Merge tag 'v5.1-rc6' into for-5.2/block

Pull in v5.1-rc6 to resolve two conflicts. One is in BFQ, in just a
comment, and is trivial. The other one is a conflict due to a later fix
in the bio multi-page work, and needs a bit more care.

* tag 'v5.1-rc6': (770 commits)
  Linux 5.1-rc6
  block: make sure that bvec length can't be overflow
  block: kill all_q_node in request_queue
  x86/cpu/intel: Lower the "ENERGY_PERF_BIAS: Set to normal" message's log priority
  coredump: fix race condition between mmget_not_zero()/get_task_mm() and core dumping
  mm/kmemleak.c: fix unused-function warning
  init: initialize jump labels before command line option parsing
  kernel/watchdog_hld.c: hard lockup message should end with a newline
  kcov: improve CONFIG_ARCH_HAS_KCOV help text
  mm: fix inactive list balancing between NUMA nodes and cgroups
  mm/hotplug: treat CMA pages as unmovable
  proc: fixup proc-pid-vm test
  proc: fix map_files test on F29
  mm/vmstat.c: fix /proc/vmstat format for CONFIG_DEBUG_TLBFLUSH=y CONFIG_SMP=n
  mm/memory_hotplug: do not unlock after failing to take the device_hotplug_lock
  mm: swapoff: shmem_unuse() stop eviction without igrab()
  mm: swapoff: take notice of completion sooner
  mm: swapoff: remove too limiting SWAP_UNUSE_MAX_TRIES
  mm: swapoff: shmem_find_swap_entries() filter out other types
  slab: store tagged freelist for off-slab slabmgmt
  ...

Signed-off-by: Jens Axboe <axboe@kernel.dk>

tools/testing/nvdimm/test/nfit.c

@@ -146,6 +146,7 @@ static int dimm_fail_cmd_code[ARRAY_SIZE(handle)];
 struct nfit_test_sec {
 	u8 state;
 	u8 ext_state;
+	u8 old_state;
 	u8 passphrase[32];
 	u8 master_passphrase[32];
 	u64 overwrite_end_time;
@@ -225,6 +226,8 @@ static struct workqueue_struct *nfit_wq;
 
 static struct gen_pool *nfit_pool;
 
+static const char zero_key[NVDIMM_PASSPHRASE_LEN];
+
 static struct nfit_test *to_nfit_test(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
@@ -1059,8 +1062,7 @@ static int nd_intel_test_cmd_secure_erase(struct nfit_test *t,
 	struct device *dev = &t->pdev.dev;
 	struct nfit_test_sec *sec = &dimm_sec_info[dimm];
 
-	if (!(sec->state & ND_INTEL_SEC_STATE_ENABLED) ||
-			(sec->state & ND_INTEL_SEC_STATE_FROZEN)) {
+	if (sec->state & ND_INTEL_SEC_STATE_FROZEN) {
 		nd_cmd->status = ND_INTEL_STATUS_INVALID_STATE;
 		dev_dbg(dev, "secure erase: wrong security state\n");
 	} else if (memcmp(nd_cmd->passphrase, sec->passphrase,
@@ -1068,6 +1070,12 @@ static int nd_intel_test_cmd_secure_erase(struct nfit_test *t,
 		nd_cmd->status = ND_INTEL_STATUS_INVALID_PASS;
 		dev_dbg(dev, "secure erase: wrong passphrase\n");
 	} else {
+		if (!(sec->state & ND_INTEL_SEC_STATE_ENABLED)
+				&& (memcmp(nd_cmd->passphrase, zero_key,
+					ND_INTEL_PASSPHRASE_SIZE) != 0)) {
+			dev_dbg(dev, "invalid zero key\n");
+			return 0;
+		}
 		memset(sec->passphrase, 0, ND_INTEL_PASSPHRASE_SIZE);
 		memset(sec->master_passphrase, 0, ND_INTEL_PASSPHRASE_SIZE);
 		sec->state = 0;
@@ -1093,7 +1101,7 @@ static int nd_intel_test_cmd_overwrite(struct nfit_test *t,
 		return 0;
 	}
 
-	memset(sec->passphrase, 0, ND_INTEL_PASSPHRASE_SIZE);
+	sec->old_state = sec->state;
 	sec->state = ND_INTEL_SEC_STATE_OVERWRITE;
 	dev_dbg(dev, "overwrite progressing.\n");
 	sec->overwrite_end_time = get_jiffies_64() + 5 * HZ;
@@ -1115,7 +1123,8 @@ static int nd_intel_test_cmd_query_overwrite(struct nfit_test *t,
 
 	if (time_is_before_jiffies64(sec->overwrite_end_time)) {
 		sec->overwrite_end_time = 0;
-		sec->state = 0;
+		sec->state = sec->old_state;
+		sec->old_state = 0;
 		sec->ext_state = ND_INTEL_SEC_ESTATE_ENABLED;
 		dev_dbg(dev, "overwrite is complete\n");
 	} else

tools/testing/selftests/bpf/prog_tests/flow_dissector.c

@@ -39,6 +39,58 @@ static struct bpf_flow_keys pkt_v6_flow_keys = {
 	.n_proto = __bpf_constant_htons(ETH_P_IPV6),
 };
 
+#define VLAN_HLEN	4
+
+static struct {
+	struct ethhdr eth;
+	__u16 vlan_tci;
+	__u16 vlan_proto;
+	struct iphdr iph;
+	struct tcphdr tcp;
+} __packed pkt_vlan_v4 = {
+	.eth.h_proto = __bpf_constant_htons(ETH_P_8021Q),
+	.vlan_proto = __bpf_constant_htons(ETH_P_IP),
+	.iph.ihl = 5,
+	.iph.protocol = IPPROTO_TCP,
+	.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+	.tcp.urg_ptr = 123,
+	.tcp.doff = 5,
+};
+
+static struct bpf_flow_keys pkt_vlan_v4_flow_keys = {
+	.nhoff = VLAN_HLEN,
+	.thoff = VLAN_HLEN + sizeof(struct iphdr),
+	.addr_proto = ETH_P_IP,
+	.ip_proto = IPPROTO_TCP,
+	.n_proto = __bpf_constant_htons(ETH_P_IP),
+};
+
+static struct {
+	struct ethhdr eth;
+	__u16 vlan_tci;
+	__u16 vlan_proto;
+	__u16 vlan_tci2;
+	__u16 vlan_proto2;
+	struct ipv6hdr iph;
+	struct tcphdr tcp;
+} __packed pkt_vlan_v6 = {
+	.eth.h_proto = __bpf_constant_htons(ETH_P_8021AD),
+	.vlan_proto = __bpf_constant_htons(ETH_P_8021Q),
+	.vlan_proto2 = __bpf_constant_htons(ETH_P_IPV6),
+	.iph.nexthdr = IPPROTO_TCP,
+	.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+	.tcp.urg_ptr = 123,
+	.tcp.doff = 5,
+};
+
+static struct bpf_flow_keys pkt_vlan_v6_flow_keys = {
+	.nhoff = VLAN_HLEN * 2,
+	.thoff = VLAN_HLEN * 2 + sizeof(struct ipv6hdr),
+	.addr_proto = ETH_P_IPV6,
+	.ip_proto = IPPROTO_TCP,
+	.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+};
+
 void test_flow_dissector(void)
 {
 	struct bpf_flow_keys flow_keys;
@@ -68,5 +120,21 @@ void test_flow_dissector(void)
 	      err, errno, retval, duration, size, sizeof(flow_keys));
 	CHECK_FLOW_KEYS("ipv6_flow_keys", flow_keys, pkt_v6_flow_keys);
 
+	err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v4, sizeof(pkt_vlan_v4),
+				&flow_keys, &size, &retval, &duration);
+	CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv4",
+	      "err %d errno %d retval %d duration %d size %u/%lu\n",
+	      err, errno, retval, duration, size, sizeof(flow_keys));
+	CHECK_FLOW_KEYS("vlan_ipv4_flow_keys", flow_keys,
+			pkt_vlan_v4_flow_keys);
+
+	err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v6, sizeof(pkt_vlan_v6),
+				&flow_keys, &size, &retval, &duration);
+	CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv6",
+	      "err %d errno %d retval %d duration %d size %u/%lu\n",
+	      err, errno, retval, duration, size, sizeof(flow_keys));
+	CHECK_FLOW_KEYS("vlan_ipv6_flow_keys", flow_keys,
+			pkt_vlan_v6_flow_keys);
+
 	bpf_object__close(obj);
 }

tools/testing/selftests/bpf/progs/bpf_flow.c

@@ -92,7 +92,6 @@ 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);
@@ -119,10 +118,9 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)
 SEC("flow_dissector")
 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);
+	struct bpf_flow_keys *keys = skb->flow_keys;
+
+	return parse_eth_proto(skb, keys->n_proto);
 }
 
 /* Parses on IPPROTO_* */
@@ -336,15 +334,9 @@ 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->thoff - sizeof(proto), &proto,
-			       sizeof(proto)))
-		return BPF_DROP;
 
 	/* Account for double-tagging */
-	if (proto == bpf_htons(ETH_P_8021AD)) {
+	if (keys->n_proto == bpf_htons(ETH_P_8021AD)) {
 		vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan);
 		if (!vlan)
 			return BPF_DROP;
@@ -352,6 +344,7 @@ PROG(VLAN)(struct __sk_buff *skb)
 		if (vlan->h_vlan_encapsulated_proto != bpf_htons(ETH_P_8021Q))
 			return BPF_DROP;
 
+		keys->nhoff += sizeof(*vlan);
 		keys->thoff += sizeof(*vlan);
 	}
 
@@ -359,12 +352,14 @@ PROG(VLAN)(struct __sk_buff *skb)
 	if (!vlan)
 		return BPF_DROP;
 
+	keys->nhoff += sizeof(*vlan);
 	keys->thoff += 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;
 
+	keys->n_proto = vlan->h_vlan_encapsulated_proto;
 	return parse_eth_proto(skb, vlan->h_vlan_encapsulated_proto);
 }
 

tools/testing/selftests/bpf/test_btf.c

@@ -5776,6 +5776,53 @@ const struct btf_dedup_test dedup_tests[] = {
 		.dedup_table_size = 1, /* force hash collisions */
 	},
 },
+{
+	.descr = "dedup: void equiv check",
+	/*
+	 * // CU 1:
+	 * struct s {
+	 *	struct {} *x;
+	 * };
+	 * // CU 2:
+	 * struct s {
+	 *	int *x;
+	 * };
+	 */
+	.input = {
+		.raw_types = {
+			/* CU 1 */
+			BTF_STRUCT_ENC(0, 0, 1),				/* [1] struct {}  */
+			BTF_PTR_ENC(1),						/* [2] ptr -> [1] */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 8),			/* [3] struct s   */
+				BTF_MEMBER_ENC(NAME_NTH(2), 2, 0),
+			/* CU 2 */
+			BTF_PTR_ENC(0),						/* [4] ptr -> void */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 8),			/* [5] struct s   */
+				BTF_MEMBER_ENC(NAME_NTH(2), 4, 0),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0s\0x"),
+	},
+	.expect = {
+		.raw_types = {
+			/* CU 1 */
+			BTF_STRUCT_ENC(0, 0, 1),				/* [1] struct {}  */
+			BTF_PTR_ENC(1),						/* [2] ptr -> [1] */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 8),			/* [3] struct s   */
+				BTF_MEMBER_ENC(NAME_NTH(2), 2, 0),
+			/* CU 2 */
+			BTF_PTR_ENC(0),						/* [4] ptr -> void */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 8),			/* [5] struct s   */
+				BTF_MEMBER_ENC(NAME_NTH(2), 4, 0),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0s\0x"),
+	},
+	.opts = {
+		.dont_resolve_fwds = false,
+		.dedup_table_size = 1, /* force hash collisions */
+	},
+},
 {
 	.descr = "dedup: all possible kinds (no duplicates)",
 	.input = {

tools/testing/selftests/bpf/verifier/calls.c

@@ -907,6 +907,44 @@
 	.errstr = "call stack",
 	.result = REJECT,
 },
+{
+	"calls: stack depth check in dead code",
+	.insns = {
+	/* main */
+	BPF_MOV64_IMM(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call A */
+	BPF_EXIT_INSN(),
+	/* A */
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 2), /* call B */
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	/* B */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call C */
+	BPF_EXIT_INSN(),
+	/* C */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call D */
+	BPF_EXIT_INSN(),
+	/* D */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call E */
+	BPF_EXIT_INSN(),
+	/* E */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call F */
+	BPF_EXIT_INSN(),
+	/* F */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call G */
+	BPF_EXIT_INSN(),
+	/* G */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call H */
+	BPF_EXIT_INSN(),
+	/* H */
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.errstr = "call stack",
+	.result = REJECT,
+},
 {
 	"calls: spill into caller stack frame",
 	.insns = {

tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh

@@ -11,6 +11,7 @@ lib_dir=$(dirname $0)/../../../net/forwarding
 
 ALL_TESTS="
 	rif_set_addr_test
+	rif_vrf_set_addr_test
 	rif_inherit_bridge_addr_test
 	rif_non_inherit_bridge_addr_test
 	vlan_interface_deletion_test
@@ -98,6 +99,25 @@ rif_set_addr_test()
 	ip link set dev $swp1 addr $swp1_mac
 }
 
+rif_vrf_set_addr_test()
+{
+	# Test that it is possible to set an IP address on a VRF upper despite
+	# its random MAC address.
+	RET=0
+
+	ip link add name vrf-test type vrf table 10
+	ip link set dev $swp1 master vrf-test
+
+	ip -4 address add 192.0.2.1/24 dev vrf-test
+	check_err $? "failed to set IPv4 address on VRF"
+	ip -6 address add 2001:db8:1::1/64 dev vrf-test
+	check_err $? "failed to set IPv6 address on VRF"
+
+	log_test "RIF - setting IP address on VRF"
+
+	ip link del dev vrf-test
+}
+
 rif_inherit_bridge_addr_test()
 {
 	RET=0

tools/testing/selftests/kvm/Makefile

@@ -1,3 +1,5 @@
+include ../../../../scripts/Kbuild.include
+
 all:
 
 top_srcdir = ../../../..
@@ -17,6 +19,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/state_test
 TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
+TEST_GEN_PROGS_x86_64 += x86_64/smm_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
 TEST_GEN_PROGS_x86_64 += clear_dirty_log_test
 
@@ -30,7 +33,11 @@ INSTALL_HDR_PATH = $(top_srcdir)/usr
 LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
 LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include
 CFLAGS += -O2 -g -std=gnu99 -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I..
-LDFLAGS += -pthread -no-pie
+
+no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \
+        $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)
+
+LDFLAGS += -pthread $(no-pie-option)
 
 # After inclusion, $(OUTPUT) is defined and
 # $(TEST_GEN_PROGS) starts with $(OUTPUT)/

tools/testing/selftests/kvm/include/x86_64/processor.h

@@ -778,6 +778,33 @@ void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
 #define MSR_IA32_APICBASE_ENABLE	(1<<11)
 #define MSR_IA32_APICBASE_BASE		(0xfffff<<12)
 
+#define APIC_BASE_MSR	0x800
+#define X2APIC_ENABLE	(1UL << 10)
+#define	APIC_ICR	0x300
+#define		APIC_DEST_SELF		0x40000
+#define		APIC_DEST_ALLINC	0x80000
+#define		APIC_DEST_ALLBUT	0xC0000
+#define		APIC_ICR_RR_MASK	0x30000
+#define		APIC_ICR_RR_INVALID	0x00000
+#define		APIC_ICR_RR_INPROG	0x10000
+#define		APIC_ICR_RR_VALID	0x20000
+#define		APIC_INT_LEVELTRIG	0x08000
+#define		APIC_INT_ASSERT		0x04000
+#define		APIC_ICR_BUSY		0x01000
+#define		APIC_DEST_LOGICAL	0x00800
+#define		APIC_DEST_PHYSICAL	0x00000
+#define		APIC_DM_FIXED		0x00000
+#define		APIC_DM_FIXED_MASK	0x00700
+#define		APIC_DM_LOWEST		0x00100
+#define		APIC_DM_SMI		0x00200
+#define		APIC_DM_REMRD		0x00300
+#define		APIC_DM_NMI		0x00400
+#define		APIC_DM_INIT		0x00500
+#define		APIC_DM_STARTUP		0x00600
+#define		APIC_DM_EXTINT		0x00700
+#define		APIC_VECTOR_MASK	0x000FF
+#define	APIC_ICR2	0x310
+
 #define MSR_IA32_TSCDEADLINE		0x000006e0
 
 #define MSR_IA32_UCODE_WRITE		0x00000079

tools/testing/selftests/kvm/lib/kvm_util.c

@@ -91,6 +91,11 @@ static void vm_open(struct kvm_vm *vm, int perm, unsigned long type)
 	if (vm->kvm_fd < 0)
 		exit(KSFT_SKIP);
 
+	if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) {
+		fprintf(stderr, "immediate_exit not available, skipping test\n");
+		exit(KSFT_SKIP);
+	}
+
 	vm->fd = ioctl(vm->kvm_fd, KVM_CREATE_VM, type);
 	TEST_ASSERT(vm->fd >= 0, "KVM_CREATE_VM ioctl failed, "
 		"rc: %i errno: %i", vm->fd, errno);

tools/testing/selftests/kvm/lib/x86_64/processor.c

@@ -1030,6 +1030,14 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
 			    nested_size, sizeof(state->nested_));
 	}
 
+	/*
+	 * When KVM exits to userspace with KVM_EXIT_IO, KVM guarantees
+	 * guest state is consistent only after userspace re-enters the
+	 * kernel with KVM_RUN.  Complete IO prior to migrating state
+	 * to a new VM.
+	 */
+	vcpu_run_complete_io(vm, vcpuid);
+
 	nmsrs = kvm_get_num_msrs(vm);
 	list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
 	list->nmsrs = nmsrs;
@@ -1093,12 +1101,6 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s
 	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);
@@ -1130,4 +1132,10 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s
 	r = ioctl(vcpu->fd, KVM_SET_REGS, &state->regs);
         TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i",
                 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);
+	}
 }

tools/testing/selftests/kvm/x86_64/evmcs_test.c

@@ -123,8 +123,6 @@ int main(int argc, char *argv[])
 			    stage, 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],
@@ -144,6 +142,9 @@ int main(int argc, char *argv[])
 			    stage, (ulong)uc.args[1]);
 
 		state = vcpu_save_state(vm, VCPU_ID);
+		memset(&regs1, 0, sizeof(regs1));
+		vcpu_regs_get(vm, VCPU_ID, &regs1);
+
 		kvm_vm_release(vm);
 
 		/* Restore state in a new VM.  */

tools/testing/selftests/kvm/x86_64/smm_test.c

@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018, Red Hat, Inc.
+ *
+ * Tests for SMM.
+ */
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+
+#include "kvm_util.h"
+
+#include "vmx.h"
+
+#define VCPU_ID	      1
+
+#define PAGE_SIZE  4096
+
+#define SMRAM_SIZE 65536
+#define SMRAM_MEMSLOT ((1 << 16) | 1)
+#define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE)
+#define SMRAM_GPA 0x1000000
+#define SMRAM_STAGE 0xfe
+
+#define STR(x) #x
+#define XSTR(s) STR(s)
+
+#define SYNC_PORT 0xe
+#define DONE 0xff
+
+/*
+ * This is compiled as normal 64-bit code, however, SMI handler is executed
+ * in real-address mode. To stay simple we're limiting ourselves to a mode
+ * independent subset of asm here.
+ * SMI handler always report back fixed stage SMRAM_STAGE.
+ */
+uint8_t smi_handler[] = {
+	0xb0, SMRAM_STAGE,    /* mov $SMRAM_STAGE, %al */
+	0xe4, SYNC_PORT,      /* in $SYNC_PORT, %al */
+	0x0f, 0xaa,           /* rsm */
+};
+
+void sync_with_host(uint64_t phase)
+{
+	asm volatile("in $" XSTR(SYNC_PORT)", %%al \n"
+		     : : "a" (phase));
+}
+
+void self_smi(void)
+{
+	wrmsr(APIC_BASE_MSR + (APIC_ICR >> 4),
+	      APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_SMI);
+}
+
+void guest_code(struct vmx_pages *vmx_pages)
+{
+	uint64_t apicbase = rdmsr(MSR_IA32_APICBASE);
+
+	sync_with_host(1);
+
+	wrmsr(MSR_IA32_APICBASE, apicbase | X2APIC_ENABLE);
+
+	sync_with_host(2);
+
+	self_smi();
+
+	sync_with_host(4);
+
+	if (vmx_pages) {
+		GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+
+		sync_with_host(5);
+
+		self_smi();
+
+		sync_with_host(7);
+	}
+
+	sync_with_host(DONE);
+}
+
+int main(int argc, char *argv[])
+{
+	struct vmx_pages *vmx_pages = NULL;
+	vm_vaddr_t vmx_pages_gva = 0;
+
+	struct kvm_regs regs;
+	struct kvm_vm *vm;
+	struct kvm_run *run;
+	struct kvm_x86_state *state;
+	int stage, stage_reported;
+
+	/* 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);
+
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SMRAM_GPA,
+				    SMRAM_MEMSLOT, SMRAM_PAGES, 0);
+	TEST_ASSERT(vm_phy_pages_alloc(vm, SMRAM_PAGES, SMRAM_GPA, SMRAM_MEMSLOT)
+		    == SMRAM_GPA, "could not allocate guest physical addresses?");
+
+	memset(addr_gpa2hva(vm, SMRAM_GPA), 0x0, SMRAM_SIZE);
+	memcpy(addr_gpa2hva(vm, SMRAM_GPA) + 0x8000, smi_handler,
+	       sizeof(smi_handler));
+
+	vcpu_set_msr(vm, VCPU_ID, MSR_IA32_SMBASE, SMRAM_GPA);
+
+	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 SMM test with VMX enabled\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,
+			    "Stage %d: unexpected exit reason: %u (%s),\n",
+			    stage, run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		memset(&regs, 0, sizeof(regs));
+		vcpu_regs_get(vm, VCPU_ID, &regs);
+
+		stage_reported = regs.rax & 0xff;
+
+		if (stage_reported == DONE)
+			goto done;
+
+		TEST_ASSERT(stage_reported == stage ||
+			    stage_reported == SMRAM_STAGE,
+			    "Unexpected stage: #%x, got %x",
+			    stage, stage_reported);
+
+		state = vcpu_save_state(vm, VCPU_ID);
+		kvm_vm_release(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);
+	}
+
+done:
+	kvm_vm_free(vm);
+}

tools/testing/selftests/kvm/x86_64/state_test.c

@@ -134,11 +134,6 @@ int main(int argc, char *argv[])
 
 	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
 
-	if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) {
-		fprintf(stderr, "immediate_exit not available, skipping test\n");
-		exit(KSFT_SKIP);
-	}
-
 	/* Create VM */
 	vm = vm_create_default(VCPU_ID, 0, guest_code);
 	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
@@ -179,18 +174,10 @@ int main(int argc, char *argv[])
 			    uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx",
 			    stage, (ulong)uc.args[1]);
 
-		/*
-		 * When KVM exits to userspace with KVM_EXIT_IO, KVM guarantees
-		 * guest state is consistent only after userspace re-enters the
-		 * kernel with KVM_RUN.  Complete IO prior to migrating state
-		 * to a new VM.
-		 */
-		vcpu_run_complete_io(vm, VCPU_ID);
-
+		state = vcpu_save_state(vm, VCPU_ID);
 		memset(&regs1, 0, sizeof(regs1));
 		vcpu_regs_get(vm, VCPU_ID, &regs1);
 
-		state = vcpu_save_state(vm, VCPU_ID);
 		kvm_vm_release(vm);
 
 		/* Restore state in a new VM.  */

tools/testing/selftests/net/fib_tests.sh

@@ -605,6 +605,39 @@ run_cmd()
 	return $rc
 }
 
+check_expected()
+{
+	local out="$1"
+	local expected="$2"
+	local rc=0
+
+	[ "${out}" = "${expected}" ] && return 0
+
+	if [ -z "${out}" ]; then
+		if [ "$VERBOSE" = "1" ]; then
+			printf "\nNo route entry found\n"
+			printf "Expected:\n"
+			printf "    ${expected}\n"
+		fi
+		return 1
+	fi
+
+	# tricky way to convert output to 1-line without ip's
+	# messy '\'; this drops all extra white space
+	out=$(echo ${out})
+	if [ "${out}" != "${expected}" ]; then
+		rc=1
+		if [ "${VERBOSE}" = "1" ]; then
+			printf "    Unexpected route entry. Have:\n"
+			printf "        ${out}\n"
+			printf "    Expected:\n"
+			printf "        ${expected}\n\n"
+		fi
+	fi
+
+	return $rc
+}
+
 # add route for a prefix, flushing any existing routes first
 # expected to be the first step of a test
 add_route6()
@@ -652,31 +685,7 @@ check_route6()
 	pfx=$1
 
 	out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//')
-	[ "${out}" = "${expected}" ] && return 0
-
-	if [ -z "${out}" ]; then
-		if [ "$VERBOSE" = "1" ]; then
-			printf "\nNo route entry found\n"
-			printf "Expected:\n"
-			printf "    ${expected}\n"
-		fi
-		return 1
-	fi
-
-	# tricky way to convert output to 1-line without ip's
-	# messy '\'; this drops all extra white space
-	out=$(echo ${out})
-	if [ "${out}" != "${expected}" ]; then
-		rc=1
-		if [ "${VERBOSE}" = "1" ]; then
-			printf "    Unexpected route entry. Have:\n"
-			printf "        ${out}\n"
-			printf "    Expected:\n"
-			printf "        ${expected}\n\n"
-		fi
-	fi
-
-	return $rc
+	check_expected "${out}" "${expected}"
 }
 
 route_cleanup()
@@ -725,7 +734,7 @@ route_setup()
 	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
+	set +e
 }
 
 # assumption is that basic add of a single path route works
@@ -960,7 +969,8 @@ ipv6_addr_metric_test()
 	run_cmd "$IP li set dev dummy2 down"
 	rc=$?
 	if [ $rc -eq 0 ]; then
-		check_route6 ""
+		out=$($IP -6 ro ls match 2001:db8:104::/64)
+		check_expected "${out}" ""
 		rc=$?
 	fi
 	log_test $rc 0 "Prefix route removed on link down"
@@ -1091,38 +1101,13 @@ check_route()
 	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}" = "${expected}" ] && return 0
-
-	if [ -z "${out}" ]; then
-		if [ "$VERBOSE" = "1" ]; then
-			printf "\nNo route entry found\n"
-			printf "Expected:\n"
-			printf "    ${expected}\n"
-		fi
-		return 1
-	fi
-
-	# tricky way to convert output to 1-line without ip's
-	# messy '\'; this drops all extra white space
-	out=$(echo ${out})
-	if [ "${out}" != "${expected}" ]; then
-		rc=1
-		if [ "${VERBOSE}" = "1" ]; then
-			printf "    Unexpected route entry. Have:\n"
-			printf "        ${out}\n"
-			printf "    Expected:\n"
-			printf "        ${expected}\n\n"
-		fi
-	fi
-
-	return $rc
+	check_expected "${out}" "${expected}"
 }
 
 # assumption is that basic add of a single path route works
@@ -1387,7 +1372,8 @@ ipv4_addr_metric_test()
 	run_cmd "$IP li set dev dummy2 down"
 	rc=$?
 	if [ $rc -eq 0 ]; then
-		check_route ""
+		out=$($IP ro ls match 172.16.104.0/24)
+		check_expected "${out}" ""
 		rc=$?
 	fi
 	log_test $rc 0 "Prefix route removed on link down"

tools/testing/selftests/proc/proc-pid-vm.c

@@ -187,8 +187,8 @@ static int make_exe(const uint8_t *payload, size_t len)
 	ph.p_offset = 0;
 	ph.p_vaddr = VADDR;
 	ph.p_paddr = 0;
-	ph.p_filesz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + sizeof(payload);
-	ph.p_memsz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + sizeof(payload);
+	ph.p_filesz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + len;
+	ph.p_memsz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + len;
 	ph.p_align = 4096;
 
 	fd = openat(AT_FDCWD, "/tmp", O_WRONLY|O_EXCL|O_TMPFILE, 0700);

tools/testing/selftests/proc/proc-self-map-files-002.c

@@ -46,12 +46,9 @@ static void fail(const char *fmt, unsigned long a, unsigned long b)
 
 int main(void)
 {
-	const unsigned int PAGE_SIZE = sysconf(_SC_PAGESIZE);
-#ifdef __arm__
-	unsigned long va = 2 * PAGE_SIZE;
-#else
-	unsigned long va = 0;
-#endif
+	const int PAGE_SIZE = sysconf(_SC_PAGESIZE);
+	const unsigned long va_max = 1UL << 32;
+	unsigned long va;
 	void *p;
 	int fd;
 	unsigned long a, b;
@@ -60,10 +57,13 @@ int main(void)
 	if (fd == -1)
 		return 1;
 
-	p = mmap((void *)va, PAGE_SIZE, PROT_NONE, MAP_PRIVATE|MAP_FILE|MAP_FIXED, fd, 0);
-	if (p == MAP_FAILED) {
-		if (errno == EPERM)
-			return 4;
+	for (va = 0; va < va_max; va += PAGE_SIZE) {
+		p = mmap((void *)va, PAGE_SIZE, PROT_NONE, MAP_PRIVATE|MAP_FILE|MAP_FIXED, fd, 0);
+		if (p == (void *)va)
+			break;
+	}
+	if (va == va_max) {
+		fprintf(stderr, "error: mmap doesn't like you\n");
 		return 1;
 	}
 

tools/testing/selftests/tc-testing/tc-tests/actions/sample.json

@@ -143,6 +143,30 @@
             "$TC actions flush action sample"
         ]
     },
+    {
+        "id": "7571",
+        "name": "Add sample action with invalid rate",
+        "category": [
+            "actions",
+            "sample"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action sample",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action sample rate 0 group 1 index 2",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action sample index 2",
+        "matchPattern": "action order [0-9]+: sample rate 1/0 group 1.*index 2 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action sample"
+        ]
+    },
     {
         "id": "b6d4",
         "name": "Add sample action with mandatory arguments and invalid control action",

tools/testing/selftests/tc-testing/tc-tests/filters/tests.json

@@ -18,6 +18,26 @@
             "$TC qdisc del dev $DEV1 ingress"
         ]
     },
+    {
+        "id": "2638",
+        "name": "Add matchall and try to get it",
+        "category": [
+            "filter",
+            "matchall"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 clsact",
+            "$TC filter add dev $DEV1 protocol all pref 1 ingress handle 0x1234 matchall action ok"
+        ],
+        "cmdUnderTest": "$TC filter get dev $DEV1 protocol all pref 1 ingress handle 0x1234 matchall",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 ingress",
+        "matchPattern": "filter protocol all pref 1 matchall chain 0 handle 0x1234",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 clsact"
+        ]
+    },
     {
         "id": "d052",
         "name": "Add 1M filters with the same action",

tools/testing/selftests/tpm2/tpm2.py

@@ -22,6 +22,7 @@ TPM2_CC_UNSEAL = 0x015E
 TPM2_CC_FLUSH_CONTEXT = 0x0165
 TPM2_CC_START_AUTH_SESSION = 0x0176
 TPM2_CC_GET_CAPABILITY	= 0x017A
+TPM2_CC_GET_RANDOM = 0x017B
 TPM2_CC_PCR_READ = 0x017E
 TPM2_CC_POLICY_PCR = 0x017F
 TPM2_CC_PCR_EXTEND = 0x0182
@@ -357,9 +358,9 @@ class Client:
         self.flags = flags
 
         if (self.flags & Client.FLAG_SPACE) == 0:
-            self.tpm = open('/dev/tpm0', 'r+b')
+            self.tpm = open('/dev/tpm0', 'r+b', buffering=0)
         else:
-            self.tpm = open('/dev/tpmrm0', 'r+b')
+            self.tpm = open('/dev/tpmrm0', 'r+b', buffering=0)
 
     def close(self):
         self.tpm.close()

tools/testing/selftests/tpm2/tpm2_tests.py

@@ -158,6 +158,69 @@ class SmokeTest(unittest.TestCase):
             pass
         self.assertEqual(rejected, True)
 
+    def test_read_partial_resp(self):
+        try:
+            fmt = '>HIIH'
+            cmd = struct.pack(fmt,
+                              tpm2.TPM2_ST_NO_SESSIONS,
+                              struct.calcsize(fmt),
+                              tpm2.TPM2_CC_GET_RANDOM,
+                              0x20)
+            self.client.tpm.write(cmd)
+            hdr = self.client.tpm.read(10)
+            sz = struct.unpack('>I', hdr[2:6])[0]
+            rsp = self.client.tpm.read()
+        except:
+            pass
+        self.assertEqual(sz, 10 + 2 + 32)
+        self.assertEqual(len(rsp), 2 + 32)
+
+    def test_read_partial_overwrite(self):
+        try:
+            fmt = '>HIIH'
+            cmd = struct.pack(fmt,
+                              tpm2.TPM2_ST_NO_SESSIONS,
+                              struct.calcsize(fmt),
+                              tpm2.TPM2_CC_GET_RANDOM,
+                              0x20)
+            self.client.tpm.write(cmd)
+            # Read part of the respone
+            rsp1 = self.client.tpm.read(15)
+
+            # Send a new cmd
+            self.client.tpm.write(cmd)
+
+            # Read the whole respone
+            rsp2 = self.client.tpm.read()
+        except:
+            pass
+        self.assertEqual(len(rsp1), 15)
+        self.assertEqual(len(rsp2), 10 + 2 + 32)
+
+    def test_send_two_cmds(self):
+        rejected = False
+        try:
+            fmt = '>HIIH'
+            cmd = struct.pack(fmt,
+                              tpm2.TPM2_ST_NO_SESSIONS,
+                              struct.calcsize(fmt),
+                              tpm2.TPM2_CC_GET_RANDOM,
+                              0x20)
+            self.client.tpm.write(cmd)
+
+            # expect the second one to raise -EBUSY error
+            self.client.tpm.write(cmd)
+            rsp = self.client.tpm.read()
+
+        except IOError, e:
+            # read the response
+            rsp = self.client.tpm.read()
+            rejected = True
+            pass
+        except:
+            pass
+        self.assertEqual(rejected, True)
+
 class SpaceTest(unittest.TestCase):
     def setUp(self):
         logging.basicConfig(filename='SpaceTest.log', level=logging.DEBUG)