARD error '%s'\n", strerror(errno));
 			break;
 		case 'p':
 			ping_rate = strtoul(optarg, NULL, 0);
@@ -139,7 +139,7 @@ int main(int argc, char *argv[])
 			if (!ret)
 				printf("Watchdog timeout set to %u seconds.\n", flags);
 			else
-				printf("WDIOC_SETTIMEOUT errno '%s'\n", strerror(errno));
+				printf("WDIOC_SETTIMEOUT error '%s'\n", strerror(errno));
 			break;
 		default:
 			usage(argv[0]);
-- 
cgit 


From 7514c39cf1d9433203c9b7c6674dbfa429db804b Mon Sep 17 00:00:00 2001
From: Jerry Hoemann <jerry.hoemann@hpe.com>
Date: Wed, 26 Sep 2018 15:23:09 -0600
Subject: selftests: watchdog: Add gettimeout and get|set pretimeout

Add command line arguments to call ioctl WDIOC_GETTIMEOUT,
WDIOC_GETPRETIMEOUT and WDIOC_SETPRETIMEOUT.

Signed-off-by: Jerry Hoemann <jerry.hoemann@hpe.com>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/watchdog/watchdog-test.c | 33 +++++++++++++++++++++++-
 1 file changed, 32 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c
index f1c6e025cbe5..e0f1600dc1b3 100644
--- a/tools/testing/selftests/watchdog/watchdog-test.c
+++ b/tools/testing/selftests/watchdog/watchdog-test.c
@@ -19,7 +19,7 @@
 
 int fd;
 const char v = 'V';
-static const char sopts[] = "bdehp:t:";
+static const char sopts[] = "bdehp:t:Tn:N";
 static const struct option lopts[] = {
 	{"bootstatus",          no_argument, NULL, 'b'},
 	{"disable",             no_argument, NULL, 'd'},
@@ -27,6 +27,9 @@ static const struct option lopts[] = {
 	{"help",                no_argument, NULL, 'h'},
 	{"pingrate",      required_argument, NULL, 'p'},
 	{"timeout",       required_argument, NULL, 't'},
+	{"gettimeout",          no_argument, NULL, 'T'},
+	{"pretimeout",    required_argument, NULL, 'n'},
+	{"getpretimeout",       no_argument, NULL, 'N'},
 	{NULL,                  no_argument, NULL, 0x0}
 };
 
@@ -71,9 +74,13 @@ static void usage(char *progname)
 	printf(" -h, --help          Print the help message\n");
 	printf(" -p, --pingrate=P    Set ping rate to P seconds (default %d)\n", DEFAULT_PING_RATE);
 	printf(" -t, --timeout=T     Set timeout to T seconds\n");
+	printf(" -T, --gettimeout    Get the timeout\n");
+	printf(" -n, --pretimeout=T  Set the pretimeout to T seconds\n");
+	printf(" -N, --getpretimeout Get the pretimeout\n");
 	printf("\n");
 	printf("Parameters are parsed left-to-right in real-time.\n");
 	printf("Example: %s -d -t 10 -p 5 -e\n", progname);
+	printf("Example: %s -t 12 -T -n 7 -N\n", progname);
 }
 
 int main(int argc, char *argv[])
@@ -141,6 +148,30 @@ int main(int argc, char *argv[])
 			else
 				printf("WDIOC_SETTIMEOUT error '%s'\n", strerror(errno));
 			break;
+		case 'T':
+			oneshot = 1;
+			ret = ioctl(fd, WDIOC_GETTIMEOUT, &flags);
+			if (!ret)
+				printf("WDIOC_GETTIMEOUT returns %u seconds.\n", flags);
+			else
+				printf("WDIOC_GETTIMEOUT error '%s'\n", strerror(errno));
+			break;
+		case 'n':
+			flags = strtoul(optarg, NULL, 0);
+			ret = ioctl(fd, WDIOC_SETPRETIMEOUT, &flags);
+			if (!ret)
+				printf("Watchdog pretimeout set to %u seconds.\n", flags);
+			else
+				printf("WDIOC_SETPRETIMEOUT error '%s'\n", strerror(errno));
+			break;
+		case 'N':
+			oneshot = 1;
+			ret = ioctl(fd, WDIOC_GETPRETIMEOUT, &flags);
+			if (!ret)
+				printf("WDIOC_GETPRETIMEOUT returns %u seconds.\n", flags);
+			else
+				printf("WDIOC_GETPRETIMEOUT error '%s'\n", strerror(errno));
+			break;
 		default:
 			usage(argv[0]);
 			goto end;
-- 
cgit 


From d89d08ffd2c5a9043c8df7333d9bee6c09904a8f Mon Sep 17 00:00:00 2001
From: "Shuah Khan (Samsung OSG)" <shuah@kernel.org>
Date: Wed, 26 Sep 2018 16:37:43 -0600
Subject: selftests: watchdog: Fix ioctl SET* error paths to take oneshot exit
 path

When ioctls for WDIOC_SETOPTIONS (WDIOS_DISABLECARD or WDIOS_ENABLECARD),
WDIOC_SETTIMEOUT, and WDIOC_SETPRETIMEOUT fail, the error path continues
to handler watchdog timer until user terminates it. When ioctl returns
error, it might not be safe to let the watchdog tick. The error could be
due an unsupported ioctl command or some other error.

Fix it to handle error paths as oneshot to stop the watchdog ticks and
exit right away.

Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/watchdog/watchdog-test.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c
index e0f1600dc1b3..c6bd9a68306b 100644
--- a/tools/testing/selftests/watchdog/watchdog-test.c
+++ b/tools/testing/selftests/watchdog/watchdog-test.c
@@ -123,16 +123,20 @@ int main(int argc, char *argv[])
 			ret = ioctl(fd, WDIOC_SETOPTIONS, &flags);
 			if (!ret)
 				printf("Watchdog card disabled.\n");
-			else
+			else {
 				printf("WDIOS_DISABLECARD error '%s'\n", strerror(errno));
+				oneshot = 1;
+			}
 			break;
 		case 'e':
 			flags = WDIOS_ENABLECARD;
 			ret = ioctl(fd, WDIOC_SETOPTIONS, &flags);
 			if (!ret)
 				printf("Watchdog card enabled.\n");
-			else
+			else {
 				printf("WDIOS_ENABLECARD error '%s'\n", strerror(errno));
+				oneshot = 1;
+			}
 			break;
 		case 'p':
 			ping_rate = strtoul(optarg, NULL, 0);
@@ -145,8 +149,10 @@ int main(int argc, char *argv[])
 			ret = ioctl(fd, WDIOC_SETTIMEOUT, &flags);
 			if (!ret)
 				printf("Watchdog timeout set to %u seconds.\n", flags);
-			else
+			else {
 				printf("WDIOC_SETTIMEOUT error '%s'\n", strerror(errno));
+				oneshot = 1;
+			}
 			break;
 		case 'T':
 			oneshot = 1;
@@ -161,8 +167,10 @@ int main(int argc, char *argv[])
 			ret = ioctl(fd, WDIOC_SETPRETIMEOUT, &flags);
 			if (!ret)
 				printf("Watchdog pretimeout set to %u seconds.\n", flags);
-			else
+			else {
 				printf("WDIOC_SETPRETIMEOUT error '%s'\n", strerror(errno));
+				oneshot = 1;
+			}
 			break;
 		case 'N':
 			oneshot = 1;
-- 
cgit 


From a4f222e000b3f75bd1ab763dcc289d004ff6596e Mon Sep 17 00:00:00 2001
From: Fathi Boudra <fathi.boudra@linaro.org>
Date: Fri, 7 Sep 2018 09:34:54 -0500
Subject: selftests: gpio: restructure Makefile
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch cleans up the Makefile by restructuring a couple of
things, namely:
1) change explicit paths in targets for variables
2) substitute a variable (BINARIES) for another, part of the
   selftests build system (TEST_PROGS_EXTENDED)
3) proper cleaning up of the EXTRA objects

The resulting Makefile is much more readable and manageable.

Signed-off-by: Fathi Boudra <fathi.boudra@linaro.org>
Signed-off-by: Daniel Díaz <daniel.diaz@linaro.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/gpio/Makefile | 32 +++++++++++++++-----------------
 1 file changed, 15 insertions(+), 17 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile
index 4665cdbf1a8d..a4a01ec8b2a5 100644
--- a/tools/testing/selftests/gpio/Makefile
+++ b/tools/testing/selftests/gpio/Makefile
@@ -1,28 +1,26 @@
 # SPDX-License-Identifier: GPL-2.0
 
+CFLAGS += -O2 -g -std=gnu99 -Wall -I../../../../usr/include/
+LDLIBS += -lmount -I/usr/include/libmount
+
 TEST_PROGS := gpio-mockup.sh
-TEST_FILES := gpio-mockup-sysfs.sh $(BINARIES)
-BINARIES := gpio-mockup-chardev
-EXTRA_PROGS := ../gpiogpio-event-mon ../gpiogpio-hammer ../gpiolsgpio
-EXTRA_DIRS := ../gpioinclude/
-EXTRA_OBJS := ../gpiogpio-event-mon-in.o ../gpiogpio-event-mon.o
-EXTRA_OBJS += ../gpiogpio-hammer-in.o ../gpiogpio-utils.o ../gpiolsgpio-in.o
-EXTRA_OBJS += ../gpiolsgpio.o
+TEST_FILES := gpio-mockup-sysfs.sh
+TEST_PROGS_EXTENDED := gpio-mockup-chardev
+
+GPIODIR := ../../../gpio
+GPIOOBJ := gpio-utils.o
 
 include ../lib.mk
 
-all: $(BINARIES)
+all: $(TEST_PROGS_EXTENDED)
 
 override define CLEAN
-	$(RM) $(BINARIES) $(EXTRA_PROGS) $(EXTRA_OBJS)
-	$(RM) -r $(EXTRA_DIRS)
+	$(RM) $(TEST_PROGS_EXTENDED)
+	$(MAKE) -C $(GPIODIR) clean
 endef
 
-CFLAGS += -O2 -g -std=gnu99 -Wall -I../../../../usr/include/
-LDLIBS += -lmount -I/usr/include/libmount
-
-$(BINARIES):| khdr
-$(BINARIES): ../../../gpio/gpio-utils.o
+$(TEST_PROGS_EXTENDED):| khdr
+$(TEST_PROGS_EXTENDED): $(GPIODIR)/$(GPIOOBJ)
 
-../../../gpio/gpio-utils.o:
-	make ARCH=$(ARCH) CROSS_COMPILE=$(CROSS_COMPILE) -C ../../../gpio
+$(GPIODIR)/$(GPIOOBJ):
+	$(MAKE) -C $(GPIODIR)
-- 
cgit 


From 8c7f6316fccf38ca45d33ed658cc4813837b6294 Mon Sep 17 00:00:00 2001
From: Daniel Díaz <daniel.diaz@linaro.org>
Date: Fri, 7 Sep 2018 09:34:55 -0500
Subject: selftests: gpio: Fix OUTPUT directory in Makefile
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When simply running `make' from the selftests top dir, this
error shows up:

  cc -O2 -g -std=gnu99 -Wall -I../../../../usr/include/ -I/usr/include/libmount -I/usr/include/blkid -I/usr/include/uuid    gpio-mockup-chardev.c ../../../gpio/gpio-utils.o  -lmount -o gpio-mockup-chardev
  cc: error: ../../../gpio/gpio-utils.o: No such file or directory
  <builtin>: recipe for target 'gpio-mockup-chardev' failed
  make[1]: *** [gpio-mockup-chardev] Error 1

because the output directory is set to "selftests/gpio" and
all binaries built from ../../../gpio/ end up there. In fact,
they appear as, exempli gratia:
* gpiogpio-event-mon
* gpiogpio-hammer
* gpioinclude/
* gpiolsgpio
which is wrong, as it's missing a directory separator
somewhere.

This patch sets straight the output directory when building
../../../gpio/ so that binaries don't cross paths.

Signed-off-by: Daniel Díaz <daniel.diaz@linaro.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/gpio/Makefile | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile
index a4a01ec8b2a5..46648427d537 100644
--- a/tools/testing/selftests/gpio/Makefile
+++ b/tools/testing/selftests/gpio/Makefile
@@ -7,7 +7,7 @@ TEST_PROGS := gpio-mockup.sh
 TEST_FILES := gpio-mockup-sysfs.sh
 TEST_PROGS_EXTENDED := gpio-mockup-chardev
 
-GPIODIR := ../../../gpio
+GPIODIR := $(realpath ../../../gpio)
 GPIOOBJ := gpio-utils.o
 
 include ../lib.mk
@@ -16,11 +16,11 @@ all: $(TEST_PROGS_EXTENDED)
 
 override define CLEAN
 	$(RM) $(TEST_PROGS_EXTENDED)
-	$(MAKE) -C $(GPIODIR) clean
+	$(MAKE) -C $(GPIODIR) OUTPUT=$(GPIODIR)/ clean
 endef
 
 $(TEST_PROGS_EXTENDED):| khdr
 $(TEST_PROGS_EXTENDED): $(GPIODIR)/$(GPIOOBJ)
 
 $(GPIODIR)/$(GPIOOBJ):
-	$(MAKE) -C $(GPIODIR)
+	$(MAKE) OUTPUT=$(GPIODIR)/ -C $(GPIODIR)
-- 
cgit 


From 717da97e94a9ba590632624992a9f79d53d3579b Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Sat, 13 Oct 2018 16:41:05 +0100
Subject: kvm: selftests: fix spelling mistake "Insufficent" -> "Insufficient"

Trivial fix to spelling mistake in TEST_ASSERT message text

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/kvm/lib/kvm_util.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 6fd8c089cafc..a56ef6b187bb 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -123,7 +123,7 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 
 	/* Allocate memory. */
 	vm = calloc(1, sizeof(*vm));
-	TEST_ASSERT(vm != NULL, "Insufficent Memory");
+	TEST_ASSERT(vm != NULL, "Insufficient Memory");
 
 	vm->mode = mode;
 	vm_open(vm, perm);
-- 
cgit 


From 8f381ac4d3210025891c5397e744fd4c771481d7 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Fri, 12 Oct 2018 22:21:06 -0400
Subject: selftests/ftrace: Add color to the PASS / FAIL results

Now that ftracetest has over 80 tests, it is difficult to simply scroll
up the console window to find the failed tests when it reports just two
tests have failed. In order to make this stand out better, have the
color of the word "PASS" be green, "FAIL" and "XFAIL" be red, and all
other results be blue. This helps tremendously in quickly spotting the
failed tests by just scrolling up the console window.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/ftracetest | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index 5c71d58febb2..4946b2edfcff 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -153,7 +153,7 @@ else
 fi
 
 prlog() { # messages
-  [ -z "$LOG_FILE" ] && echo "$@" || echo "$@" | tee -a $LOG_FILE
+  [ -z "$LOG_FILE" ] && echo -e "$@" || echo -e "$@" | tee -a $LOG_FILE
 }
 catlog() { #file
   [ -z "$LOG_FILE" ] && cat $1 || cat $1 | tee -a $LOG_FILE
@@ -195,37 +195,37 @@ test_on_instance() { # testfile
 eval_result() { # sigval
   case $1 in
     $PASS)
-      prlog "	[PASS]"
+      prlog "	[\e[32mPASS\e[30m]"
       PASSED_CASES="$PASSED_CASES $CASENO"
       return 0
     ;;
     $FAIL)
-      prlog "	[FAIL]"
+      prlog "	[\e[31mFAIL\e[30m]"
       FAILED_CASES="$FAILED_CASES $CASENO"
       return 1 # this is a bug.
     ;;
     $UNRESOLVED)
-      prlog "	[UNRESOLVED]"
+      prlog "	[\e[34mUNRESOLVED\e[30m]"
       UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO"
       return 1 # this is a kind of bug.. something happened.
     ;;
     $UNTESTED)
-      prlog "	[UNTESTED]"
+      prlog "	[\e[34mUNTESTED\e[30m]"
       UNTESTED_CASES="$UNTESTED_CASES $CASENO"
       return 0
     ;;
     $UNSUPPORTED)
-      prlog "	[UNSUPPORTED]"
+      prlog "	[\e[34mUNSUPPORTED\e[30m]"
       UNSUPPORTED_CASES="$UNSUPPORTED_CASES $CASENO"
       return $UNSUPPORTED_RESULT # depends on use case
     ;;
     $XFAIL)
-      prlog "	[XFAIL]"
+      prlog "	[\e[31mXFAIL\e[30m]"
       XFAILED_CASES="$XFAILED_CASES $CASENO"
       return 0
     ;;
     *)
-      prlog "	[UNDEFINED]"
+      prlog "	[\e[34mUNDEFINED\e[30m]"
       UNDEFINED_CASES="$UNDEFINED_CASES $CASENO"
       return 1 # this must be a test bug
     ;;
-- 
cgit 


From fb363e2d20351e1d16629df19e7bce1a31b3227a Mon Sep 17 00:00:00 2001
From: Andrea Parri <andrea.parri@amarulasolutions.com>
Date: Tue, 16 Oct 2018 16:13:46 +0200
Subject: selftests: kvm: Fix -Wformat warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fixes the following warnings:

dirty_log_test.c: In function ‘help’:
dirty_log_test.c:216:9: warning: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 2 has type ‘int’ [-Wformat=]
  printf(" -i: specify iteration counts (default: %"PRIu64")\n",
         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from include/test_util.h:18:0,
                 from dirty_log_test.c:16:
/usr/include/inttypes.h:105:34: note: format string is defined here
 # define PRIu64  __PRI64_PREFIX "u"
dirty_log_test.c:218:9: warning: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 2 has type ‘int’ [-Wformat=]
  printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from include/test_util.h:18:0,
                 from dirty_log_test.c:16:
/usr/include/inttypes.h:105:34: note: format string is defined here
 # define PRIu64  __PRI64_PREFIX "u"

Signed-off-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/kvm/dirty_log_test.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 0c2cdc105f96..a9c4b5e21d7e 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -31,9 +31,9 @@
 /* How many pages to dirty for each guest loop */
 #define  TEST_PAGES_PER_LOOP            1024
 /* How many host loops to run (one KVM_GET_DIRTY_LOG for each loop) */
-#define  TEST_HOST_LOOP_N               32
+#define  TEST_HOST_LOOP_N               32UL
 /* Interval for each host loop (ms) */
-#define  TEST_HOST_LOOP_INTERVAL        10
+#define  TEST_HOST_LOOP_INTERVAL        10UL
 
 /*
  * Guest variables.  We use these variables to share data between host
-- 
cgit 


From 0387662d1b6c5ad2950d8e94d5e380af3f15c05c Mon Sep 17 00:00:00 2001
From: Peng Hao <peng.hao2@zte.com.cn>
Date: Fri, 12 Oct 2018 03:53:50 +0800
Subject: selftests: fix warning: "_GNU_SOURCE" redefined

Makefile contains -D_GNU_SOURCE. remove define "_GNU_SOURCE"
in c files.

Signed-off-by: Peng Hao <peng.hao2@zte.com.cn>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/proc/fd-001-lookup.c  | 2 +-
 tools/testing/selftests/proc/fd-003-kthread.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/proc/fd-001-lookup.c b/tools/testing/selftests/proc/fd-001-lookup.c
index a2010dfb2110..60d7948e7124 100644
--- a/tools/testing/selftests/proc/fd-001-lookup.c
+++ b/tools/testing/selftests/proc/fd-001-lookup.c
@@ -14,7 +14,7 @@
  * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
  */
 // Test /proc/*/fd lookup.
-#define _GNU_SOURCE
+
 #undef NDEBUG
 #include <assert.h>
 #include <dirent.h>
diff --git a/tools/testing/selftests/proc/fd-003-kthread.c b/tools/testing/selftests/proc/fd-003-kthread.c
index 1d659d55368c..dc591f97b63d 100644
--- a/tools/testing/selftests/proc/fd-003-kthread.c
+++ b/tools/testing/selftests/proc/fd-003-kthread.c
@@ -14,7 +14,7 @@
  * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
  */
 // Test that /proc/$KERNEL_THREAD/fd/ is empty.
-#define _GNU_SOURCE
+
 #undef NDEBUG
 #include <sys/syscall.h>
 #include <assert.h>
-- 
cgit 


From 8096fbcf55c0da535bdca9adab982ec0c5affb67 Mon Sep 17 00:00:00 2001
From: Daniel Díaz <daniel.diaz@linaro.org>
Date: Tue, 16 Oct 2018 12:02:20 -0500
Subject: selftests/ftrace: Use colored output when available
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If test is being directly executed (with stdout opened on the
terminal) and the terminal capabilities indicate enough
colors, then use the existing scheme of green, red, and blue
to show when tests pass, fail or end in a different way.

When running the tests redirecting the stdout, for instance,
to a file, then colors are not shown, thus producing a more
readable output.

Signed-off-by: Daniel Díaz <daniel.diaz@linaro.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/ftracetest | 29 ++++++++++++++++++++++-------
 1 file changed, 22 insertions(+), 7 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index 4946b2edfcff..d987bbec675f 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -152,6 +152,21 @@ else
   date > $LOG_FILE
 fi
 
+# Define text colors
+# Check available colors on the terminal, if any
+ncolors=`tput colors 2>/dev/null`
+color_reset=
+color_red=
+color_green=
+color_blue=
+# If stdout exists and number of colors is eight or more, use them
+if [ -t 1 -a "$ncolors" -a "$ncolors" -ge 8 ]; then
+  color_reset="\e[0m"
+  color_red="\e[31m"
+  color_green="\e[32m"
+  color_blue="\e[34m"
+fi
+
 prlog() { # messages
   [ -z "$LOG_FILE" ] && echo -e "$@" || echo -e "$@" | tee -a $LOG_FILE
 }
@@ -195,37 +210,37 @@ test_on_instance() { # testfile
 eval_result() { # sigval
   case $1 in
     $PASS)
-      prlog "	[\e[32mPASS\e[30m]"
+      prlog "	[${color_green}PASS${color_reset}]"
       PASSED_CASES="$PASSED_CASES $CASENO"
       return 0
     ;;
     $FAIL)
-      prlog "	[\e[31mFAIL\e[30m]"
+      prlog "	[${color_red}FAIL${color_reset}]"
       FAILED_CASES="$FAILED_CASES $CASENO"
       return 1 # this is a bug.
     ;;
     $UNRESOLVED)
-      prlog "	[\e[34mUNRESOLVED\e[30m]"
+      prlog "	[${color_blue}UNRESOLVED${color_reset}]"
       UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO"
       return 1 # this is a kind of bug.. something happened.
     ;;
     $UNTESTED)
-      prlog "	[\e[34mUNTESTED\e[30m]"
+      prlog "	[${color_blue}UNTESTED${color_reset}]"
       UNTESTED_CASES="$UNTESTED_CASES $CASENO"
       return 0
     ;;
     $UNSUPPORTED)
-      prlog "	[\e[34mUNSUPPORTED\e[30m]"
+      prlog "	[${color_blue}UNSUPPORTED${color_reset}]"
       UNSUPPORTED_CASES="$UNSUPPORTED_CASES $CASENO"
       return $UNSUPPORTED_RESULT # depends on use case
     ;;
     $XFAIL)
-      prlog "	[\e[31mXFAIL\e[30m]"
+      prlog "	[${color_red}XFAIL${color_reset}]"
       XFAILED_CASES="$XFAILED_CASES $CASENO"
       return 0
     ;;
     *)
-      prlog "	[\e[34mUNDEFINED\e[30m]"
+      prlog "	[${color_blue}UNDEFINED${color_reset}]"
       UNDEFINED_CASES="$UNDEFINED_CASES $CASENO"
       return 1 # this must be a test bug
     ;;
-- 
cgit 


From f73581f8d9a367459f36e6a4ef0065997ab14c75 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 17 Oct 2018 12:33:23 +0900
Subject: selftests/ftrace: Strip escape sequences for log file

Strip escape sequences from the stream to the ftracetest
summary log file. Note that all test-case results are
dumped raw in each file.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/ftracetest | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index d987bbec675f..75244db70331 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -167,11 +167,18 @@ if [ -t 1 -a "$ncolors" -a "$ncolors" -ge 8 ]; then
   color_blue="\e[34m"
 fi
 
+strip_esc() {
+  # busybox sed implementation doesn't accept "\x1B", so use [:cntrl:] instead.
+  sed -E "s/[[:cntrl:]]\[([0-9]{1,2}(;[0-9]{1,2})?)?[m|K]//g"
+}
+
 prlog() { # messages
-  [ -z "$LOG_FILE" ] && echo -e "$@" || echo -e "$@" | tee -a $LOG_FILE
+  echo -e "$@"
+  [ "$LOG_FILE" ] && echo -e "$@" | strip_esc >> $LOG_FILE
 }
 catlog() { #file
-  [ -z "$LOG_FILE" ] && cat $1 || cat $1 | tee -a $LOG_FILE
+  cat $1
+  [ "$LOG_FILE" ] && cat $1 | strip_esc >> $LOG_FILE
 }
 prlog "=== Ftrace unit tests ==="
 
-- 
cgit 


From 4ed591c8ab44e711e56b8e021ffaf4f407c045f5 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 24 Oct 2018 13:58:39 -0700
Subject: net/ipv6: Allow onlink routes to have a device mismatch if it is the
 default route

The intent of ip6_route_check_nh_onlink is to make sure the gateway
given for an onlink route is not actually on a connected route for
a different interface (e.g., 2001:db8:1::/64 is on dev eth1 and then
an onlink route has a via 2001:db8:1::1 dev eth2). If the gateway
lookup hits the default route then it most likely will be a different
interface than the onlink route which is ok.

Update ip6_route_check_nh_onlink to disregard the device mismatch
if the gateway lookup hits the default route. Turns out the existing
onlink tests are passing because there is no default route or it is
an unreachable default, so update the onlink tests to have a default
route other than unreachable.

Fixes: fc1e64e1092f6 ("net/ipv6: Add support for onlink flag")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c                                |  2 ++
 tools/testing/selftests/net/fib-onlink-tests.sh | 14 +++++++-------
 2 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'tools/testing')

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e3226284e480..2a7423c39456 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2745,6 +2745,8 @@ static int ip6_route_check_nh_onlink(struct net *net,
 	grt = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0);
 	if (grt) {
 		if (!grt->dst.error &&
+		    /* ignore match if it is the default route */
+		    grt->from && !ipv6_addr_any(&grt->from->fib6_dst.addr) &&
 		    (grt->rt6i_flags & flags || dev != grt->dst.dev)) {
 			NL_SET_ERR_MSG(extack,
 				       "Nexthop has invalid gateway or device mismatch");
diff --git a/tools/testing/selftests/net/fib-onlink-tests.sh b/tools/testing/selftests/net/fib-onlink-tests.sh
index 3991ad1a368d..864f865eee55 100755
--- a/tools/testing/selftests/net/fib-onlink-tests.sh
+++ b/tools/testing/selftests/net/fib-onlink-tests.sh
@@ -167,8 +167,8 @@ setup()
 	# add vrf table
 	ip li add ${VRF} type vrf table ${VRF_TABLE}
 	ip li set ${VRF} up
-	ip ro add table ${VRF_TABLE} unreachable default
-	ip -6 ro add table ${VRF_TABLE} unreachable default
+	ip ro add table ${VRF_TABLE} unreachable default metric 8192
+	ip -6 ro add table ${VRF_TABLE} unreachable default metric 8192
 
 	# create test interfaces
 	ip li add ${NETIFS[p1]} type veth peer name ${NETIFS[p2]}
@@ -185,20 +185,20 @@ setup()
 	for n in 1 3 5 7; do
 		ip li set ${NETIFS[p${n}]} up
 		ip addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]}
-		ip addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]}
+		ip addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad
 	done
 
 	# move peer interfaces to namespace and add addresses
 	for n in 2 4 6 8; do
 		ip li set ${NETIFS[p${n}]} netns ${PEER_NS} up
 		ip -netns ${PEER_NS} addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]}
-		ip -netns ${PEER_NS} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]}
+		ip -netns ${PEER_NS} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad
 	done
 
-	set +e
+	ip -6 ro add default via ${V6ADDRS[p3]/::[0-9]/::64}
+	ip -6 ro add table ${VRF_TABLE} default via ${V6ADDRS[p7]/::[0-9]/::64}
 
-	# let DAD complete - assume default of 1 probe
-	sleep 1
+	set +e
 }
 
 cleanup()
-- 
cgit 


From a3f49d97c22022666fb94101454520a7adacaf08 Mon Sep 17 00:00:00 2001
From: Naresh Kamboju <naresh.kamboju@linaro.org>
Date: Thu, 25 Oct 2018 20:17:28 +0530
Subject: selftests/bpf: add config fragments BPF_STREAM_PARSER and XDP_SOCKETS

BPF sockmap and hashmap are dependent on CONFIG_BPF_STREAM_PARSER and
xskmap is dependent on CONFIG_XDP_SOCKETS

Signed-off-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/config | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index dd49df5e2df4..7f90d3645af8 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -20,3 +20,5 @@ CONFIG_VXLAN=y
 CONFIG_GENEVE=y
 CONFIG_NET_CLS_FLOWER=m
 CONFIG_LWTUNNEL=y
+CONFIG_BPF_STREAM_PARSER=y
+CONFIG_XDP_SOCKETS=y
-- 
cgit 


From 36641ad61db5ce9befd5eb0071abb36eaff16cfc Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 24 Oct 2018 22:05:43 +0200
Subject: bpf: fix test suite to enable all unpriv program types

Given BPF_PROG_TYPE_CGROUP_SKB program types are also valid in an
unprivileged setting, lets not omit these tests and potentially
have issues fall through the cracks. Make this more obvious by
adding a small test_as_unpriv() helper.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_verifier.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 769d68a48f30..8e1a79d2792c 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -4891,6 +4891,8 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
+		.result_unpriv = REJECT,
+		.errstr_unpriv = "R3 pointer comparison prohibited",
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
 	},
 	{
@@ -5146,6 +5148,7 @@ static struct bpf_test tests[] = {
 		.fixup_cgroup_storage = { 1 },
 		.result = REJECT,
 		.errstr = "get_local_storage() doesn't support non-zero flags",
+		.errstr_unpriv = "R2 leaks addr into helper function",
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
 	},
 	{
@@ -5261,6 +5264,7 @@ static struct bpf_test tests[] = {
 		.fixup_percpu_cgroup_storage = { 1 },
 		.result = REJECT,
 		.errstr = "get_local_storage() doesn't support non-zero flags",
+		.errstr_unpriv = "R2 leaks addr into helper function",
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
 	},
 	{
@@ -14050,6 +14054,13 @@ static void get_unpriv_disabled()
 	fclose(fd);
 }
 
+static bool test_as_unpriv(struct bpf_test *test)
+{
+	return !test->prog_type ||
+	       test->prog_type == BPF_PROG_TYPE_SOCKET_FILTER ||
+	       test->prog_type == BPF_PROG_TYPE_CGROUP_SKB;
+}
+
 static int do_test(bool unpriv, unsigned int from, unsigned int to)
 {
 	int i, passes = 0, errors = 0, skips = 0;
@@ -14060,10 +14071,10 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to)
 		/* Program types that are not supported by non-root we
 		 * skip right away.
 		 */
-		if (!test->prog_type && unpriv_disabled) {
+		if (test_as_unpriv(test) && unpriv_disabled) {
 			printf("#%d/u %s SKIP\n", i, test->descr);
 			skips++;
-		} else if (!test->prog_type) {
+		} else if (test_as_unpriv(test)) {
 			if (!unpriv)
 				set_admin(false);
 			printf("#%d/u %s ", i, test->descr);
-- 
cgit 


From ab21c1b5f799395232b838e98981cfed6d647905 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 24 Oct 2018 22:05:44 +0200
Subject: bpf: disallow direct packet access for unpriv in cg_skb

Commit b39b5f411dcf ("bpf: add cg_skb_is_valid_access for
BPF_PROG_TYPE_CGROUP_SKB") added support for returning pkt pointers
for direct packet access. Given this program type is allowed for both
unprivileged and privileged users, we shouldn't allow unprivileged
ones to use it, e.g. besides others one reason would be to avoid any
potential speculation on the packet test itself, thus guard this for
root only.

Fixes: b39b5f411dcf ("bpf: add cg_skb_is_valid_access for BPF_PROG_TYPE_CGROUP_SKB")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/core/filter.c                           | 6 ++++++
 tools/testing/selftests/bpf/test_verifier.c | 2 +-
 2 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/net/core/filter.c b/net/core/filter.c
index 35c6933c2622..3fdddfa9a0fd 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5496,7 +5496,13 @@ static bool cg_skb_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, data_meta):
 	case bpf_ctx_range(struct __sk_buff, flow_keys):
 		return false;
+	case bpf_ctx_range(struct __sk_buff, data):
+	case bpf_ctx_range(struct __sk_buff, data_end):
+		if (!capable(CAP_SYS_ADMIN))
+			return false;
+		break;
 	}
+
 	if (type == BPF_WRITE) {
 		switch (off) {
 		case bpf_ctx_range(struct __sk_buff, mark):
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 8e1a79d2792c..36f3d3009d1a 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -4892,7 +4892,7 @@ static struct bpf_test tests[] = {
 		},
 		.result = ACCEPT,
 		.result_unpriv = REJECT,
-		.errstr_unpriv = "R3 pointer comparison prohibited",
+		.errstr_unpriv = "invalid bpf_context access off=76 size=4",
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
 	},
 	{
-- 
cgit 


From 48dc0ef19044bfb69193302fbe3a834e3331b7ae Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Mon, 22 Oct 2018 18:16:26 -0300
Subject: selftests/powerpc: Fix ptrace tm failure

Test ptrace-tm-spd-gpr fails on current kernel (4.19) due to a segmentation
fault that happens on the child process prior to setting cptr[2] = 1. This
causes the parent process to wait forever at 'while (!pptr[2])' and the test to
be killed by the test harness framework by timeout, thus, failing.

The segmentation fault happens because of a inline assembly being
generated as:

	0x10000355c <tm_spd_gpr+492>    lfs    f0, 0(0)

This is reading memory position 0x0 and causing the segmentation fault.

This code is being generated by ASM_LOAD_FPR_SINGLE_PRECISION(flt_4), where
flt_4 is passed to the inline assembly block as:

	[flt_4] "r" (&d)

Since the inline assembly 'r' constraint means any GPR, gpr0 is being
chosen, thus causing this issue when issuing a Load Floating-Point Single
instruction.

This patch simply changes the constraint to 'b', which specify that this
register will be used as base, and r0 is not allowed to be used, avoiding
this issue.

Other than that, removing flt_2 register from the input operands, since it
is not used by the inline assembly code at all.

Cc: stable@vger.kernel.org
Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Segher Boessenkool <segher@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c
index 327fa943c7f3..dbdffa2e2c82 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c
@@ -67,8 +67,8 @@ trans:
 		"3: ;"
 		: [res] "=r" (result), [texasr] "=r" (texasr)
 		: [gpr_1]"i"(GPR_1), [gpr_2]"i"(GPR_2), [gpr_4]"i"(GPR_4),
-		[sprn_texasr] "i" (SPRN_TEXASR), [flt_1] "r" (&a),
-		[flt_2] "r" (&b), [flt_4] "r" (&d)
+		[sprn_texasr] "i" (SPRN_TEXASR), [flt_1] "b" (&a),
+		[flt_4] "b" (&d)
 		: "memory", "r5", "r6", "r7",
 		"r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15",
 		"r16", "r17", "r18", "r19", "r20", "r21", "r22", "r23",
-- 
cgit 


From 58cfbac25b1fd2b76f94566aed28a3662b0ff8c6 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Fri, 26 Oct 2018 04:24:15 +1100
Subject: Revert "selftests/powerpc: Fix out-of-tree build errors"

This reverts commit d8a2fe29d3c97038c8efcc328d5e7940c5310565.

That commit, by me, fixed the out of tree build errors by causing some
of the tests not to build at all.
---
 tools/testing/selftests/powerpc/cache_shape/Makefile   | 2 ++
 tools/testing/selftests/powerpc/ptrace/Makefile        | 2 ++
 tools/testing/selftests/powerpc/signal/Makefile        | 2 ++
 tools/testing/selftests/powerpc/switch_endian/Makefile | 1 -
 4 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/powerpc/cache_shape/Makefile b/tools/testing/selftests/powerpc/cache_shape/Makefile
index 62e947ca9921..ede4d3dae750 100644
--- a/tools/testing/selftests/powerpc/cache_shape/Makefile
+++ b/tools/testing/selftests/powerpc/cache_shape/Makefile
@@ -1,6 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 TEST_PROGS := cache_shape
 
+all: $(TEST_PROGS)
+
 $(TEST_PROGS): ../harness.c ../utils.c
 
 top_srcdir = ../../../../..
diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile
index 6ac71b629276..9b35ca8e8f13 100644
--- a/tools/testing/selftests/powerpc/ptrace/Makefile
+++ b/tools/testing/selftests/powerpc/ptrace/Makefile
@@ -7,6 +7,8 @@ TEST_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \
 top_srcdir = ../../../../..
 include ../../lib.mk
 
+all: $(TEST_PROGS)
+
 CFLAGS += -m64 -I../../../../../usr/include -I../tm -mhtm -fno-pie
 
 ptrace-pkey core-pkey: child.h
diff --git a/tools/testing/selftests/powerpc/signal/Makefile b/tools/testing/selftests/powerpc/signal/Makefile
index d34a7c7710db..1fca25c6ace0 100644
--- a/tools/testing/selftests/powerpc/signal/Makefile
+++ b/tools/testing/selftests/powerpc/signal/Makefile
@@ -1,6 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 TEST_PROGS := signal signal_tm
 
+all: $(TEST_PROGS)
+
 $(TEST_PROGS): ../harness.c ../utils.c signal.S
 
 CFLAGS += -maltivec
diff --git a/tools/testing/selftests/powerpc/switch_endian/Makefile b/tools/testing/selftests/powerpc/switch_endian/Makefile
index bdc081afedb0..fcd2dcb8972b 100644
--- a/tools/testing/selftests/powerpc/switch_endian/Makefile
+++ b/tools/testing/selftests/powerpc/switch_endian/Makefile
@@ -8,7 +8,6 @@ EXTRA_CLEAN = $(OUTPUT)/*.o $(OUTPUT)/check-reversed.S
 top_srcdir = ../../../../..
 include ../../lib.mk
 
-$(OUTPUT)/switch_endian_test: ASFLAGS += -I $(OUTPUT)
 $(OUTPUT)/switch_endian_test: $(OUTPUT)/check-reversed.S
 
 $(OUTPUT)/check-reversed.o: $(OUTPUT)/check.o
-- 
cgit 


From 439de0d7443789c688428429874b8e27f693c00e Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Fri, 26 Oct 2018 15:09:09 -0700
Subject: userfaultfd: selftest: cleanup help messages

Firstly, the help in the comment region is obsolete, now we support
three parameters.  Since at it, change it and move it into the help
message of the program.

Also, the help messages dumped here and there is obsolete too.  Use a
single usage() helper.

Link: http://lkml.kernel.org/r/20180930074259.18229-2-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Acked-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Zi Yan <zi.yan@cs.rutgers.edu>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Shaohua Li <shli@fb.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/vm/userfaultfd.c | 46 +++++++++++++++++++-------------
 1 file changed, 28 insertions(+), 18 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index 7b8171e3128a..5ff3a4f9173e 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -34,18 +34,6 @@
  * per-CPU threads 1 by triggering userfaults inside
  * pthread_mutex_lock will also verify the atomicity of the memory
  * transfer (UFFDIO_COPY).
- *
- * The program takes two parameters: the amounts of physical memory in
- * megabytes (MiB) of the area and the number of bounces to execute.
- *
- * # 100MiB 99999 bounces
- * ./userfaultfd 100 99999
- *
- * # 1GiB 99 bounces
- * ./userfaultfd 1000 99
- *
- * # 10MiB-~6GiB 999 bounces, continue forever unless an error triggers
- * while ./userfaultfd $[RANDOM % 6000 + 10] 999; do true; done
  */
 
 #define _GNU_SOURCE
@@ -115,6 +103,30 @@ pthread_attr_t attr;
 				 ~(unsigned long)(sizeof(unsigned long long) \
 						  -  1)))
 
+const char *examples =
+    "# Run anonymous memory test on 100MiB region with 99999 bounces:\n"
+    "./userfaultfd anon 100 99999\n\n"
+    "# Run share memory test on 1GiB region with 99 bounces:\n"
+    "./userfaultfd shmem 1000 99\n\n"
+    "# Run hugetlb memory test on 256MiB region with 50 bounces (using /dev/hugepages/hugefile):\n"
+    "./userfaultfd hugetlb 256 50 /dev/hugepages/hugefile\n\n"
+    "# Run the same hugetlb test but using shmem:\n"
+    "./userfaultfd hugetlb_shared 256 50 /dev/hugepages/hugefile\n\n"
+    "# 10MiB-~6GiB 999 bounces anonymous test, "
+    "continue forever unless an error triggers\n"
+    "while ./userfaultfd anon $[RANDOM % 6000 + 10] 999; do true; done\n\n";
+
+static void usage(void)
+{
+	fprintf(stderr, "\nUsage: ./userfaultfd <test type> <MiB> <bounces> "
+		"[hugetlbfs_file]\n\n");
+	fprintf(stderr, "Supported <test type>: anon, hugetlb, "
+		"hugetlb_shared, shmem\n\n");
+	fprintf(stderr, "Examples:\n\n");
+	fprintf(stderr, examples);
+	exit(1);
+}
+
 static int anon_release_pages(char *rel_area)
 {
 	int ret = 0;
@@ -1272,8 +1284,7 @@ static void sigalrm(int sig)
 int main(int argc, char **argv)
 {
 	if (argc < 4)
-		fprintf(stderr, "Usage: <test type> <MiB> <bounces> [hugetlbfs_file]\n"),
-				exit(1);
+		usage();
 
 	if (signal(SIGALRM, sigalrm) == SIG_ERR)
 		fprintf(stderr, "failed to arm SIGALRM"), exit(1);
@@ -1286,20 +1297,19 @@ int main(int argc, char **argv)
 		nr_cpus;
 	if (!nr_pages_per_cpu) {
 		fprintf(stderr, "invalid MiB\n");
-		fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1);
+		usage();
 	}
 
 	bounces = atoi(argv[3]);
 	if (bounces <= 0) {
 		fprintf(stderr, "invalid bounces\n");
-		fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1);
+		usage();
 	}
 	nr_pages = nr_pages_per_cpu * nr_cpus;
 
 	if (test_type == TEST_HUGETLB) {
 		if (argc < 5)
-			fprintf(stderr, "Usage: hugetlb <MiB> <bounces> <hugetlbfs_file>\n"),
-				exit(1);
+			usage();
 		huge_fd = open(argv[4], O_CREAT | O_RDWR, 0755);
 		if (huge_fd < 0) {
 			fprintf(stderr, "Open of %s failed", argv[3]);
-- 
cgit 


From 04d877319e2aa3895cc7998adb32de0967d3927b Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Fri, 26 Oct 2018 15:09:13 -0700
Subject: userfaultfd: selftest: generalize read and poll

We do very similar things in read and poll modes, but we're copying the
codes around.  Share the codes properly on reading the message and
handling the page fault to make the code cleaner.  Meanwhile this solves
previous mismatch of behaviors between the two modes on that the old code:

- did not check EAGAIN case in read() mode
- ignored BOUNCE_VERIFY check in read() mode

Link: http://lkml.kernel.org/r/20180930074259.18229-3-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Acked-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Zi Yan <zi.yan@cs.rutgers.edu>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Shaohua Li <shli@fb.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/vm/userfaultfd.c | 77 ++++++++++++++++++--------------
 1 file changed, 43 insertions(+), 34 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index 5ff3a4f9173e..7a8c6937cc67 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -451,6 +451,43 @@ static int copy_page(int ufd, unsigned long offset)
 	return __copy_page(ufd, offset, false);
 }
 
+static int uffd_read_msg(int ufd, struct uffd_msg *msg)
+{
+	int ret = read(uffd, msg, sizeof(*msg));
+
+	if (ret != sizeof(*msg)) {
+		if (ret < 0) {
+			if (errno == EAGAIN)
+				return 1;
+			else
+				perror("blocking read error"), exit(1);
+		} else {
+			fprintf(stderr, "short read\n"), exit(1);
+		}
+	}
+
+	return 0;
+}
+
+/* Return 1 if page fault handled by us; otherwise 0 */
+static int uffd_handle_page_fault(struct uffd_msg *msg)
+{
+	unsigned long offset;
+
+	if (msg->event != UFFD_EVENT_PAGEFAULT)
+		fprintf(stderr, "unexpected msg event %u\n",
+			msg->event), exit(1);
+
+	if (bounces & BOUNCE_VERIFY &&
+	    msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
+		fprintf(stderr, "unexpected write fault\n"), exit(1);
+
+	offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst;
+	offset &= ~(page_size-1);
+
+	return copy_page(uffd, offset);
+}
+
 static void *uffd_poll_thread(void *arg)
 {
 	unsigned long cpu = (unsigned long) arg;
@@ -458,7 +495,6 @@ static void *uffd_poll_thread(void *arg)
 	struct uffd_msg msg;
 	struct uffdio_register uffd_reg;
 	int ret;
-	unsigned long offset;
 	char tmp_chr;
 	unsigned long userfaults = 0;
 
@@ -482,25 +518,15 @@ static void *uffd_poll_thread(void *arg)
 		if (!(pollfd[0].revents & POLLIN))
 			fprintf(stderr, "pollfd[0].revents %d\n",
 				pollfd[0].revents), exit(1);
-		ret = read(uffd, &msg, sizeof(msg));
-		if (ret < 0) {
-			if (errno == EAGAIN)
-				continue;
-			perror("nonblocking read error"), exit(1);
-		}
+		if (uffd_read_msg(uffd, &msg))
+			continue;
 		switch (msg.event) {
 		default:
 			fprintf(stderr, "unexpected msg event %u\n",
 				msg.event), exit(1);
 			break;
 		case UFFD_EVENT_PAGEFAULT:
-			if (msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
-				fprintf(stderr, "unexpected write fault\n"), exit(1);
-			offset = (char *)(unsigned long)msg.arg.pagefault.address -
-				area_dst;
-			offset &= ~(page_size-1);
-			if (copy_page(uffd, offset))
-				userfaults++;
+			userfaults += uffd_handle_page_fault(&msg);
 			break;
 		case UFFD_EVENT_FORK:
 			close(uffd);
@@ -528,8 +554,6 @@ static void *uffd_read_thread(void *arg)
 {
 	unsigned long *this_cpu_userfaults;
 	struct uffd_msg msg;
-	unsigned long offset;
-	int ret;
 
 	this_cpu_userfaults = (unsigned long *) arg;
 	*this_cpu_userfaults = 0;
@@ -538,24 +562,9 @@ static void *uffd_read_thread(void *arg)
 	/* from here cancellation is ok */
 
 	for (;;) {
-		ret = read(uffd, &msg, sizeof(msg));
-		if (ret != sizeof(msg)) {
-			if (ret < 0)
-				perror("blocking read error"), exit(1);
-			else
-				fprintf(stderr, "short read\n"), exit(1);
-		}
-		if (msg.event != UFFD_EVENT_PAGEFAULT)
-			fprintf(stderr, "unexpected msg event %u\n",
-				msg.event), exit(1);
-		if (bounces & BOUNCE_VERIFY &&
-		    msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
-			fprintf(stderr, "unexpected write fault\n"), exit(1);
-		offset = (char *)(unsigned long)msg.arg.pagefault.address -
-			 area_dst;
-		offset &= ~(page_size-1);
-		if (copy_page(uffd, offset))
-			(*this_cpu_userfaults)++;
+		if (uffd_read_msg(uffd, &msg))
+			continue;
+		(*this_cpu_userfaults) += uffd_handle_page_fault(&msg);
 	}
 	return (void *)NULL;
 }
-- 
cgit 


From 7eaa8c969efa77127de9a05856eef9e5d22cf487 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Fri, 26 Oct 2018 15:09:17 -0700
Subject: userfaultfd: selftest: recycle lock threads first

Now we recycle the uffd servicing threads earlier than the lock threads.
It might happen that when the lock thread is still blocked at a pthread
mutex lock while the servicing thread has already quitted for the cpu so
the lock thread will be blocked forever and hang the test program.  To fix
the possible race, recycle the lock threads first.

This never happens with current missing-only tests, but when I start to
run the write-protection tests (the feature is not yet posted upstream) it
happens every time of the run possibly because in that new test we'll need
to service two page faults for each lock operation.

Link: http://lkml.kernel.org/r/20180930074259.18229-4-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Acked-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Zi Yan <zi.yan@cs.rutgers.edu>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Shaohua Li <shli@fb.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/vm/userfaultfd.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index 7a8c6937cc67..5d1db824f73a 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -626,6 +626,12 @@ static int stress(unsigned long *userfaults)
 	if (uffd_test_ops->release_pages(area_src))
 		return 1;
 
+
+	finished = 1;
+	for (cpu = 0; cpu < nr_cpus; cpu++)
+		if (pthread_join(locking_threads[cpu], NULL))
+			return 1;
+
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		char c;
 		if (bounces & BOUNCE_POLL) {
@@ -643,11 +649,6 @@ static int stress(unsigned long *userfaults)
 		}
 	}
 
-	finished = 1;
-	for (cpu = 0; cpu < nr_cpus; cpu++)
-		if (pthread_join(locking_threads[cpu], NULL))
-			return 1;
-
 	return 0;
 }
 
-- 
cgit 


From 26db3d09d9e1963c9db77cb275bd2d36e56ef57a Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Fri, 26 Oct 2018 15:09:52 -0700
Subject: mm/gup_benchmark.c: time put_page()

We'd like to measure time to unpin user pages, so this adds a second
benchmark timer on put_page, separate from get_page.

Adding the field breaks this ioctl ABI, but should be okay since this an
in-tree kernel selftest.

[akpm@linux-foundation.org: add expansion to struct gup_benchmark for future use]
Link: http://lkml.kernel.org/r/20181010195605.10689-1-keith.busch@intel.com
Signed-off-by: Keith Busch <keith.busch@intel.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/gup_benchmark.c                         | 9 +++++++--
 tools/testing/selftests/vm/gup_benchmark.c | 6 ++++--
 2 files changed, 11 insertions(+), 4 deletions(-)

(limited to 'tools/testing')

diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c
index 7405c9d89d65..e6aff102373b 100644
--- a/mm/gup_benchmark.c
+++ b/mm/gup_benchmark.c
@@ -8,11 +8,13 @@
 #define GUP_FAST_BENCHMARK	_IOWR('g', 1, struct gup_benchmark)
 
 struct gup_benchmark {
-	__u64 delta_usec;
+	__u64 get_delta_usec;
+	__u64 put_delta_usec;
 	__u64 addr;
 	__u64 size;
 	__u32 nr_pages_per_call;
 	__u32 flags;
+	__u64 expansion[10];	/* For future use */
 };
 
 static int __gup_benchmark_ioctl(unsigned int cmd,
@@ -48,14 +50,17 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
 	}
 	end_time = ktime_get();
 
-	gup->delta_usec = ktime_us_delta(end_time, start_time);
+	gup->get_delta_usec = ktime_us_delta(end_time, start_time);
 	gup->size = addr - gup->addr;
 
+	start_time = ktime_get();
 	for (i = 0; i < nr_pages; i++) {
 		if (!pages[i])
 			break;
 		put_page(pages[i]);
 	}
+	end_time = ktime_get();
+	gup->put_delta_usec = ktime_us_delta(end_time, start_time);
 
 	kvfree(pages);
 	return 0;
diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
index 36df55132036..bdcb97acd0ac 100644
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -17,7 +17,8 @@
 #define GUP_FAST_BENCHMARK	_IOWR('g', 1, struct gup_benchmark)
 
 struct gup_benchmark {
-	__u64 delta_usec;
+	__u64 get_delta_usec;
+	__u64 put_delta_usec;
 	__u64 addr;
 	__u64 size;
 	__u32 nr_pages_per_call;
@@ -81,7 +82,8 @@ int main(int argc, char **argv)
 		if (ioctl(fd, GUP_FAST_BENCHMARK, &gup))
 			perror("ioctl"), exit(1);
 
-		printf("Time: %lld us", gup.delta_usec);
+		printf("Time: get:%lld put:%lld us", gup.get_delta_usec,
+			gup.put_delta_usec);
 		if (gup.size != size)
 			printf(", truncated (size: %lld)", gup.size);
 		printf("\n");
-- 
cgit 


From 714a3a1ebafe6e23af55a5c694c308f4044a7e00 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Fri, 26 Oct 2018 15:09:56 -0700
Subject: mm/gup_benchmark.c: add additional pinning methods

Provide new gup benchmark ioctl commands to run different user page
pinning methods, get_user_pages_longterm() and get_user_pages(), in
addition to the existing get_user_pages_fast().

Link: http://lkml.kernel.org/r/20181010195605.10689-2-keith.busch@intel.com
Signed-off-by: Keith Busch <keith.busch@intel.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/gup_benchmark.c                         | 28 ++++++++++++++++++++++++++--
 tools/testing/selftests/vm/gup_benchmark.c | 13 +++++++++++--
 2 files changed, 37 insertions(+), 4 deletions(-)

(limited to 'tools/testing')

diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c
index e6aff102373b..debf11388a60 100644
--- a/mm/gup_benchmark.c
+++ b/mm/gup_benchmark.c
@@ -6,6 +6,8 @@
 #include <linux/debugfs.h>
 
 #define GUP_FAST_BENCHMARK	_IOWR('g', 1, struct gup_benchmark)
+#define GUP_LONGTERM_BENCHMARK	_IOWR('g', 2, struct gup_benchmark)
+#define GUP_BENCHMARK		_IOWR('g', 3, struct gup_benchmark)
 
 struct gup_benchmark {
 	__u64 get_delta_usec;
@@ -43,7 +45,23 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
 			nr = (next - addr) / PAGE_SIZE;
 		}
 
-		nr = get_user_pages_fast(addr, nr, gup->flags & 1, pages + i);
+		switch (cmd) {
+		case GUP_FAST_BENCHMARK:
+			nr = get_user_pages_fast(addr, nr, gup->flags & 1,
+						 pages + i);
+			break;
+		case GUP_LONGTERM_BENCHMARK:
+			nr = get_user_pages_longterm(addr, nr, gup->flags & 1,
+						     pages + i, NULL);
+			break;
+		case GUP_BENCHMARK:
+			nr = get_user_pages(addr, nr, gup->flags & 1, pages + i,
+					    NULL);
+			break;
+		default:
+			return -1;
+		}
+
 		if (nr <= 0)
 			break;
 		i += nr;
@@ -72,8 +90,14 @@ static long gup_benchmark_ioctl(struct file *filep, unsigned int cmd,
 	struct gup_benchmark gup;
 	int ret;
 
-	if (cmd != GUP_FAST_BENCHMARK)
+	switch (cmd) {
+	case GUP_FAST_BENCHMARK:
+	case GUP_LONGTERM_BENCHMARK:
+	case GUP_BENCHMARK:
+		break;
+	default:
 		return -EINVAL;
+	}
 
 	if (copy_from_user(&gup, (void __user *)arg, sizeof(gup)))
 		return -EFAULT;
diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
index bdcb97acd0ac..c2f785ded9b9 100644
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -15,6 +15,8 @@
 #define PAGE_SIZE sysconf(_SC_PAGESIZE)
 
 #define GUP_FAST_BENCHMARK	_IOWR('g', 1, struct gup_benchmark)
+#define GUP_LONGTERM_BENCHMARK	_IOWR('g', 2, struct gup_benchmark)
+#define GUP_BENCHMARK		_IOWR('g', 3, struct gup_benchmark)
 
 struct gup_benchmark {
 	__u64 get_delta_usec;
@@ -30,9 +32,10 @@ int main(int argc, char **argv)
 	struct gup_benchmark gup;
 	unsigned long size = 128 * MB;
 	int i, fd, opt, nr_pages = 1, thp = -1, repeats = 1, write = 0;
+	int cmd = GUP_FAST_BENCHMARK;
 	char *p;
 
-	while ((opt = getopt(argc, argv, "m:r:n:tT")) != -1) {
+	while ((opt = getopt(argc, argv, "m:r:n:tTLU")) != -1) {
 		switch (opt) {
 		case 'm':
 			size = atoi(optarg) * MB;
@@ -49,6 +52,12 @@ int main(int argc, char **argv)
 		case 'T':
 			thp = 0;
 			break;
+		case 'L':
+			cmd = GUP_LONGTERM_BENCHMARK;
+			break;
+		case 'U':
+			cmd = GUP_BENCHMARK;
+			break;
 		case 'w':
 			write = 1;
 		default:
@@ -79,7 +88,7 @@ int main(int argc, char **argv)
 
 	for (i = 0; i < repeats; i++) {
 		gup.size = size;
-		if (ioctl(fd, GUP_FAST_BENCHMARK, &gup))
+		if (ioctl(fd, cmd, &gup))
 			perror("ioctl"), exit(1);
 
 		printf("Time: get:%lld put:%lld us", gup.get_delta_usec,
-- 
cgit 


From 319e0bec1aecb36c5ac6d23812af487ff2c8f47f Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Fri, 26 Oct 2018 15:09:59 -0700
Subject: tools/testing/selftests/vm/gup_benchmark.c: fix 'write' flag usage

If the '-w' parameter was provided, the benchmark would exit due to a
mssing 'break'.

Link: http://lkml.kernel.org/r/20181010195605.10689-3-keith.busch@intel.com
Signed-off-by: Keith Busch <keith.busch@intel.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/vm/gup_benchmark.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
index c2f785ded9b9..b2082df8beb4 100644
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -60,6 +60,7 @@ int main(int argc, char **argv)
 			break;
 		case 'w':
 			write = 1;
+			break;
 		default:
 			return -1;
 		}
-- 
cgit 


From aeb85ed4f41a8c0f5c4606d69f5da75e2348d984 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Fri, 26 Oct 2018 15:10:02 -0700
Subject: tools/testing/selftests/vm/gup_benchmark.c: allow user specified file

Allow a user to specify a file to map by adding a new option, '-f',
providing a means to test various file backings.

If not specified, the benchmark will use a private mapping of /dev/zero,
which produces an anonymous mapping as before.

[akpm@linux-foundation.org: avoid using comma operator]
Link: http://lkml.kernel.org/r/20181010195605.10689-4-keith.busch@intel.com
Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/vm/gup_benchmark.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
index b2082df8beb4..43a2d60e0e93 100644
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -31,11 +31,12 @@ int main(int argc, char **argv)
 {
 	struct gup_benchmark gup;
 	unsigned long size = 128 * MB;
-	int i, fd, opt, nr_pages = 1, thp = -1, repeats = 1, write = 0;
+	int i, fd, filed, opt, nr_pages = 1, thp = -1, repeats = 1, write = 0;
 	int cmd = GUP_FAST_BENCHMARK;
+	char *file = "/dev/zero";
 	char *p;
 
-	while ((opt = getopt(argc, argv, "m:r:n:tTLU")) != -1) {
+	while ((opt = getopt(argc, argv, "m:r:n:f:tTLU")) != -1) {
 		switch (opt) {
 		case 'm':
 			size = atoi(optarg) * MB;
@@ -61,11 +62,20 @@ int main(int argc, char **argv)
 		case 'w':
 			write = 1;
 			break;
+		case 'f':
+			file = optarg;
+			break;
 		default:
 			return -1;
 		}
 	}
 
+	filed = open(file, O_RDWR|O_CREAT);
+	if (filed < 0) {
+		perror("open");
+		exit(filed);
+	}
+
 	gup.nr_pages_per_call = nr_pages;
 	gup.flags = write;
 
@@ -73,8 +83,7 @@ int main(int argc, char **argv)
 	if (fd == -1)
 		perror("open"), exit(1);
 
-	p = mmap(NULL, size, PROT_READ | PROT_WRITE,
-			MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	p = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE, filed, 0);
 	if (p == MAP_FAILED)
 		perror("mmap"), exit(1);
 	gup.addr = (unsigned long)p;
-- 
cgit 


From 0dd8666afb99c71d124e0c2abf1ad7d934a242a0 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Fri, 26 Oct 2018 15:10:08 -0700
Subject: tools/testing/selftests/vm/gup_benchmark.c: add MAP_SHARED option

Add a new benchmark option, -S, to request MAP_SHARED.  This can be used
to compare with MAP_PRIVATE, or for files that require this option, like
dax.

Link: http://lkml.kernel.org/r/20181010195605.10689-5-keith.busch@intel.com
Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/vm/gup_benchmark.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
index 43a2d60e0e93..5c8e4cb1441a 100644
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -32,11 +32,11 @@ int main(int argc, char **argv)
 	struct gup_benchmark gup;
 	unsigned long size = 128 * MB;
 	int i, fd, filed, opt, nr_pages = 1, thp = -1, repeats = 1, write = 0;
-	int cmd = GUP_FAST_BENCHMARK;
+	int cmd = GUP_FAST_BENCHMARK, flags = MAP_PRIVATE;
 	char *file = "/dev/zero";
 	char *p;
 
-	while ((opt = getopt(argc, argv, "m:r:n:f:tTLU")) != -1) {
+	while ((opt = getopt(argc, argv, "m:r:n:f:tTLUS")) != -1) {
 		switch (opt) {
 		case 'm':
 			size = atoi(optarg) * MB;
@@ -65,6 +65,10 @@ int main(int argc, char **argv)
 		case 'f':
 			file = optarg;
 			break;
+		case 'S':
+			flags &= ~MAP_PRIVATE;
+			flags |= MAP_SHARED;
+			break;
 		default:
 			return -1;
 		}
@@ -83,7 +87,7 @@ int main(int argc, char **argv)
 	if (fd == -1)
 		perror("open"), exit(1);
 
-	p = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE, filed, 0);
+	p = mmap(NULL, size, PROT_READ | PROT_WRITE, flags, filed, 0);
 	if (p == MAP_FAILED)
 		perror("mmap"), exit(1);
 	gup.addr = (unsigned long)p;
-- 
cgit 


From 3821b76c3cdb5f2c5ef1b082de79829e8ff50a7d Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Fri, 26 Oct 2018 15:10:12 -0700
Subject: tools/testing/selftests/vm/gup_benchmark.c: add MAP_HUGETLB option

Add a new option '-H' to the gup benchmark to help understand how hugetlb
mapping pages compare with the default.

Link: http://lkml.kernel.org/r/20181010195605.10689-6-keith.busch@intel.com
Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/vm/gup_benchmark.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
index 5c8e4cb1441a..880b96fc80d4 100644
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -36,7 +36,7 @@ int main(int argc, char **argv)
 	char *file = "/dev/zero";
 	char *p;
 
-	while ((opt = getopt(argc, argv, "m:r:n:f:tTLUS")) != -1) {
+	while ((opt = getopt(argc, argv, "m:r:n:f:tTLUSH")) != -1) {
 		switch (opt) {
 		case 'm':
 			size = atoi(optarg) * MB;
@@ -69,6 +69,9 @@ int main(int argc, char **argv)
 			flags &= ~MAP_PRIVATE;
 			flags |= MAP_SHARED;
 			break;
+		case 'H':
+			flags |= MAP_HUGETLB;
+			break;
 		default:
 			return -1;
 		}
-- 
cgit 


From 91cbacc34512e37c9bb89125ca4b224ca6459245 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Fri, 26 Oct 2018 15:10:48 -0700
Subject: tools/testing/selftests/vm/map_fixed_noreplace.c: add test for
 MAP_FIXED_NOREPLACE

Add a test for MAP_FIXED_NOREPLACE, based on some code originally by Jann
Horn.  This would have caught the overlap bug reported by Daniel Micay.

I originally suggested to Michal that we create MAP_FIXED_NOREPLACE, but
instead of writing a selftest I spent my time bike-shedding whether it
should be called MAP_FIXED_SAFE/NOCLOBBER/WEAK/NEW ..  mea culpa.

Link: http://lkml.kernel.org/r/20181013133929.28653-1-mpe@ellerman.id.au
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Khalid Aziz <khalid.aziz@oracle.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Jann Horn <jannh@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Abdul Haleem <abdhalee@linux.vnet.ibm.com>
Cc: Joel Stanley <joel@jms.id.au>
Cc: Jason Evans <jasone@google.com>
Cc: David Goldblatt <davidtgoldblatt@gmail.com>
Cc: Daniel Micay <danielmicay@gmail.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/vm/.gitignore            |   1 +
 tools/testing/selftests/vm/Makefile              |   1 +
 tools/testing/selftests/vm/map_fixed_noreplace.c | 206 +++++++++++++++++++++++
 3 files changed, 208 insertions(+)
 create mode 100644 tools/testing/selftests/vm/map_fixed_noreplace.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index af5ff83f6d7f..31b3c98b6d34 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -13,3 +13,4 @@ mlock-random-test
 virtual_address_range
 gup_benchmark
 va_128TBswitch
+map_fixed_noreplace
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index e94b7b14bcb2..6e67e726e5a5 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -12,6 +12,7 @@ TEST_GEN_FILES += gup_benchmark
 TEST_GEN_FILES += hugepage-mmap
 TEST_GEN_FILES += hugepage-shm
 TEST_GEN_FILES += map_hugetlb
+TEST_GEN_FILES += map_fixed_noreplace
 TEST_GEN_FILES += map_populate
 TEST_GEN_FILES += mlock-random-test
 TEST_GEN_FILES += mlock2-tests
diff --git a/tools/testing/selftests/vm/map_fixed_noreplace.c b/tools/testing/selftests/vm/map_fixed_noreplace.c
new file mode 100644
index 000000000000..d91bde511268
--- /dev/null
+++ b/tools/testing/selftests/vm/map_fixed_noreplace.c
@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Test that MAP_FIXED_NOREPLACE works.
+ *
+ * Copyright 2018, Jann Horn <jannh@google.com>
+ * Copyright 2018, Michael Ellerman, IBM Corporation.
+ */
+
+#include <sys/mman.h>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#ifndef MAP_FIXED_NOREPLACE
+#define MAP_FIXED_NOREPLACE 0x100000
+#endif
+
+#define BASE_ADDRESS	(256ul * 1024 * 1024)
+
+
+static void dump_maps(void)
+{
+	char cmd[32];
+
+	snprintf(cmd, sizeof(cmd), "cat /proc/%d/maps", getpid());
+	system(cmd);
+}
+
+int main(void)
+{
+	unsigned long flags, addr, size, page_size;
+	char *p;
+
+	page_size = sysconf(_SC_PAGE_SIZE);
+
+	flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED_NOREPLACE;
+
+	// Check we can map all the areas we need below
+	errno = 0;
+	addr = BASE_ADDRESS;
+	size = 5 * page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p == MAP_FAILED) {
+		dump_maps();
+		printf("Error: couldn't map the space we need for the test\n");
+		return 1;
+	}
+
+	errno = 0;
+	if (munmap((void *)addr, 5 * page_size) != 0) {
+		dump_maps();
+		printf("Error: munmap failed!?\n");
+		return 1;
+	}
+	printf("unmap() successful\n");
+
+	errno = 0;
+	addr = BASE_ADDRESS + page_size;
+	size = 3 * page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p == MAP_FAILED) {
+		dump_maps();
+		printf("Error: first mmap() failed unexpectedly\n");
+		return 1;
+	}
+
+	/*
+	 * Exact same mapping again:
+	 *   base |  free  | new
+	 *     +1 | mapped | new
+	 *     +2 | mapped | new
+	 *     +3 | mapped | new
+	 *     +4 |  free  | new
+	 */
+	errno = 0;
+	addr = BASE_ADDRESS;
+	size = 5 * page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p != MAP_FAILED) {
+		dump_maps();
+		printf("Error:1: mmap() succeeded when it shouldn't have\n");
+		return 1;
+	}
+
+	/*
+	 * Second mapping contained within first:
+	 *
+	 *   base |  free  |
+	 *     +1 | mapped |
+	 *     +2 | mapped | new
+	 *     +3 | mapped |
+	 *     +4 |  free  |
+	 */
+	errno = 0;
+	addr = BASE_ADDRESS + (2 * page_size);
+	size = page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p != MAP_FAILED) {
+		dump_maps();
+		printf("Error:2: mmap() succeeded when it shouldn't have\n");
+		return 1;
+	}
+
+	/*
+	 * Overlap end of existing mapping:
+	 *   base |  free  |
+	 *     +1 | mapped |
+	 *     +2 | mapped |
+	 *     +3 | mapped | new
+	 *     +4 |  free  | new
+	 */
+	errno = 0;
+	addr = BASE_ADDRESS + (3 * page_size);
+	size = 2 * page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p != MAP_FAILED) {
+		dump_maps();
+		printf("Error:3: mmap() succeeded when it shouldn't have\n");
+		return 1;
+	}
+
+	/*
+	 * Overlap start of existing mapping:
+	 *   base |  free  | new
+	 *     +1 | mapped | new
+	 *     +2 | mapped |
+	 *     +3 | mapped |
+	 *     +4 |  free  |
+	 */
+	errno = 0;
+	addr = BASE_ADDRESS;
+	size = 2 * page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p != MAP_FAILED) {
+		dump_maps();
+		printf("Error:4: mmap() succeeded when it shouldn't have\n");
+		return 1;
+	}
+
+	/*
+	 * Adjacent to start of existing mapping:
+	 *   base |  free  | new
+	 *     +1 | mapped |
+	 *     +2 | mapped |
+	 *     +3 | mapped |
+	 *     +4 |  free  |
+	 */
+	errno = 0;
+	addr = BASE_ADDRESS;
+	size = page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p == MAP_FAILED) {
+		dump_maps();
+		printf("Error:5: mmap() failed when it shouldn't have\n");
+		return 1;
+	}
+
+	/*
+	 * Adjacent to end of existing mapping:
+	 *   base |  free  |
+	 *     +1 | mapped |
+	 *     +2 | mapped |
+	 *     +3 | mapped |
+	 *     +4 |  free  |  new
+	 */
+	errno = 0;
+	addr = BASE_ADDRESS + (4 * page_size);
+	size = page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p == MAP_FAILED) {
+		dump_maps();
+		printf("Error:6: mmap() failed when it shouldn't have\n");
+		return 1;
+	}
+
+	addr = BASE_ADDRESS;
+	size = 5 * page_size;
+	if (munmap((void *)addr, size) != 0) {
+		dump_maps();
+		printf("Error: munmap failed!?\n");
+		return 1;
+	}
+	printf("unmap() successful\n");
+
+	printf("OK\n");
+	return 0;
+}
-- 
cgit 


From 0d0352d8b3d6d7ca9a710b40e194cbbaeb841c88 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Mon, 22 Oct 2018 00:08:48 +0900
Subject: selftests/ftrace: Fix synthetic event test to delete event correctly

Fix the synthetic event test case to remove event correctly.
If redirecting command to synthetic_event file without append
mode, it cleans up all existing events and execute (parse) the
command. This means "delete event" always fails to find the
target event.

Since previous synthetic event has a bug which doesn't return
-ENOENT even if it fails to find the deleting event, this test
passed. But fixing that bug, this test fails because this test
itself has a bug.

This fixes that bug by trying to delete event right after
adding an event, and use append mode redirection ('>>') instead
of normal redirection ('>').

Link: http://lkml.kernel.org/r/154013452832.25576.2305459545429386517.stgit@devbox

Acked-by: Shuah Khan <shuah@kernel.org>
Acked-by: Tom Zanussi <zanussi@linux.intel.com>
Tested-by: Tom Zanussi <zanussi@linux.intel.com>
Cc: Tom Zanussi <zanussi@kernel.org>
Cc: Tom Zanussi <tom.zanussi@linux.intel.com>
Cc: Rajvi Jingar <rajvi.jingar@intel.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: stable@vger.kernel.org
Fixes: f06eec4d0f2c ('selftests: ftrace: Add inter-event hist triggers testcases')
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 .../inter-event/trigger-synthetic-event-createremove.tc      | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc
index cef11377dcbd..c604438df13b 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc
@@ -35,18 +35,18 @@ fi
 
 reset_trigger
 
-echo "Test create synthetic event with an error"
-echo 'wakeup_latency  u64 lat pid_t pid char' > synthetic_events > /dev/null
+echo "Test remove synthetic event"
+echo '!wakeup_latency  u64 lat pid_t pid char comm[16]' >> synthetic_events
 if [ -d events/synthetic/wakeup_latency ]; then
-    fail "Created wakeup_latency synthetic event with an invalid format"
+    fail "Failed to delete wakeup_latency synthetic event"
 fi
 
 reset_trigger
 
-echo "Test remove synthetic event"
-echo '!wakeup_latency  u64 lat pid_t pid char comm[16]' > synthetic_events
+echo "Test create synthetic event with an error"
+echo 'wakeup_latency  u64 lat pid_t pid char' > synthetic_events > /dev/null
 if [ -d events/synthetic/wakeup_latency ]; then
-    fail "Failed to delete wakeup_latency synthetic event"
+    fail "Created wakeup_latency synthetic event with an invalid format"
 fi
 
 do_reset
-- 
cgit 


From a95ecac5cb2fc8a8ee606991384d33ee121df00c Mon Sep 17 00:00:00 2001
From: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
Date: Tue, 23 Oct 2018 13:34:56 +0530
Subject: selftests/powerpc: Relax L1d miss targets for rfi_flush test

When running the rfi_flush test, if the system is loaded, we see two
issues:
1. The L1d misses when rfi_flush is disabled increase significantly due
to other workloads interfering with the cache.
2. The L1d misses when rfi_flush is enabled sometimes goes slightly
below the expected number of misses.

To address these, let's relax the expected number of L1d misses:
1. When rfi_flush is disabled, we allow upto half the expected number of
the misses for when rfi_flush is enabled.
2. When rfi_flush is enabled, we allow ~1% lower number of cache misses.

Reported-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Tested-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/security/rfi_flush.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/powerpc/security/rfi_flush.c b/tools/testing/selftests/powerpc/security/rfi_flush.c
index 564ed45bbf73..0a7d0afb26b8 100644
--- a/tools/testing/selftests/powerpc/security/rfi_flush.c
+++ b/tools/testing/selftests/powerpc/security/rfi_flush.c
@@ -49,6 +49,7 @@ int rfi_flush_test(void)
 	struct perf_event_read v;
 	__u64 l1d_misses_total = 0;
 	unsigned long iterations = 100000, zero_size = 24 * 1024;
+	unsigned long l1d_misses_expected;
 	int rfi_flush_org, rfi_flush;
 
 	SKIP_IF(geteuid() != 0);
@@ -71,6 +72,12 @@ int rfi_flush_test(void)
 
 	iter = repetitions;
 
+	/*
+	 * We expect to see l1d miss for each cacheline access when rfi_flush
+	 * is set. Allow a small variation on this.
+	 */
+	l1d_misses_expected = iterations * (zero_size / CACHELINE_SIZE - 2);
+
 again:
 	FAIL_IF(perf_event_reset(fd));
 
@@ -78,10 +85,9 @@ again:
 
 	FAIL_IF(read(fd, &v, sizeof(v)) != sizeof(v));
 
-	/* Expect at least zero_size/CACHELINE_SIZE misses per iteration */
-	if (v.l1d_misses >= (iterations * zero_size / CACHELINE_SIZE) && rfi_flush)
+	if (rfi_flush && v.l1d_misses >= l1d_misses_expected)
 		passes++;
-	else if (v.l1d_misses < iterations && !rfi_flush)
+	else if (!rfi_flush && v.l1d_misses < (l1d_misses_expected / 2))
 		passes++;
 
 	l1d_misses_total += v.l1d_misses;
@@ -92,13 +98,15 @@ again:
 	if (passes < repetitions) {
 		printf("FAIL (L1D misses with rfi_flush=%d: %llu %c %lu) [%d/%d failures]\n",
 		       rfi_flush, l1d_misses_total, rfi_flush ? '<' : '>',
-		       rfi_flush ? (repetitions * iterations * zero_size / CACHELINE_SIZE) : iterations,
+		       rfi_flush ? repetitions * l1d_misses_expected :
+		       repetitions * l1d_misses_expected / 2,
 		       repetitions - passes, repetitions);
 		rc = 1;
 	} else
 		printf("PASS (L1D misses with rfi_flush=%d: %llu %c %lu) [%d/%d pass]\n",
 		       rfi_flush, l1d_misses_total, rfi_flush ? '>' : '<',
-		       rfi_flush ? (repetitions * iterations * zero_size / CACHELINE_SIZE) : iterations,
+		       rfi_flush ? repetitions * l1d_misses_expected :
+		       repetitions * l1d_misses_expected / 2,
 		       passes, repetitions);
 
 	if (rfi_flush == rfi_flush_org) {
-- 
cgit 


From b31d30d9be32d41bef3e6076a965565d3a3d8005 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 29 Oct 2018 14:56:48 -0700
Subject: tools/bpf: add unlimited rlimit for flow_dissector_load

On our test machine, bpf selftest test_flow_dissector.sh failed
with the following error:
  # ./test_flow_dissector.sh
  bpffs not mounted. Mounting...
  libbpf: failed to create map (name: 'jmp_table'): Operation not permitted
  libbpf: failed to load object 'bpf_flow.o'
  ./flow_dissector_load: bpf_prog_load bpf_flow.o
  selftests: test_flow_dissector [FAILED]

Let us increase the rlimit to remove the above map
creation failure.

Signed-off-by: Yonghong Song <yhs@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/flow_dissector_load.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/flow_dissector_load.c b/tools/testing/selftests/bpf/flow_dissector_load.c
index d3273b5b3173..ae8180b11d5f 100644
--- a/tools/testing/selftests/bpf/flow_dissector_load.c
+++ b/tools/testing/selftests/bpf/flow_dissector_load.c
@@ -11,6 +11,8 @@
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
 
+#include "bpf_rlimit.h"
+
 const char *cfg_pin_path = "/sys/fs/bpf/flow_dissector";
 const char *cfg_map_name = "jmp_table";
 bool cfg_attach = true;
-- 
cgit 


From a0aebae07f211c05d64be886e56d352eea86350b Mon Sep 17 00:00:00 2001
From: Joel Stanley <joel@jms.id.au>
Date: Mon, 22 Oct 2018 22:39:26 +1030
Subject: selftests: powerpc: Fix warning for security subdir

typing 'make' inside tools/testing/selftests/powerpc gave a build
warning:

BUILD_TARGET=tools/testing/selftests/powerpc/security; mkdir -p $BUILD_TARGET; make OUTPUT=$BUILD_TARGET -k -C security all
make[1]: Entering directory 'tools/testing/selftests/powerpc/security'
../../lib.mk:20: ../../../../scripts/subarch.include: No such file or directory
make[1]: *** No rule to make target '../../../../scripts/subarch.include'.
make[1]: Failed to remake makefile '../../../../scripts/subarch.include'.

The build is one level deeper than lib.mk thinks it is. Set top_srcdir
to set things straight.

Note that the test program is still built.

Signed-off-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/security/Makefile | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/powerpc/security/Makefile b/tools/testing/selftests/powerpc/security/Makefile
index 44690f1bb26a..85861c46b445 100644
--- a/tools/testing/selftests/powerpc/security/Makefile
+++ b/tools/testing/selftests/powerpc/security/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0+
 
 TEST_GEN_PROGS := rfi_flush
+top_srcdir = ../../../../..
 
 CFLAGS += -I../../../../../usr/include
 
-- 
cgit 


From c39b79082a38a4f8c801790edecbbb4d62ed2992 Mon Sep 17 00:00:00 2001
From: Joel Stanley <joel@jms.id.au>
Date: Mon, 29 Oct 2018 22:23:49 +1100
Subject: selftests/powerpc/ptrace: Fix out-of-tree build

We should use TEST_GEN_PROGS, not TEST_PROGS. That tells the selftests
makefile (lib.mk) that those tests are generated (built), and so it
adds the $(OUTPUT) prefix for us, making the out-of-tree build work
correctly.

It also means we don't need our own clean rule, lib.mk does it.

We also have to update the ptrace-pkey and core-pkey rules to use
$(OUTPUT).

Signed-off-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/ptrace/Makefile | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile
index 9b35ca8e8f13..8d3f006c98cc 100644
--- a/tools/testing/selftests/powerpc/ptrace/Makefile
+++ b/tools/testing/selftests/powerpc/ptrace/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-TEST_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \
+TEST_GEN_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \
               ptrace-tar ptrace-tm-tar ptrace-tm-spd-tar ptrace-vsx ptrace-tm-vsx \
               ptrace-tm-spd-vsx ptrace-tm-spr ptrace-hwbreak ptrace-pkey core-pkey \
               perf-hwbreak ptrace-syscall
@@ -7,14 +7,9 @@ TEST_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \
 top_srcdir = ../../../../..
 include ../../lib.mk
 
-all: $(TEST_PROGS)
-
 CFLAGS += -m64 -I../../../../../usr/include -I../tm -mhtm -fno-pie
 
-ptrace-pkey core-pkey: child.h
-ptrace-pkey core-pkey: LDLIBS += -pthread
-
-$(TEST_PROGS): ../harness.c ../utils.c ../lib/reg.S ptrace.h
+$(OUTPUT)/ptrace-pkey $(OUTPUT)/core-pkey: child.h
+$(OUTPUT)/ptrace-pkey $(OUTPUT)/core-pkey: LDLIBS += -pthread
 
-clean:
-	rm -f $(TEST_PROGS) *.o
+$(TEST_GEN_PROGS): ../harness.c ../utils.c ../lib/reg.S ptrace.h
-- 
cgit 


From 27825349d7b238533a47e3d98b8bb0efd886b752 Mon Sep 17 00:00:00 2001
From: Joel Stanley <joel@jms.id.au>
Date: Mon, 29 Oct 2018 22:23:50 +1100
Subject: selftests/powerpc/signal: Fix out-of-tree build

We should use TEST_GEN_PROGS, not TEST_PROGS. That tells the selftests
makefile (lib.mk) that those tests are generated (built), and so it
adds the $(OUTPUT) prefix for us, making the out-of-tree build work
correctly.

It also means we don't need our own clean rule, lib.mk does it.

We also have to update the signal_tm rule to use $(OUTPUT).

Signed-off-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/signal/Makefile | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/powerpc/signal/Makefile b/tools/testing/selftests/powerpc/signal/Makefile
index 1fca25c6ace0..209a958dca12 100644
--- a/tools/testing/selftests/powerpc/signal/Makefile
+++ b/tools/testing/selftests/powerpc/signal/Makefile
@@ -1,15 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
-TEST_PROGS := signal signal_tm
-
-all: $(TEST_PROGS)
-
-$(TEST_PROGS): ../harness.c ../utils.c signal.S
+TEST_GEN_PROGS := signal signal_tm
 
 CFLAGS += -maltivec
-signal_tm: CFLAGS += -mhtm
+$(OUTPUT)/signal_tm: CFLAGS += -mhtm
 
 top_srcdir = ../../../../..
 include ../../lib.mk
 
-clean:
-	rm -f $(TEST_PROGS) *.o
+$(TEST_GEN_PROGS): ../harness.c ../utils.c signal.S
-- 
cgit 


From 98415da03ae6559dc62899fd31e55e194779c45b Mon Sep 17 00:00:00 2001
From: Joel Stanley <joel@jms.id.au>
Date: Mon, 29 Oct 2018 22:23:51 +1100
Subject: selftests/powerpc/pmu: Link ebb tests with -no-pie

When running the ebb tests after building on a ppc64le Ubuntu machine:

 $ pmu/ebb/reg_access_test: error while loading shared libraries:
 R_PPC64_ADDR16_HI reloc at 0x000000013a965130 for symbol `' out of
 range

This is because the Ubuntu toolchain builds has PIE enabled by default.
Change it to be always off instead.

Signed-off-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/pmu/ebb/Makefile | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
index bd5dfa509272..23f4caf48ffc 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
@@ -5,6 +5,9 @@ noarg:
 # The EBB handler is 64-bit code and everything links against it
 CFLAGS += -m64
 
+# Toolchains may build PIE by default which breaks the assembly
+LDFLAGS += -no-pie
+
 TEST_GEN_PROGS := reg_access_test event_attributes_test cycles_test	\
 	 cycles_with_freeze_test pmc56_overflow_test		\
 	 ebb_vs_cpu_event_test cpu_event_vs_ebb_test		\
-- 
cgit 


From 266bac361d5677e61a6815bd29abeb3bdced2b07 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Mon, 29 Oct 2018 22:23:52 +1100
Subject: selftests/powerpc/switch_endian: Fix out-of-tree build

For the out-of-tree build to work we need to tell switch_endian_test
to look for check-reversed.S in $(OUTPUT).

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/switch_endian/Makefile | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/powerpc/switch_endian/Makefile b/tools/testing/selftests/powerpc/switch_endian/Makefile
index fcd2dcb8972b..bdc081afedb0 100644
--- a/tools/testing/selftests/powerpc/switch_endian/Makefile
+++ b/tools/testing/selftests/powerpc/switch_endian/Makefile
@@ -8,6 +8,7 @@ EXTRA_CLEAN = $(OUTPUT)/*.o $(OUTPUT)/check-reversed.S
 top_srcdir = ../../../../..
 include ../../lib.mk
 
+$(OUTPUT)/switch_endian_test: ASFLAGS += -I $(OUTPUT)
 $(OUTPUT)/switch_endian_test: $(OUTPUT)/check-reversed.S
 
 $(OUTPUT)/check-reversed.o: $(OUTPUT)/check.o
-- 
cgit 


From 69f8117f17b332a68cd8f4bf8c2d0d3d5b84efc5 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Mon, 29 Oct 2018 22:23:53 +1100
Subject: selftests/powerpc/cache_shape: Fix out-of-tree build

Use TEST_GEN_PROGS and don't redefine all, this makes the out-of-tree
build work. We need to move the extra dependencies below the include
of lib.mk, because it adds the $(OUTPUT) prefix if it's defined.

We can also drop the clean rule, lib.mk does it for us.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/cache_shape/Makefile | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/powerpc/cache_shape/Makefile b/tools/testing/selftests/powerpc/cache_shape/Makefile
index ede4d3dae750..689f6c8ebcd8 100644
--- a/tools/testing/selftests/powerpc/cache_shape/Makefile
+++ b/tools/testing/selftests/powerpc/cache_shape/Makefile
@@ -1,12 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
-TEST_PROGS := cache_shape
-
-all: $(TEST_PROGS)
-
-$(TEST_PROGS): ../harness.c ../utils.c
+TEST_GEN_PROGS := cache_shape
 
 top_srcdir = ../../../../..
 include ../../lib.mk
 
-clean:
-	rm -f $(TEST_PROGS) *.o
+$(TEST_GEN_PROGS): ../harness.c ../utils.c
-- 
cgit 


From 8f3f09358c81248109463b3cae254b7db4ea9af0 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 31 Oct 2018 09:56:45 +0000
Subject: selftests: mlxsw: qos_mc_aware: Tweak for min shaper

Since the minimum shaper is now being enabled for MC TCs, it's
unreasonable to expect no UC traffic loss. Minimal min shaper value is
200Mbps, which is 20% of the 1Gbps that this test configures on egress.
To cover for glitches, tolerate up to 25% UC degradation under MC
overload.

Fixes: b5638d46c90a ("selftests: mlxsw: Add a test for UC behavior under MC flood")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
index 0150bb2741eb..a8fc36d670e1 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
@@ -311,7 +311,7 @@ test_mc_aware()
 			ret = 100 * ($ucth1 - $ucth2) / $ucth1
 			if (ret > 0) { ret } else { 0 }
 		    ")
-	check_err $(bc <<< "$deg > 10")
+	check_err $(bc <<< "$deg > 25")
 
 	local interval=$((d1 - d0))
 	local mc_ir=$(rate $u0 $u1 $interval)
-- 
cgit 


From a5ee171d087ee632a5f190bb3ce1c0f98e06ec0a Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 31 Oct 2018 09:56:46 +0000
Subject: selftests: mlxsw: qos_mc_aware: Add a test for UC awareness

In a previous patch, mlxsw was updated to configure a minimum bandwidth
allowance on MC TCs. Test that this indeed fixes the problem of UC
traffic overload pushing out all MC traffic.

Fixes: b5638d46c90a ("selftests: mlxsw: Add a test for UC behavior under MC flood")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/qos_mc_aware.sh    | 93 ++++++++++++++++------
 1 file changed, 70 insertions(+), 23 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
index a8fc36d670e1..117f6f35d72f 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
@@ -25,24 +25,24 @@
 # Thus we set MTU to 10K on all involved interfaces. Then both unicast and
 # multicast traffic uses 8K frames.
 #
-# +-----------------------+                +----------------------------------+
-# | H1                    |                |                               H2 |
-# |                       |                |  unicast --> + $h2.111           |
-# |                       |                |  traffic     | 192.0.2.129/28    |
-# |          multicast    |                |              | e-qos-map 0:1     |
-# |          traffic      |                |              |                   |
-# | $h1 + <-----          |                |              + $h2               |
-# +-----|-----------------+                +--------------|-------------------+
-#       |                                                 |
-# +-----|-------------------------------------------------|-------------------+
-# |     + $swp1                                           + $swp2             |
-# |     | >1Gbps                                          | >1Gbps            |
-# | +---|----------------+                     +----------|----------------+  |
-# | |   + $swp1.1        |                     |          + $swp2.111      |  |
+# +---------------------------+            +----------------------------------+
+# | H1                        |            |                               H2 |
+# |                           |            |  unicast --> + $h2.111           |
+# |                 multicast |            |  traffic     | 192.0.2.129/28    |
+# |                 traffic   |            |              | e-qos-map 0:1     |
+# |           $h1 + <-----    |            |              |                   |
+# | 192.0.2.65/28 |           |            |              + $h2               |
+# +---------------|-----------+            +--------------|-------------------+
+#                 |                                       |
+# +---------------|---------------------------------------|-------------------+
+# |         $swp1 +                                       + $swp2             |
+# |        >1Gbps |                                       | >1Gbps            |
+# | +-------------|------+                     +----------|----------------+  |
+# | |     $swp1.1 +      |                     |          + $swp2.111      |  |
 # | |                BR1 |             SW      | BR111                     |  |
-# | |   + $swp3.1        |                     |          + $swp3.111      |  |
-# | +---|----------------+                     +----------|----------------+  |
-# |     \_________________________________________________/                   |
+# | |     $swp3.1 +      |                     |          + $swp3.111      |  |
+# | +-------------|------+                     +----------|----------------+  |
+# |               \_______________________________________/                   |
 # |                                    |                                      |
 # |                                    + $swp3                                |
 # |                                    | 1Gbps bottleneck                     |
@@ -51,6 +51,7 @@
 #                                      |
 #                                   +--|-----------------+
 #                                   |  + $h3          H3 |
+#                                   |  | 192.0.2.66/28   |
 #                                   |  |                 |
 #                                   |  + $h3.111         |
 #                                   |    192.0.2.130/28  |
@@ -59,6 +60,7 @@
 ALL_TESTS="
 	ping_ipv4
 	test_mc_aware
+	test_uc_aware
 "
 
 lib_dir=$(dirname $0)/../../../net/forwarding
@@ -68,14 +70,14 @@ source $lib_dir/lib.sh
 
 h1_create()
 {
-	simple_if_init $h1
+	simple_if_init $h1 192.0.2.65/28
 	mtu_set $h1 10000
 }
 
 h1_destroy()
 {
 	mtu_restore $h1
-	simple_if_fini $h1
+	simple_if_fini $h1 192.0.2.65/28
 }
 
 h2_create()
@@ -97,7 +99,7 @@ h2_destroy()
 
 h3_create()
 {
-	simple_if_init $h3
+	simple_if_init $h3 192.0.2.66/28
 	mtu_set $h3 10000
 
 	vlan_create $h3 111 v$h3 192.0.2.130/28
@@ -108,7 +110,7 @@ h3_destroy()
 	vlan_destroy $h3 111
 
 	mtu_restore $h3
-	simple_if_fini $h3
+	simple_if_fini $h3 192.0.2.66/28
 }
 
 switch_create()
@@ -251,7 +253,7 @@ measure_uc_rate()
 	# average ingress rate to somewhat mitigate this.
 	local min_ingress=2147483648
 
-	mausezahn $h2.111 -p 8000 -A 192.0.2.129 -B 192.0.2.130 -c 0 \
+	$MZ $h2.111 -p 8000 -A 192.0.2.129 -B 192.0.2.130 -c 0 \
 		-a own -b $h3mac -t udp -q &
 	sleep 1
 
@@ -291,7 +293,7 @@ test_mc_aware()
 	check_err $? "Could not get high enough UC-only ingress rate"
 	local ucth1=${uc_rate[1]}
 
-	mausezahn $h1 -p 8000 -c 0 -a own -b bc -t udp -q &
+	$MZ $h1 -p 8000 -c 0 -a own -b bc -t udp -q &
 
 	local d0=$(date +%s)
 	local t0=$(ethtool_stats_get $h3 rx_octets_prio_0)
@@ -335,6 +337,51 @@ test_mc_aware()
 	echo "    egress UC throughput  $(humanize ${uc_rate_2[1]})"
 	echo "    ingress MC throughput $(humanize $mc_ir)"
 	echo "    egress MC throughput  $(humanize $mc_er)"
+	echo
+}
+
+test_uc_aware()
+{
+	RET=0
+
+	$MZ $h2.111 -p 8000 -A 192.0.2.129 -B 192.0.2.130 -c 0 \
+		-a own -b $h3mac -t udp -q &
+
+	local d0=$(date +%s)
+	local t0=$(ethtool_stats_get $h3 rx_octets_prio_1)
+	local u0=$(ethtool_stats_get $swp2 rx_octets_prio_1)
+	sleep 1
+
+	local attempts=50
+	local passes=0
+	local i
+
+	for ((i = 0; i < attempts; ++i)); do
+		if $ARPING -c 1 -I $h1 -b 192.0.2.66 -q -w 0.1; then
+			((passes++))
+		fi
+
+		sleep 0.1
+	done
+
+	local d1=$(date +%s)
+	local t1=$(ethtool_stats_get $h3 rx_octets_prio_1)
+	local u1=$(ethtool_stats_get $swp2 rx_octets_prio_1)
+
+	local interval=$((d1 - d0))
+	local uc_ir=$(rate $u0 $u1 $interval)
+	local uc_er=$(rate $t0 $t1 $interval)
+
+	((attempts == passes))
+	check_err $?
+
+	# Suppress noise from killing mausezahn.
+	{ kill %% && wait; } 2>/dev/null
+
+	log_test "MC performace under UC overload"
+	echo "    ingress UC throughput $(humanize ${uc_ir})"
+	echo "    egress UC throughput  $(humanize ${uc_er})"
+	echo "    sent $attempts BC ARPs, got $passes responses"
 }
 
 trap cleanup EXIT
-- 
cgit 


From deee2cae27d1914850195e3fb219cc611e953560 Mon Sep 17 00:00:00 2001
From: Li Zhijian <lizhijian@cn.fujitsu.com>
Date: Tue, 30 Oct 2018 11:15:55 +0800
Subject: kselftests/bpf: use ping6 as the default ipv6 ping binary if it
 exists

ping binary on some distros doesn't support "ping -6" anymore.

Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_skb_cgroup_id.sh | 3 ++-
 tools/testing/selftests/bpf/test_sock_addr.sh     | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_skb_cgroup_id.sh b/tools/testing/selftests/bpf/test_skb_cgroup_id.sh
index 42544a969abc..a9bc6f82abc1 100755
--- a/tools/testing/selftests/bpf/test_skb_cgroup_id.sh
+++ b/tools/testing/selftests/bpf/test_skb_cgroup_id.sh
@@ -10,7 +10,7 @@ wait_for_ip()
 	echo -n "Wait for testing link-local IP to become available "
 	for _i in $(seq ${MAX_PING_TRIES}); do
 		echo -n "."
-		if ping -6 -q -c 1 -W 1 ff02::1%${TEST_IF} >/dev/null 2>&1; then
+		if $PING6 -c 1 -W 1 ff02::1%${TEST_IF} >/dev/null 2>&1; then
 			echo " OK"
 			return
 		fi
@@ -58,5 +58,6 @@ BPF_PROG_OBJ="${DIR}/test_skb_cgroup_id_kern.o"
 BPF_PROG_SECTION="cgroup_id_logger"
 BPF_PROG_ID=0
 PROG="${DIR}/test_skb_cgroup_id_user"
+type ping6 >/dev/null 2>&1 && PING6="ping6" || PING6="ping -6"
 
 main
diff --git a/tools/testing/selftests/bpf/test_sock_addr.sh b/tools/testing/selftests/bpf/test_sock_addr.sh
index 9832a875a828..3b9fdb8094aa 100755
--- a/tools/testing/selftests/bpf/test_sock_addr.sh
+++ b/tools/testing/selftests/bpf/test_sock_addr.sh
@@ -4,7 +4,8 @@ set -eu
 
 ping_once()
 {
-	ping -${1} -q -c 1 -W 1 ${2%%/*} >/dev/null 2>&1
+	type ping${1} >/dev/null 2>&1 && PING="ping${1}" || PING="ping -${1}"
+	$PING -q -c 1 -W 1 ${2%%/*} >/dev/null 2>&1
 }
 
 wait_for_ip()
-- 
cgit 


From 1936f094e164cc13ebf17aba1d6b34e033e64188 Mon Sep 17 00:00:00 2001
From: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
Date: Wed, 31 Oct 2018 22:48:13 +0530
Subject: selftests/powerpc: Fix compilation issue due to asm label

We are using 'dscr_insn' as a label in inline asm to identify if a
SIGILL was generated by the mtspr instruction at that point. However,
with inline assembly, the compiler is still free to duplicate the asm
statement for optimization purposes, which results in the label being
defined twice with the error:
	/tmp/ccerQCql.s:874: Error: symbol `dscr_insn' is already defined

With different compiler versions, we may also see:
	/tmp/ccJzLDlN.o:(.toc+0x0): undefined reference to `dscr_insn'

Remove the use of the label in the inline assembly. Instead, just look
for the offending instruction in the signal handler.

Fixes: d2bf793237b3 ("selftests/powerpc: Add test to verify rfi flush across a system call")
Reported-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Tested-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/utils.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c
index 43c342845be0..ed62f4153d3e 100644
--- a/tools/testing/selftests/powerpc/utils.c
+++ b/tools/testing/selftests/powerpc/utils.c
@@ -25,7 +25,6 @@
 #include "utils.h"
 
 static char auxv[4096];
-extern unsigned int dscr_insn[];
 
 int read_auxv(char *buf, ssize_t buf_size)
 {
@@ -247,7 +246,8 @@ static void sigill_handler(int signr, siginfo_t *info, void *unused)
 	ucontext_t *ctx = (ucontext_t *)unused;
 	unsigned long *pc = &UCONTEXT_NIA(ctx);
 
-	if (*pc == (unsigned long)&dscr_insn) {
+	/* mtspr 3,RS to check for move to DSCR below */
+	if ((*((unsigned int *)*pc) & 0xfc1fffff) == 0x7c0303a6) {
 		if (!warned++)
 			printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n");
 		*pc += 4;
@@ -271,5 +271,5 @@ void set_dscr(unsigned long val)
 		init = 1;
 	}
 
-	asm volatile("dscr_insn: mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR));
+	asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR));
 }
-- 
cgit 


From 2683f4128c8730699296827d3209d2de80fa1d6c Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 1 Nov 2018 00:05:54 +0100
Subject: bpf: add various test cases to test_verifier

Add some more map related test cases to test_verifier kselftest
to improve test coverage. Summary: 1012 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_verifier.c | 250 ++++++++++++++++++++++++++++
 1 file changed, 250 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 36f3d3009d1a..4c7445d4b3e6 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -6454,6 +6454,256 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 min value is negative",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
+	{
+		"map access: known scalar += value_ptr",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			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, 3),
+			BPF_MOV64_IMM(BPF_REG_1, 4),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"map access: value_ptr += known scalar",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			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, 3),
+			BPF_MOV64_IMM(BPF_REG_1, 4),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"map access: unknown scalar += value_ptr",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			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_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"map access: value_ptr += unknown scalar",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			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_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"map access: value_ptr += value_ptr",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			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_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_0),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = REJECT,
+		.errstr = "R0 pointer += pointer prohibited",
+	},
+	{
+		"map access: known scalar -= value_ptr",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			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, 3),
+			BPF_MOV64_IMM(BPF_REG_1, 4),
+			BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = REJECT,
+		.errstr = "R1 tried to subtract pointer from scalar",
+	},
+	{
+		"map access: value_ptr -= known scalar",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			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, 3),
+			BPF_MOV64_IMM(BPF_REG_1, 4),
+			BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = REJECT,
+		.errstr = "R0 min value is outside of the array range",
+	},
+	{
+		"map access: value_ptr -= known scalar, 2",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			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, 5),
+			BPF_MOV64_IMM(BPF_REG_1, 6),
+			BPF_MOV64_IMM(BPF_REG_2, 4),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_2),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"map access: unknown scalar -= value_ptr",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			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_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
+			BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = REJECT,
+		.errstr = "R1 tried to subtract pointer from scalar",
+	},
+	{
+		"map access: value_ptr -= unknown scalar",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			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_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
+			BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = REJECT,
+		.errstr = "R0 min value is negative",
+	},
+	{
+		"map access: value_ptr -= unknown scalar, 2",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			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, 8),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
+			BPF_ALU64_IMM(BPF_OR, BPF_REG_1, 0x7),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+			BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"map access: value_ptr -= value_ptr",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			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_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_0),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = REJECT,
+		.errstr = "R0 invalid mem access 'inv'",
+		.errstr_unpriv = "R0 pointer -= pointer prohibited",
+	},
 	{
 		"map lookup helper access to map",
 		.insns = {
-- 
cgit 


From 832c6f2c29ec519b766923937f4f93fb1008b47d Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 1 Nov 2018 00:05:55 +0100
Subject: bpf: test make sure to run unpriv test cases in test_verifier

Right now unprivileged tests are never executed as a BPF test run,
only loaded. Allow for running them as well so that we can check
the outcome and probe for regressions.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_verifier.c | 71 ++++++++++++++++-------------
 1 file changed, 40 insertions(+), 31 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 4c7445d4b3e6..6f61df62f690 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -76,7 +76,7 @@ struct bpf_test {
 	int fixup_percpu_cgroup_storage[MAX_FIXUPS];
 	const char *errstr;
 	const char *errstr_unpriv;
-	uint32_t retval;
+	uint32_t retval, retval_unpriv;
 	enum {
 		UNDEF,
 		ACCEPT,
@@ -3084,6 +3084,8 @@ static struct bpf_test tests[] = {
 		.fixup_prog1 = { 2 },
 		.result = ACCEPT,
 		.retval = 42,
+		/* Verifier rewrite for unpriv skips tail call here. */
+		.retval_unpriv = 2,
 	},
 	{
 		"stack pointer arithmetic",
@@ -14149,6 +14151,33 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_map_type prog_type,
 	}
 }
 
+static int set_admin(bool admin)
+{
+	cap_t caps;
+	const cap_value_t cap_val = CAP_SYS_ADMIN;
+	int ret = -1;
+
+	caps = cap_get_proc();
+	if (!caps) {
+		perror("cap_get_proc");
+		return -1;
+	}
+	if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_val,
+				admin ? CAP_SET : CAP_CLEAR)) {
+		perror("cap_set_flag");
+		goto out;
+	}
+	if (cap_set_proc(caps)) {
+		perror("cap_set_proc");
+		goto out;
+	}
+	ret = 0;
+out:
+	if (cap_free(caps))
+		perror("cap_free");
+	return ret;
+}
+
 static void do_test_single(struct bpf_test *test, bool unpriv,
 			   int *passes, int *errors)
 {
@@ -14157,6 +14186,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	struct bpf_insn *prog = test->insns;
 	int map_fds[MAX_NR_MAPS];
 	const char *expected_err;
+	uint32_t expected_val;
 	uint32_t retval;
 	int i, err;
 
@@ -14176,6 +14206,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		       test->result_unpriv : test->result;
 	expected_err = unpriv && test->errstr_unpriv ?
 		       test->errstr_unpriv : test->errstr;
+	expected_val = unpriv && test->retval_unpriv ?
+		       test->retval_unpriv : test->retval;
 
 	reject_from_alignment = fd_prog < 0 &&
 				(test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) &&
@@ -14209,16 +14241,20 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		__u8 tmp[TEST_DATA_LEN << 2];
 		__u32 size_tmp = sizeof(tmp);
 
+		if (unpriv)
+			set_admin(true);
 		err = bpf_prog_test_run(fd_prog, 1, test->data,
 					sizeof(test->data), tmp, &size_tmp,
 					&retval, NULL);
+		if (unpriv)
+			set_admin(false);
 		if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
 			printf("Unexpected bpf_prog_test_run error\n");
 			goto fail_log;
 		}
-		if (!err && retval != test->retval &&
-		    test->retval != POINTER_VALUE) {
-			printf("FAIL retval %d != %d\n", retval, test->retval);
+		if (!err && retval != expected_val &&
+		    expected_val != POINTER_VALUE) {
+			printf("FAIL retval %d != %d\n", retval, expected_val);
 			goto fail_log;
 		}
 	}
@@ -14261,33 +14297,6 @@ static bool is_admin(void)
 	return (sysadmin == CAP_SET);
 }
 
-static int set_admin(bool admin)
-{
-	cap_t caps;
-	const cap_value_t cap_val = CAP_SYS_ADMIN;
-	int ret = -1;
-
-	caps = cap_get_proc();
-	if (!caps) {
-		perror("cap_get_proc");
-		return -1;
-	}
-	if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_val,
-				admin ? CAP_SET : CAP_CLEAR)) {
-		perror("cap_set_flag");
-		goto out;
-	}
-	if (cap_set_proc(caps)) {
-		perror("cap_set_proc");
-		goto out;
-	}
-	ret = 0;
-out:
-	if (cap_free(caps))
-		perror("cap_free");
-	return ret;
-}
-
 static void get_unpriv_disabled()
 {
 	char buf[2];
-- 
cgit