Merge tag 'kvmarm-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for 5.15

- Page ownership tracking between host EL1 and EL2

- Rely on userspace page tables to create large stage-2 mappings

- Fix incompatibility between pKVM and kmemleak

- Fix the PMU reset state, and improve the performance of the virtual PMU

- Move over to the generic KVM entry code

- Address PSCI reset issues w.r.t. save/restore

- Preliminary rework for the upcoming pKVM fixed feature

- A bunch of MM cleanups

- a vGIC fix for timer spurious interrupts

- Various cleanups

12 files changed, 666 insertions, 22 deletions

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 1828bba19020..dc6daa193557 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -222,6 +222,11 @@ int mount_bpffs_for_pin(const char *name)
 	int err = 0;
 
 	file = malloc(strlen(name) + 1);
+	if (!file) {
+		p_err("mem alloc failed");
+		return -1;
+	}
+
 	strcpy(file, name);
 	dir = dirname(file);
 
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 22f8326547eb..bc1f64873c8f 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -2434,6 +2434,22 @@ static int cs_etm__process_event(struct perf_session *session,
 	return 0;
 }
 
+static void dump_queued_data(struct cs_etm_auxtrace *etm,
+			     struct perf_record_auxtrace *event)
+{
+	struct auxtrace_buffer *buf;
+	unsigned int i;
+	/*
+	 * Find all buffers with same reference in the queues and dump them.
+	 * This is because the queues can contain multiple entries of the same
+	 * buffer that were split on aux records.
+	 */
+	for (i = 0; i < etm->queues.nr_queues; ++i)
+		list_for_each_entry(buf, &etm->queues.queue_array[i].head, list)
+			if (buf->reference == event->reference)
+				cs_etm__dump_event(etm, buf);
+}
+
 static int cs_etm__process_auxtrace_event(struct perf_session *session,
 					  union perf_event *event,
 					  struct perf_tool *tool __maybe_unused)
@@ -2466,7 +2482,8 @@ static int cs_etm__process_auxtrace_event(struct perf_session *session,
 				cs_etm__dump_event(etm, buffer);
 				auxtrace_buffer__put_data(buffer);
 			}
-	}
+	} else if (dump_trace)
+		dump_queued_data(etm, &event->auxtrace);
 
 	return 0;
 }
@@ -3042,7 +3059,6 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 
 	if (dump_trace) {
 		cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu);
-		return 0;
 	}
 
 	err = cs_etm__synth_events(etm, session);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 72e7f3616157..8af693d9678c 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -192,8 +192,6 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 			if (!(prot & PROT_EXEC))
 				dso__set_loaded(dso);
 		}
-
-		nsinfo__put(dso->nsinfo);
 		dso->nsinfo = nsi;
 
 		if (build_id__is_defined(bid))
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index a1bd7007a8b4..fc683bc41715 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -742,9 +742,13 @@ struct pmu_events_map *__weak pmu_events_map__find(void)
 	return perf_pmu__find_map(NULL);
 }
 
-static bool perf_pmu__valid_suffix(char *pmu_name, char *tok)
+/*
+ * Suffix must be in form tok_{digits}, or tok{digits}, or same as pmu_name
+ * to be valid.
+ */
+static bool perf_pmu__valid_suffix(const char *pmu_name, char *tok)
 {
-	char *p;
+	const char *p;
 
 	if (strncmp(pmu_name, tok, strlen(tok)))
 		return false;
@@ -753,12 +757,16 @@ static bool perf_pmu__valid_suffix(char *pmu_name, char *tok)
 	if (*p == 0)
 		return true;
 
-	if (*p != '_')
-		return false;
+	if (*p == '_')
+		++p;
 
-	++p;
-	if (*p == 0 || !isdigit(*p))
-		return false;
+	/* Ensure we end in a number */
+	while (1) {
+		if (!isdigit(*p))
+			return false;
+		if (*(++p) == 0)
+			break;
+	}
 
 	return true;
 }
@@ -789,12 +797,19 @@ bool pmu_uncore_alias_match(const char *pmu_name, const char *name)
 	 *	    match "socket" in "socketX_pmunameY" and then "pmuname" in
 	 *	    "pmunameY".
 	 */
-	for (; tok; name += strlen(tok), tok = strtok_r(NULL, ",", &tmp)) {
+	while (1) {
+		char *next_tok = strtok_r(NULL, ",", &tmp);
+
 		name = strstr(name, tok);
-		if (!name || !perf_pmu__valid_suffix((char *)name, tok)) {
+		if (!name ||
+		    (!next_tok && !perf_pmu__valid_suffix(name, tok))) {
 			res = false;
 			goto out;
 		}
+		if (!next_tok)
+			break;
+		tok = next_tok;
+		name += strlen(tok);
 	}
 
 	res = true;
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
index a3e593ddfafc..2debba4e8a3a 100644
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
@@ -1,4 +1,233 @@
 {
+	"map access: known scalar += value_ptr unknown vs const",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+		    offsetof(struct __sk_buff, len)),
+	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_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+	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, 9),
+	BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
+	BPF_MOV64_IMM(BPF_REG_1, 6),
+	BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_MOV64_IMM(BPF_REG_1, 3),
+	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_hash_16b = { 5 },
+	.fixup_map_array_48b = { 8 },
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+	.result = ACCEPT,
+	.retval = 1,
+},
+{
+	"map access: known scalar += value_ptr const vs unknown",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+		    offsetof(struct __sk_buff, len)),
+	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_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+	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, 9),
+	BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2),
+	BPF_MOV64_IMM(BPF_REG_1, 3),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 3),
+	BPF_MOV64_IMM(BPF_REG_1, 6),
+	BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+	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_hash_16b = { 5 },
+	.fixup_map_array_48b = { 8 },
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+	.result = ACCEPT,
+	.retval = 1,
+},
+{
+	"map access: known scalar += value_ptr const vs const (ne)",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+		    offsetof(struct __sk_buff, len)),
+	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_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+	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, 7),
+	BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2),
+	BPF_MOV64_IMM(BPF_REG_1, 3),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_MOV64_IMM(BPF_REG_1, 5),
+	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_hash_16b = { 5 },
+	.fixup_map_array_48b = { 8 },
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+	.result = ACCEPT,
+	.retval = 1,
+},
+{
+	"map access: known scalar += value_ptr const vs const (eq)",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+		    offsetof(struct __sk_buff, len)),
+	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_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+	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, 7),
+	BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2),
+	BPF_MOV64_IMM(BPF_REG_1, 5),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_MOV64_IMM(BPF_REG_1, 5),
+	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_hash_16b = { 5 },
+	.fixup_map_array_48b = { 8 },
+	.result = ACCEPT,
+	.retval = 1,
+},
+{
+	"map access: known scalar += value_ptr unknown vs unknown (eq)",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+		    offsetof(struct __sk_buff, len)),
+	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_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+	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, 11),
+	BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
+	BPF_MOV64_IMM(BPF_REG_1, 6),
+	BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 3),
+	BPF_MOV64_IMM(BPF_REG_1, 6),
+	BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+	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_hash_16b = { 5 },
+	.fixup_map_array_48b = { 8 },
+	.result = ACCEPT,
+	.retval = 1,
+},
+{
+	"map access: known scalar += value_ptr unknown vs unknown (lt)",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+		    offsetof(struct __sk_buff, len)),
+	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_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+	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, 11),
+	BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
+	BPF_MOV64_IMM(BPF_REG_1, 6),
+	BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x3),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 3),
+	BPF_MOV64_IMM(BPF_REG_1, 6),
+	BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+	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_hash_16b = { 5 },
+	.fixup_map_array_48b = { 8 },
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+	.result = ACCEPT,
+	.retval = 1,
+},
+{
+	"map access: known scalar += value_ptr unknown vs unknown (gt)",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+		    offsetof(struct __sk_buff, len)),
+	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_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+	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, 11),
+	BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
+	BPF_MOV64_IMM(BPF_REG_1, 6),
+	BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 3),
+	BPF_MOV64_IMM(BPF_REG_1, 6),
+	BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x3),
+	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_hash_16b = { 5 },
+	.fixup_map_array_48b = { 8 },
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+	.result = ACCEPT,
+	.retval = 1,
+},
+{
 	"map access: known scalar += value_ptr from different maps",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 0709af0144c8..98053d3afbda 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 /aarch64/debug-exceptions
 /aarch64/get-reg-list
+/aarch64/psci_cpu_on_test
 /aarch64/vgic_init
 /s390x/memop
 /s390x/resets
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 5832f510a16c..5d05801ab816 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -86,6 +86,7 @@ TEST_GEN_PROGS_x86_64 += kvm_binary_stats_test
 
 TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions
 TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
+TEST_GEN_PROGS_aarch64 += aarch64/psci_cpu_on_test
 TEST_GEN_PROGS_aarch64 += aarch64/vgic_init
 TEST_GEN_PROGS_aarch64 += demand_paging_test
 TEST_GEN_PROGS_aarch64 += dirty_log_test
diff --git a/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c b/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c
new file mode 100644
index 000000000000..018c269990e1
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c
@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * psci_cpu_on_test - Test that the observable state of a vCPU targeted by the
+ * CPU_ON PSCI call matches what the caller requested.
+ *
+ * Copyright (c) 2021 Google LLC.
+ *
+ * This is a regression test for a race between KVM servicing the PSCI call and
+ * userspace reading the vCPUs registers.
+ */
+
+#define _GNU_SOURCE
+
+#include <linux/psci.h>
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "test_util.h"
+
+#define VCPU_ID_SOURCE 0
+#define VCPU_ID_TARGET 1
+
+#define CPU_ON_ENTRY_ADDR 0xfeedf00dul
+#define CPU_ON_CONTEXT_ID 0xdeadc0deul
+
+static uint64_t psci_cpu_on(uint64_t target_cpu, uint64_t entry_addr,
+			    uint64_t context_id)
+{
+	register uint64_t x0 asm("x0") = PSCI_0_2_FN64_CPU_ON;
+	register uint64_t x1 asm("x1") = target_cpu;
+	register uint64_t x2 asm("x2") = entry_addr;
+	register uint64_t x3 asm("x3") = context_id;
+
+	asm("hvc #0"
+	    : "=r"(x0)
+	    : "r"(x0), "r"(x1), "r"(x2), "r"(x3)
+	    : "memory");
+
+	return x0;
+}
+
+static uint64_t psci_affinity_info(uint64_t target_affinity,
+				   uint64_t lowest_affinity_level)
+{
+	register uint64_t x0 asm("x0") = PSCI_0_2_FN64_AFFINITY_INFO;
+	register uint64_t x1 asm("x1") = target_affinity;
+	register uint64_t x2 asm("x2") = lowest_affinity_level;
+
+	asm("hvc #0"
+	    : "=r"(x0)
+	    : "r"(x0), "r"(x1), "r"(x2)
+	    : "memory");
+
+	return x0;
+}
+
+static void guest_main(uint64_t target_cpu)
+{
+	GUEST_ASSERT(!psci_cpu_on(target_cpu, CPU_ON_ENTRY_ADDR, CPU_ON_CONTEXT_ID));
+	uint64_t target_state;
+
+	do {
+		target_state = psci_affinity_info(target_cpu, 0);
+
+		GUEST_ASSERT((target_state == PSCI_0_2_AFFINITY_LEVEL_ON) ||
+			     (target_state == PSCI_0_2_AFFINITY_LEVEL_OFF));
+	} while (target_state != PSCI_0_2_AFFINITY_LEVEL_ON);
+
+	GUEST_DONE();
+}
+
+int main(void)
+{
+	uint64_t target_mpidr, obs_pc, obs_x0;
+	struct kvm_vcpu_init init;
+	struct kvm_vm *vm;
+	struct ucall uc;
+
+	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+	kvm_vm_elf_load(vm, program_invocation_name);
+	ucall_init(vm, NULL);
+
+	vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init);
+	init.features[0] |= (1 << KVM_ARM_VCPU_PSCI_0_2);
+
+	aarch64_vcpu_add_default(vm, VCPU_ID_SOURCE, &init, guest_main);
+
+	/*
+	 * make sure the target is already off when executing the test.
+	 */
+	init.features[0] |= (1 << KVM_ARM_VCPU_POWER_OFF);
+	aarch64_vcpu_add_default(vm, VCPU_ID_TARGET, &init, guest_main);
+
+	get_reg(vm, VCPU_ID_TARGET, ARM64_SYS_REG(MPIDR_EL1), &target_mpidr);
+	vcpu_args_set(vm, VCPU_ID_SOURCE, 1, target_mpidr & MPIDR_HWID_BITMASK);
+	vcpu_run(vm, VCPU_ID_SOURCE);
+
+	switch (get_ucall(vm, VCPU_ID_SOURCE, &uc)) {
+	case UCALL_DONE:
+		break;
+	case UCALL_ABORT:
+		TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], __FILE__,
+			  uc.args[1]);
+		break;
+	default:
+		TEST_FAIL("Unhandled ucall: %lu", uc.cmd);
+	}
+
+	get_reg(vm, VCPU_ID_TARGET, ARM64_CORE_REG(regs.pc), &obs_pc);
+	get_reg(vm, VCPU_ID_TARGET, ARM64_CORE_REG(regs.regs[0]), &obs_x0);
+
+	TEST_ASSERT(obs_pc == CPU_ON_ENTRY_ADDR,
+		    "unexpected target cpu pc: %lx (expected: %lx)",
+		    obs_pc, CPU_ON_ENTRY_ADDR);
+	TEST_ASSERT(obs_x0 == CPU_ON_CONTEXT_ID,
+		    "unexpected target context id: %lx (expected: %lx)",
+		    obs_x0, CPU_ON_CONTEXT_ID);
+
+	kvm_vm_free(vm);
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
index 27dc5c2e56b9..c0273aefa63d 100644
--- a/tools/testing/selftests/kvm/include/aarch64/processor.h
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -17,6 +17,7 @@
 #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 MPIDR_EL1               3, 0,  0, 0, 5
 #define TTBR0_EL1               3, 0,  2, 0, 0
 #define SCTLR_EL1               3, 0,  1, 0, 0
 #define VBAR_EL1                3, 0, 12, 0, 0
@@ -40,6 +41,8 @@
 			  (0xfful << (4 * 8)) | \
 			  (0xbbul << (5 * 8)))
 
+#define MPIDR_HWID_BITMASK (0xff00fffffful)
+
 static inline void get_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, uint64_t *addr)
 {
 	struct kvm_one_reg reg;
diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c
index 6365c7fd1262..bd6288302094 100644
--- a/tools/testing/selftests/net/nettest.c
+++ b/tools/testing/selftests/net/nettest.c
@@ -11,9 +11,11 @@
 #include <sys/socket.h>
 #include <sys/wait.h>
 #include <linux/tcp.h>
+#include <linux/udp.h>
 #include <arpa/inet.h>
 #include <net/if.h>
 #include <netinet/in.h>
+#include <netinet/ip.h>
 #include <netdb.h>
 #include <fcntl.h>
 #include <libgen.h>
@@ -27,6 +29,10 @@
 #include <time.h>
 #include <errno.h>
 
+#include <linux/xfrm.h>
+#include <linux/ipsec.h>
+#include <linux/pfkeyv2.h>
+
 #ifndef IPV6_UNICAST_IF
 #define IPV6_UNICAST_IF         76
 #endif
@@ -114,6 +120,9 @@ struct sock_args {
 		struct in_addr  in;
 		struct in6_addr in6;
 	} expected_raddr;
+
+	/* ESP in UDP encap test */
+	int use_xfrm;
 };
 
 static int server_mode;
@@ -1346,6 +1355,41 @@ static int bind_socket(int sd, struct sock_args *args)
 	return 0;
 }
 
+static int config_xfrm_policy(int sd, struct sock_args *args)
+{
+	struct xfrm_userpolicy_info policy = {};
+	int type = UDP_ENCAP_ESPINUDP;
+	int xfrm_af = IP_XFRM_POLICY;
+	int level = SOL_IP;
+
+	if (args->type != SOCK_DGRAM) {
+		log_error("Invalid socket type. Only DGRAM could be used for XFRM\n");
+		return 1;
+	}
+
+	policy.action = XFRM_POLICY_ALLOW;
+	policy.sel.family = args->version;
+	if (args->version == AF_INET6) {
+		xfrm_af = IPV6_XFRM_POLICY;
+		level = SOL_IPV6;
+	}
+
+	policy.dir = XFRM_POLICY_OUT;
+	if (setsockopt(sd, level, xfrm_af, &policy, sizeof(policy)) < 0)
+		return 1;
+
+	policy.dir = XFRM_POLICY_IN;
+	if (setsockopt(sd, level, xfrm_af, &policy, sizeof(policy)) < 0)
+		return 1;
+
+	if (setsockopt(sd, IPPROTO_UDP, UDP_ENCAP, &type, sizeof(type)) < 0) {
+		log_err_errno("Failed to set xfrm encap");
+		return 1;
+	}
+
+	return 0;
+}
+
 static int lsock_init(struct sock_args *args)
 {
 	long flags;
@@ -1389,6 +1433,11 @@ static int lsock_init(struct sock_args *args)
 	if (fcntl(sd, F_SETFD, FD_CLOEXEC) < 0)
 		log_err_errno("Failed to set close-on-exec flag");
 
+	if (args->use_xfrm && config_xfrm_policy(sd, args)) {
+		log_err_errno("Failed to set xfrm policy");
+		goto err;
+	}
+
 out:
 	return sd;
 
@@ -1772,7 +1821,7 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args)
 	return client_status;
 }
 
-#define GETOPT_STR  "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6L:0:1:2:3:Fbq"
+#define GETOPT_STR  "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6xL:0:1:2:3:Fbq"
 
 static void print_usage(char *prog)
 {
@@ -1795,6 +1844,7 @@ static void print_usage(char *prog)
 	"    -D|R          datagram (D) / raw (R) socket (default stream)\n"
 	"    -l addr       local address to bind to in server mode\n"
 	"    -c addr       local address to bind to in client mode\n"
+	"    -x            configure XFRM policy on socket\n"
 	"\n"
 	"    -d dev        bind socket to given device name\n"
 	"    -I dev        bind socket to given device name - server mode\n"
@@ -1966,6 +2016,9 @@ int main(int argc, char *argv[])
 		case 'q':
 			quiet = 1;
 			break;
+		case 'x':
+			args.use_xfrm = 1;
+			break;
 		default:
 			print_usage(argv[0]);
 			return 1;
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 64cd2e23c568..543ad7513a8e 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -118,6 +118,16 @@
 #	below for IPv6 doesn't apply here, because, on IPv4, administrative MTU
 #	changes alone won't affect PMTU
 #
+# - pmtu_vti4_udp_exception
+#       Same as pmtu_vti4_exception, but using ESP-in-UDP
+#
+# - pmtu_vti4_udp_routed_exception
+#       Set up vti tunnel on top of veth connected through routing namespace and
+#	add xfrm states and policies with ESP-in-UDP encapsulation. Check that
+#	route exception is not created if link layer MTU is not exceeded, then
+#	lower MTU on second part of routed environment and check that exception
+#	is created with the expected PMTU.
+#
 # - pmtu_vti6_exception
 #	Set up vti6 tunnel on top of veth, with xfrm states and policies, in two
 #	namespaces with matching endpoints. Check that route exception is
@@ -125,6 +135,13 @@
 #	decrease and increase MTU of tunnel, checking that route exception PMTU
 #	changes accordingly
 #
+# - pmtu_vti6_udp_exception
+#       Same as pmtu_vti6_exception, but using ESP-in-UDP
+#
+# - pmtu_vti6_udp_routed_exception
+#	Same as pmtu_vti6_udp_routed_exception but with routing between vti
+#	endpoints
+#
 # - pmtu_vti4_default_mtu
 #	Set up vti4 tunnel on top of veth, in two namespaces with matching
 #	endpoints. Check that MTU assigned to vti interface is the MTU of the
@@ -224,6 +241,10 @@ tests="
 	pmtu_ipv6_ipv6_exception	IPv6 over IPv6: PMTU exceptions		1
 	pmtu_vti6_exception		vti6: PMTU exceptions			0
 	pmtu_vti4_exception		vti4: PMTU exceptions			0
+	pmtu_vti6_udp_exception		vti6: PMTU exceptions (ESP-in-UDP)	0
+	pmtu_vti4_udp_exception		vti4: PMTU exceptions (ESP-in-UDP)	0
+	pmtu_vti6_udp_routed_exception	vti6: PMTU exceptions, routed (ESP-in-UDP)	0
+	pmtu_vti4_udp_routed_exception	vti4: PMTU exceptions, routed (ESP-in-UDP)	0
 	pmtu_vti4_default_mtu		vti4: default MTU assignment		0
 	pmtu_vti6_default_mtu		vti6: default MTU assignment		0
 	pmtu_vti4_link_add_mtu		vti4: MTU setting on link creation	0
@@ -246,7 +267,6 @@ ns_b="ip netns exec ${NS_B}"
 ns_c="ip netns exec ${NS_C}"
 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).
@@ -279,7 +299,6 @@ routes="
 	A	${prefix6}:${b_r2}::1	${prefix6}:${a_r2}::2
 	B	default			${prefix6}:${b_r1}::2
 "
-
 USE_NH="no"
 #	ns	family	nh id	   destination		gateway
 nexthops="
@@ -326,6 +345,7 @@ dummy6_mask="64"
 
 err_buf=
 tcpdump_pids=
+nettest_pids=
 
 err() {
 	err_buf="${err_buf}${1}
@@ -548,6 +568,14 @@ setup_vti6() {
 	setup_vti 6 ${veth6_a_addr} ${veth6_b_addr} ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask}
 }
 
+setup_vti4routed() {
+	setup_vti 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 ${tunnel4_a_addr} ${tunnel4_b_addr} ${tunnel4_mask}
+}
+
+setup_vti6routed() {
+	setup_vti 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask}
+}
+
 setup_vxlan_or_geneve() {
 	type="${1}"
 	a_addr="${2}"
@@ -619,18 +647,36 @@ setup_xfrm() {
 	proto=${1}
 	veth_a_addr="${2}"
 	veth_b_addr="${3}"
+	encap=${4}
 
-	run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel || return 1
-	run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
+	run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap} || return 1
+	run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap}
 	run_cmd ${ns_a} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel
 	run_cmd ${ns_a} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel
 
-	run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
-	run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
+	run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap}
+	run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap}
 	run_cmd ${ns_b} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel
 	run_cmd ${ns_b} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel
 }
 
+setup_nettest_xfrm() {
+	which nettest >/dev/null
+	if [ $? -ne 0 ]; then
+		echo "'nettest' command not found; skipping tests"
+	        return 1
+	fi
+
+	[ ${1} -eq 6 ] && proto="-6" || proto=""
+	port=${2}
+
+	run_cmd ${ns_a} nettest ${proto} -q -D -s -x -p ${port} -t 5 &
+	nettest_pids="${nettest_pids} $!"
+
+	run_cmd ${ns_b} nettest ${proto} -q -D -s -x -p ${port} -t 5 &
+	nettest_pids="${nettest_pids} $!"
+}
+
 setup_xfrm4() {
 	setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr}
 }
@@ -639,6 +685,26 @@ setup_xfrm6() {
 	setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr}
 }
 
+setup_xfrm4udp() {
+	setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0"
+	setup_nettest_xfrm 4 4500
+}
+
+setup_xfrm6udp() {
+	setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0"
+	setup_nettest_xfrm 6 4500
+}
+
+setup_xfrm4udprouted() {
+	setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0"
+	setup_nettest_xfrm 4 4500
+}
+
+setup_xfrm6udprouted() {
+	setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0"
+	setup_nettest_xfrm 6 4500
+}
+
 setup_routing_old() {
 	for i in ${routes}; do
 		[ "${ns}" = "" ]	&& ns="${i}"		&& continue
@@ -823,6 +889,11 @@ cleanup() {
 	done
 	tcpdump_pids=
 
+	for pid in ${nettest_pids}; do
+		kill ${pid}
+	done
+	nettest_pids=
+
 	for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do
 		ip netns del ${n} 2> /dev/null
 	done
@@ -1432,6 +1503,135 @@ test_pmtu_vti6_exception() {
 	return ${fail}
 }
 
+test_pmtu_vti4_udp_exception() {
+	setup namespaces veth vti4 xfrm4udp || return $ksft_skip
+	trace "${ns_a}" veth_a    "${ns_b}" veth_b \
+	      "${ns_a}" vti4_a    "${ns_b}" vti4_b
+
+	veth_mtu=1500
+	vti_mtu=$((veth_mtu - 20))
+
+	#                                UDP   SPI   SN   IV  ICV   pad length   next header
+	esp_payload_rfc4106=$((vti_mtu - 8   - 4   - 4  - 8 - 16  - 1          - 1))
+	ping_payload=$((esp_payload_rfc4106 - 28))
+
+	mtu "${ns_a}" veth_a ${veth_mtu}
+	mtu "${ns_b}" veth_b ${veth_mtu}
+	mtu "${ns_a}" vti4_a ${vti_mtu}
+	mtu "${ns_b}" vti4_b ${vti_mtu}
+
+	# Send DF packet without exceeding link layer MTU, check that no
+	# exception is created
+	run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr}
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
+	check_pmtu_value "" "${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
+	run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload + 1)) ${tunnel4_b_addr}
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
+	check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))"
+}
+
+test_pmtu_vti6_udp_exception() {
+	setup namespaces veth vti6 xfrm6udp || return $ksft_skip
+	trace "${ns_a}" veth_a    "${ns_b}" veth_b \
+	      "${ns_a}" vti6_a    "${ns_b}" vti6_b
+	fail=0
+
+	# Create route exception by exceeding link layer MTU
+	mtu "${ns_a}" veth_a 4000
+	mtu "${ns_b}" veth_b 4000
+	mtu "${ns_a}" vti6_a 5000
+	mtu "${ns_b}" vti6_b 5000
+	run_cmd ${ns_a} ${ping6} -q -i 0.1 -w 1 -s 60000 ${tunnel6_b_addr}
+
+	# Check that exception was created
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+	check_pmtu_value any "${pmtu}" "creating tunnel exceeding link layer MTU" || return 1
+
+	# Decrease tunnel MTU, check for PMTU decrease in route exception
+	mtu "${ns_a}" vti6_a 3000
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+	check_pmtu_value "3000" "${pmtu}" "decreasing tunnel MTU" || fail=1
+
+	# Increase tunnel MTU, check for PMTU increase in route exception
+	mtu "${ns_a}" vti6_a 9000
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+	check_pmtu_value "9000" "${pmtu}" "increasing tunnel MTU" || fail=1
+
+	return ${fail}
+}
+
+test_pmtu_vti4_udp_routed_exception() {
+	setup namespaces routing vti4routed xfrm4udprouted || return $ksft_skip
+	trace "${ns_a}" veth_A-R1    "${ns_b}" veth_B-R1 \
+	      "${ns_a}" vti4_a       "${ns_b}" vti4_b
+
+	veth_mtu=1500
+	vti_mtu=$((veth_mtu - 20))
+
+	#                                UDP   SPI   SN   IV  ICV   pad length   next header
+	esp_payload_rfc4106=$((vti_mtu - 8   - 4   - 4  - 8 - 16  - 1          - 1))
+	ping_payload=$((esp_payload_rfc4106 - 28))
+
+        mtu "${ns_a}"  veth_A-R1 ${veth_mtu}
+        mtu "${ns_r1}" veth_R1-A ${veth_mtu}
+        mtu "${ns_b}"  veth_B-R1 ${veth_mtu}
+        mtu "${ns_r1}" veth_R1-B ${veth_mtu}
+
+	mtu "${ns_a}" vti4_a ${vti_mtu}
+	mtu "${ns_b}" vti4_b ${vti_mtu}
+
+	# Send DF packet without exceeding link layer MTU, check that no
+	# exception is created
+	run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr}
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
+	check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
+
+	# Now decrease link layer MTU by 8 bytes on R1, check that exception is created
+	# with the right PMTU value
+        mtu "${ns_r1}" veth_R1-B $((veth_mtu - 8))
+	run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload)) ${tunnel4_b_addr}
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
+	check_pmtu_value "$((esp_payload_rfc4106 - 8))" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106)))"
+}
+
+test_pmtu_vti6_udp_routed_exception() {
+	setup namespaces routing vti6routed xfrm6udprouted || return $ksft_skip
+	trace "${ns_a}" veth_A-R1    "${ns_b}" veth_B-R1 \
+	      "${ns_a}" vti6_a       "${ns_b}" vti6_b
+
+	veth_mtu=1500
+	vti_mtu=$((veth_mtu - 40))
+
+	#                                UDP   SPI   SN   IV  ICV   pad length   next header
+	esp_payload_rfc4106=$((vti_mtu - 8   - 4   - 4  - 8 - 16  - 1          - 1))
+	ping_payload=$((esp_payload_rfc4106 - 48))
+
+        mtu "${ns_a}"  veth_A-R1 ${veth_mtu}
+        mtu "${ns_r1}" veth_R1-A ${veth_mtu}
+        mtu "${ns_b}"  veth_B-R1 ${veth_mtu}
+        mtu "${ns_r1}" veth_R1-B ${veth_mtu}
+
+	# mtu "${ns_a}" vti6_a ${vti_mtu}
+	# mtu "${ns_b}" vti6_b ${vti_mtu}
+
+	run_cmd ${ns_a} ${ping6} -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel6_b_addr}
+
+	# Check that exception was not created
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+	check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
+
+	# Now decrease link layer MTU by 8 bytes on R1, check that exception is created
+	# with the right PMTU value
+        mtu "${ns_r1}" veth_R1-B $((veth_mtu - 8))
+	run_cmd ${ns_a} ${ping6} -q -M want -i 0.1 -w 1 -s $((ping_payload)) ${tunnel6_b_addr}
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+	check_pmtu_value "$((esp_payload_rfc4106 - 8))" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106)))"
+
+}
+
 test_pmtu_vti4_default_mtu() {
 	setup namespaces veth vti4 || return $ksft_skip
 
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index e363bdaff59d..2ea438e6b8b1 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -210,8 +210,10 @@ static void anon_release_pages(char *rel_area)
 
 static void anon_allocate_area(void **alloc_area)
 {
-	if (posix_memalign(alloc_area, page_size, nr_pages * page_size))
-		err("posix_memalign() failed");
+	*alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
+			   MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	if (*alloc_area == MAP_FAILED)
+		err("mmap of anonymous memory failed");
 }
 
 static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset)