Merge 5.3-rc7 into usb-next

We need the usb fixes in here for testing

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

27 files changed, 334 insertions, 134 deletions

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 5215e0870bcb..6a71324be628 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -204,7 +204,11 @@ int do_pin_fd(int fd, const char *name)
 	if (err)
 		return err;
 
-	return bpf_obj_pin(fd, name);
+	err = bpf_obj_pin(fd, name);
+	if (err)
+		p_err("can't pin the object (%s): %s", name, strerror(errno));
+
+	return err;
 }
 
 int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
@@ -237,7 +241,7 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
 
 	fd = get_fd_by_id(id);
 	if (fd < 0) {
-		p_err("can't get prog by id (%u): %s", id, strerror(errno));
+		p_err("can't open object by id (%u): %s", id, strerror(errno));
 		return -1;
 	}
 
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 66f04a4846a5..43fdbbfe41bb 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -363,7 +363,9 @@ static int do_show(int argc, char **argv)
 		if (fd < 0)
 			return -1;
 
-		return show_prog(fd);
+		err = show_prog(fd);
+		close(fd);
+		return err;
 	}
 
 	if (argc)
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index f5597503c771..e9ef4ca6a655 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -809,7 +809,7 @@ kvp_get_ip_info(int family, char *if_name, int op,
 	int sn_offset = 0;
 	int error = 0;
 	char *buffer;
-	struct hv_kvp_ipaddr_value *ip_buffer;
+	struct hv_kvp_ipaddr_value *ip_buffer = NULL;
 	char cidr_mask[5]; /* /xyz */
 	int weight;
 	int i;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 4e455018da65..a5aa7d3ac6a1 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1466,8 +1466,8 @@ union bpf_attr {
  * 		If no cookie has been set yet, generate a new cookie. Once
  * 		generated, the socket cookie remains stable for the life of the
  * 		socket. This helper can be useful for monitoring per socket
- * 		networking traffic statistics as it provides a unique socket
- * 		identifier per namespace.
+ * 		networking traffic statistics as it provides a global socket
+ * 		identifier that can be assumed unique.
  * 	Return
  * 		A 8-byte long non-decreasing number on success, or 0 if the
  * 		socket field is missing inside *skb*.
@@ -1571,8 +1571,11 @@ union bpf_attr {
  * 		but this is only implemented for native XDP (with driver
  * 		support) as of this writing).
  *
- * 		All values for *flags* are reserved for future usage, and must
- * 		be left at zero.
+ * 		The lower two bits of *flags* are used as the return code if
+ * 		the map lookup fails. This is so that the return value can be
+ * 		one of the XDP program return codes up to XDP_TX, as chosen by
+ * 		the caller. Any higher bits in the *flags* argument must be
+ * 		unset.
  *
  * 		When used to redirect packets to net devices, this helper
  * 		provides a high performance increase over **bpf_redirect**\ ().
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 2586b6cb8f34..2b57d7ea7836 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -182,7 +182,6 @@ struct bpf_program {
 	bpf_program_clear_priv_t clear_priv;
 
 	enum bpf_attach_type expected_attach_type;
-	int btf_fd;
 	void *func_info;
 	__u32 func_info_rec_size;
 	__u32 func_info_cnt;
@@ -313,7 +312,6 @@ void bpf_program__unload(struct bpf_program *prog)
 	prog->instances.nr = -1;
 	zfree(&prog->instances.fds);
 
-	zclose(prog->btf_fd);
 	zfree(&prog->func_info);
 	zfree(&prog->line_info);
 }
@@ -392,7 +390,6 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx,
 	prog->instances.fds = NULL;
 	prog->instances.nr = -1;
 	prog->type = BPF_PROG_TYPE_UNSPEC;
-	prog->btf_fd = -1;
 
 	return 0;
 errout:
@@ -2288,9 +2285,6 @@ bpf_program_reloc_btf_ext(struct bpf_program *prog, struct bpf_object *obj,
 		prog->line_info_rec_size = btf_ext__line_info_rec_size(obj->btf_ext);
 	}
 
-	if (!insn_offset)
-		prog->btf_fd = btf__fd(obj->btf);
-
 	return 0;
 }
 
@@ -2463,7 +2457,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	char *cp, errmsg[STRERR_BUFSIZE];
 	int log_buf_size = BPF_LOG_BUF_SIZE;
 	char *log_buf;
-	int ret;
+	int btf_fd, ret;
 
 	if (!insns || !insns_cnt)
 		return -EINVAL;
@@ -2478,7 +2472,12 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	load_attr.license = license;
 	load_attr.kern_version = kern_version;
 	load_attr.prog_ifindex = prog->prog_ifindex;
-	load_attr.prog_btf_fd = prog->btf_fd >= 0 ? prog->btf_fd : 0;
+	/* if .BTF.ext was loaded, kernel supports associated BTF for prog */
+	if (prog->obj->btf_ext)
+		btf_fd = bpf_object__btf_fd(prog->obj);
+	else
+		btf_fd = -1;
+	load_attr.prog_btf_fd = btf_fd >= 0 ? btf_fd : 0;
 	load_attr.func_info = prog->func_info;
 	load_attr.func_info_rec_size = prog->func_info_rec_size;
 	load_attr.func_info_cnt = prog->func_info_cnt;
@@ -5000,13 +4999,15 @@ int libbpf_num_possible_cpus(void)
 	static const char *fcpu = "/sys/devices/system/cpu/possible";
 	int len = 0, n = 0, il = 0, ir = 0;
 	unsigned int start = 0, end = 0;
+	int tmp_cpus = 0;
 	static int cpus;
 	char buf[128];
 	int error = 0;
 	int fd = -1;
 
-	if (cpus > 0)
-		return cpus;
+	tmp_cpus = READ_ONCE(cpus);
+	if (tmp_cpus > 0)
+		return tmp_cpus;
 
 	fd = open(fcpu, O_RDONLY);
 	if (fd < 0) {
@@ -5029,7 +5030,7 @@ int libbpf_num_possible_cpus(void)
 	}
 	buf[len] = '\0';
 
-	for (ir = 0, cpus = 0; ir <= len; ir++) {
+	for (ir = 0, tmp_cpus = 0; ir <= len; ir++) {
 		/* Each sub string separated by ',' has format \d+-\d+ or \d+ */
 		if (buf[ir] == ',' || buf[ir] == '\0') {
 			buf[ir] = '\0';
@@ -5041,13 +5042,15 @@ int libbpf_num_possible_cpus(void)
 			} else if (n == 1) {
 				end = start;
 			}
-			cpus += end - start + 1;
+			tmp_cpus += end - start + 1;
 			il = ir + 1;
 		}
 	}
-	if (cpus <= 0) {
-		pr_warning("Invalid #CPUs %d from %s\n", cpus, fcpu);
+	if (tmp_cpus <= 0) {
+		pr_warning("Invalid #CPUs %d from %s\n", tmp_cpus, fcpu);
 		return -EINVAL;
 	}
-	return cpus;
+
+	WRITE_ONCE(cpus, tmp_cpus);
+	return tmp_cpus;
 }
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index 045f5f7d68ab..13f1e8b9ac52 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -9,9 +9,10 @@ ifeq ("$(origin O)", "command line")
 endif
 
 turbostat : turbostat.c
-override CFLAGS +=	-Wall -I../../../include
+override CFLAGS +=	-O2 -Wall -I../../../include
 override CFLAGS +=	-DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"'
 override CFLAGS +=	-DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"'
+override CFLAGS +=	-D_FORTIFY_SOURCE=2
 
 %: %.c
 	@mkdir -p $(BUILD_OUTPUT)
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 75fc4fb9901c..b2a86438f074 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -39,7 +39,6 @@ FILE *outf;
 int *fd_percpu;
 struct timeval interval_tv = {5, 0};
 struct timespec interval_ts = {5, 0};
-struct timespec one_msec = {0, 1000000};
 unsigned int num_iterations;
 unsigned int debug;
 unsigned int quiet;
@@ -60,6 +59,7 @@ unsigned int do_irtl_hsw;
 unsigned int units = 1000000;	/* MHz etc */
 unsigned int genuine_intel;
 unsigned int authentic_amd;
+unsigned int hygon_genuine;
 unsigned int max_level, max_extended_level;
 unsigned int has_invariant_tsc;
 unsigned int do_nhm_platform_info;
@@ -100,6 +100,7 @@ unsigned int has_hwp_epp;		/* IA32_HWP_REQUEST[bits 31:24] */
 unsigned int has_hwp_pkg;		/* IA32_HWP_REQUEST_PKG */
 unsigned int has_misc_feature_control;
 unsigned int first_counter_read = 1;
+int ignore_stdin;
 
 #define RAPL_PKG		(1 << 0)
 					/* 0x610 MSR_PKG_POWER_LIMIT */
@@ -166,6 +167,7 @@ size_t cpu_present_setsize, cpu_affinity_setsize, cpu_subset_size;
 struct thread_data {
 	struct timeval tv_begin;
 	struct timeval tv_end;
+	struct timeval tv_delta;
 	unsigned long long tsc;
 	unsigned long long aperf;
 	unsigned long long mperf;
@@ -506,6 +508,7 @@ unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAU
 unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC_X2APIC;
 
 #define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME)
+#define DO_BIC_READ(COUNTER_NAME) (bic_present & COUNTER_NAME)
 #define ENABLE_BIC(COUNTER_NAME) (bic_enabled |= COUNTER_NAME)
 #define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT)
 #define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT)
@@ -849,7 +852,6 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "pc8: %016llX\n", p->pc8);
 		outp += sprintf(outp, "pc9: %016llX\n", p->pc9);
 		outp += sprintf(outp, "pc10: %016llX\n", p->pc10);
-		outp += sprintf(outp, "pc10: %016llX\n", p->pc10);
 		outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi);
 		outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi);
 		outp += sprintf(outp, "Joules PKG: %0X\n", p->energy_pkg);
@@ -911,7 +913,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (DO_BIC(BIC_TOD))
 		outp += sprintf(outp, "%10ld.%06ld\t", t->tv_end.tv_sec, t->tv_end.tv_usec);
 
-	interval_float = tv_delta.tv_sec + tv_delta.tv_usec/1000000.0;
+	interval_float = t->tv_delta.tv_sec + t->tv_delta.tv_usec/1000000.0;
 
 	tsc = t->tsc * tsc_tweak;
 
@@ -1287,6 +1289,14 @@ delta_core(struct core_data *new, struct core_data *old)
 	}
 }
 
+int soft_c1_residency_display(int bic)
+{
+	if (!DO_BIC(BIC_CPU_c1) || use_c1_residency_msr)
+		return 0;
+
+	return DO_BIC_READ(bic);
+}
+
 /*
  * old = new - old
  */
@@ -1309,6 +1319,7 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 	 * over-write old w/ new so we can print end of interval values
 	 */
 
+	timersub(&new->tv_begin, &old->tv_begin, &old->tv_delta);
 	old->tv_begin = new->tv_begin;
 	old->tv_end = new->tv_end;
 
@@ -1322,7 +1333,8 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 
 	old->c1 = new->c1 - old->c1;
 
-	if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz)) {
+	if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) ||
+	    soft_c1_residency_display(BIC_Avg_MHz)) {
 		if ((new->aperf > old->aperf) && (new->mperf > old->mperf)) {
 			old->aperf = new->aperf - old->aperf;
 			old->mperf = new->mperf - old->mperf;
@@ -1404,6 +1416,8 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	t->tv_begin.tv_usec = 0;
 	t->tv_end.tv_sec = 0;
 	t->tv_end.tv_usec = 0;
+	t->tv_delta.tv_sec = 0;
+	t->tv_delta.tv_usec = 0;
 
 	t->tsc = 0;
 	t->aperf = 0;
@@ -1573,6 +1587,9 @@ void compute_average(struct thread_data *t, struct core_data *c,
 
 	for_all_cpus(sum_counters, t, c, p);
 
+	/* Use the global time delta for the average. */
+	average.threads.tv_delta = tv_delta;
+
 	average.threads.tsc /= topo.num_cpus;
 	average.threads.aperf /= topo.num_cpus;
 	average.threads.mperf /= topo.num_cpus;
@@ -1714,7 +1731,7 @@ void get_apic_id(struct thread_data *t)
 	if (!DO_BIC(BIC_X2APIC))
 		return;
 
-	if (authentic_amd) {
+	if (authentic_amd || hygon_genuine) {
 		unsigned int topology_extensions;
 
 		if (max_extended_level < 0x8000001e)
@@ -1762,19 +1779,20 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	struct msr_counter *mp;
 	int i;
 
-	gettimeofday(&t->tv_begin, (struct timezone *)NULL);
-
 	if (cpu_migrate(cpu)) {
 		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
 		return -1;
 	}
 
+	gettimeofday(&t->tv_begin, (struct timezone *)NULL);
+
 	if (first_counter_read)
 		get_apic_id(t);
 retry:
 	t->tsc = rdtsc();	/* we are running on local CPU of interest */
 
-	if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz)) {
+	if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) ||
+	    soft_c1_residency_display(BIC_Avg_MHz)) {
 		unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time;
 
 		/*
@@ -1851,20 +1869,20 @@ retry:
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		goto done;
 
-	if (DO_BIC(BIC_CPU_c3)) {
+	if (DO_BIC(BIC_CPU_c3) || soft_c1_residency_display(BIC_CPU_c3)) {
 		if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3))
 			return -6;
 	}
 
-	if (DO_BIC(BIC_CPU_c6) && !do_knl_cstates) {
+	if ((DO_BIC(BIC_CPU_c6) || soft_c1_residency_display(BIC_CPU_c6)) && !do_knl_cstates) {
 		if (get_msr(cpu, MSR_CORE_C6_RESIDENCY, &c->c6))
 			return -7;
-	} else if (do_knl_cstates) {
+	} else if (do_knl_cstates || soft_c1_residency_display(BIC_CPU_c6)) {
 		if (get_msr(cpu, MSR_KNL_CORE_C6_RESIDENCY, &c->c6))
 			return -7;
 	}
 
-	if (DO_BIC(BIC_CPU_c7))
+	if (DO_BIC(BIC_CPU_c7) || soft_c1_residency_display(BIC_CPU_c7))
 		if (get_msr(cpu, MSR_CORE_C7_RESIDENCY, &c->c7))
 			return -8;
 
@@ -2912,6 +2930,7 @@ int snapshot_cpu_lpi_us(void)
 	if (retval != 1) {
 		fprintf(stderr, "Disabling Low Power Idle CPU output\n");
 		BIC_NOT_PRESENT(BIC_CPU_LPI);
+		fclose(fp);
 		return -1;
 	}
 
@@ -2938,6 +2957,7 @@ int snapshot_sys_lpi_us(void)
 	if (retval != 1) {
 		fprintf(stderr, "Disabling Low Power Idle System output\n");
 		BIC_NOT_PRESENT(BIC_SYS_LPI);
+		fclose(fp);
 		return -1;
 	}
 	fclose(fp);
@@ -2985,8 +3005,6 @@ static void signal_handler (int signal)
 			fprintf(stderr, "SIGUSR1\n");
 		break;
 	}
-	/* make sure this manually-invoked interval is at least 1ms long */
-	nanosleep(&one_msec, NULL);
 }
 
 void setup_signal_handler(void)
@@ -3005,29 +3023,38 @@ void setup_signal_handler(void)
 
 void do_sleep(void)
 {
-	struct timeval select_timeout;
+	struct timeval tout;
+	struct timespec rest;
 	fd_set readfds;
 	int retval;
 
 	FD_ZERO(&readfds);
 	FD_SET(0, &readfds);
 
-	if (!isatty(fileno(stdin))) {
+	if (ignore_stdin) {
 		nanosleep(&interval_ts, NULL);
 		return;
 	}
 
-	select_timeout = interval_tv;
-	retval = select(1, &readfds, NULL, NULL, &select_timeout);
+	tout = interval_tv;
+	retval = select(1, &readfds, NULL, NULL, &tout);
 
 	if (retval == 1) {
 		switch (getc(stdin)) {
 		case 'q':
 			exit_requested = 1;
 			break;
+		case EOF:
+			/*
+			 * 'stdin' is a pipe closed on the other end. There
+			 * won't be any further input.
+			 */
+			ignore_stdin = 1;
+			/* Sleep the rest of the time */
+			rest.tv_sec = (tout.tv_sec + tout.tv_usec / 1000000);
+			rest.tv_nsec = (tout.tv_usec % 1000000) * 1000;
+			nanosleep(&rest, NULL);
 		}
-		/* make sure this manually-invoked interval is at least 1ms long */
-		nanosleep(&one_msec, NULL);
 	}
 }
 
@@ -3209,6 +3236,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 		break;
 	case INTEL_FAM6_HASWELL_CORE:	/* HSW */
 	case INTEL_FAM6_HASWELL_X:	/* HSX */
+	case INTEL_FAM6_HASWELL_ULT:	/* HSW */
 	case INTEL_FAM6_HASWELL_GT3E:	/* HSW */
 	case INTEL_FAM6_BROADWELL_CORE:	/* BDW */
 	case INTEL_FAM6_BROADWELL_GT3E:	/* BDW */
@@ -3405,6 +3433,7 @@ int has_config_tdp(unsigned int family, unsigned int model)
 	case INTEL_FAM6_IVYBRIDGE:	/* IVB */
 	case INTEL_FAM6_HASWELL_CORE:	/* HSW */
 	case INTEL_FAM6_HASWELL_X:	/* HSX */
+	case INTEL_FAM6_HASWELL_ULT:	/* HSW */
 	case INTEL_FAM6_HASWELL_GT3E:	/* HSW */
 	case INTEL_FAM6_BROADWELL_CORE:	/* BDW */
 	case INTEL_FAM6_BROADWELL_GT3E:	/* BDW */
@@ -3803,6 +3832,7 @@ double get_tdp_amd(unsigned int family)
 {
 	switch (family) {
 	case 0x17:
+	case 0x18:
 	default:
 		/* This is the max stock TDP of HEDT/Server Fam17h chips */
 		return 250.0;
@@ -3841,6 +3871,7 @@ void rapl_probe_intel(unsigned int family, unsigned int model)
 	case INTEL_FAM6_SANDYBRIDGE:
 	case INTEL_FAM6_IVYBRIDGE:
 	case INTEL_FAM6_HASWELL_CORE:	/* HSW */
+	case INTEL_FAM6_HASWELL_ULT:	/* HSW */
 	case INTEL_FAM6_HASWELL_GT3E:	/* HSW */
 	case INTEL_FAM6_BROADWELL_CORE:	/* BDW */
 	case INTEL_FAM6_BROADWELL_GT3E:	/* BDW */
@@ -3982,6 +4013,7 @@ void rapl_probe_amd(unsigned int family, unsigned int model)
 
 	switch (family) {
 	case 0x17: /* Zen, Zen+ */
+	case 0x18: /* Hygon Dhyana */
 		do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY;
 		if (rapl_joules) {
 			BIC_PRESENT(BIC_Pkg_J);
@@ -4002,7 +4034,7 @@ void rapl_probe_amd(unsigned int family, unsigned int model)
 	rapl_energy_units = ldexp(1.0, -(msr >> 8 & 0x1f));
 	rapl_power_units = ldexp(1.0, -(msr & 0xf));
 
-	tdp = get_tdp_amd(model);
+	tdp = get_tdp_amd(family);
 
 	rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
 	if (!quiet)
@@ -4018,7 +4050,7 @@ void rapl_probe(unsigned int family, unsigned int model)
 {
 	if (genuine_intel)
 		rapl_probe_intel(family, model);
-	if (authentic_amd)
+	if (authentic_amd || hygon_genuine)
 		rapl_probe_amd(family, model);
 }
 
@@ -4032,6 +4064,7 @@ void perf_limit_reasons_probe(unsigned int family, unsigned int model)
 
 	switch (model) {
 	case INTEL_FAM6_HASWELL_CORE:	/* HSW */
+	case INTEL_FAM6_HASWELL_ULT:	/* HSW */
 	case INTEL_FAM6_HASWELL_GT3E:	/* HSW */
 		do_gfx_perf_limit_reasons = 1;
 	case INTEL_FAM6_HASWELL_X:	/* HSX */
@@ -4251,6 +4284,7 @@ int has_snb_msrs(unsigned int family, unsigned int model)
 	case INTEL_FAM6_IVYBRIDGE_X:	/* IVB Xeon */
 	case INTEL_FAM6_HASWELL_CORE:	/* HSW */
 	case INTEL_FAM6_HASWELL_X:	/* HSW */
+	case INTEL_FAM6_HASWELL_ULT:	/* HSW */
 	case INTEL_FAM6_HASWELL_GT3E:	/* HSW */
 	case INTEL_FAM6_BROADWELL_CORE:	/* BDW */
 	case INTEL_FAM6_BROADWELL_GT3E:	/* BDW */
@@ -4267,7 +4301,7 @@ int has_snb_msrs(unsigned int family, unsigned int model)
 }
 
 /*
- * HSW adds support for additional MSRs:
+ * HSW ULT added support for C8/C9/C10 MSRs:
  *
  * MSR_PKG_C8_RESIDENCY		0x00000630
  * MSR_PKG_C9_RESIDENCY		0x00000631
@@ -4278,13 +4312,13 @@ int has_snb_msrs(unsigned int family, unsigned int model)
  * MSR_PKGC10_IRTL		0x00000635
  *
  */
-int has_hsw_msrs(unsigned int family, unsigned int model)
+int has_c8910_msrs(unsigned int family, unsigned int model)
 {
 	if (!genuine_intel)
 		return 0;
 
 	switch (model) {
-	case INTEL_FAM6_HASWELL_CORE:
+	case INTEL_FAM6_HASWELL_ULT:	/* HSW */
 	case INTEL_FAM6_BROADWELL_CORE:	/* BDW */
 	case INTEL_FAM6_SKYLAKE_MOBILE:	/* SKL */
 	case INTEL_FAM6_CANNONLAKE_MOBILE:	/* CNL */
@@ -4568,9 +4602,6 @@ unsigned int intel_model_duplicates(unsigned int model)
 	case INTEL_FAM6_XEON_PHI_KNM:
 		return INTEL_FAM6_XEON_PHI_KNL;
 
-	case INTEL_FAM6_HASWELL_ULT:
-		return INTEL_FAM6_HASWELL_CORE;
-
 	case INTEL_FAM6_BROADWELL_X:
 	case INTEL_FAM6_BROADWELL_XEON_D:	/* BDX-DE */
 		return INTEL_FAM6_BROADWELL_X;
@@ -4582,7 +4613,11 @@ unsigned int intel_model_duplicates(unsigned int model)
 		return INTEL_FAM6_SKYLAKE_MOBILE;
 
 	case INTEL_FAM6_ICELAKE_MOBILE:
+	case INTEL_FAM6_ICELAKE_NNPI:
 		return INTEL_FAM6_CANNONLAKE_MOBILE;
+
+	case INTEL_FAM6_ATOM_TREMONT_X:
+		return INTEL_FAM6_ATOM_GOLDMONT_X;
 	}
 	return model;
 }
@@ -4600,6 +4635,8 @@ void process_cpuid()
 		genuine_intel = 1;
 	else if (ebx == 0x68747541 && ecx == 0x444d4163 && edx == 0x69746e65)
 		authentic_amd = 1;
+	else if (ebx == 0x6f677948 && ecx == 0x656e6975 && edx == 0x6e65476e)
+		hygon_genuine = 1;
 
 	if (!quiet)
 		fprintf(outf, "CPUID(0): %.4s%.4s%.4s ",
@@ -4820,12 +4857,12 @@ void process_cpuid()
 		BIC_NOT_PRESENT(BIC_CPU_c7);
 		BIC_NOT_PRESENT(BIC_Pkgpc7);
 	}
-	if (has_hsw_msrs(family, model)) {
+	if (has_c8910_msrs(family, model)) {
 		BIC_PRESENT(BIC_Pkgpc8);
 		BIC_PRESENT(BIC_Pkgpc9);
 		BIC_PRESENT(BIC_Pkgpc10);
 	}
-	do_irtl_hsw = has_hsw_msrs(family, model);
+	do_irtl_hsw = has_c8910_msrs(family, model);
 	if (has_skl_msrs(family, model)) {
 		BIC_PRESENT(BIC_Totl_c0);
 		BIC_PRESENT(BIC_Any_c0);
@@ -5123,7 +5160,7 @@ int initialize_counters(int cpu_id)
 
 void allocate_output_buffer()
 {
-	output_buffer = calloc(1, (1 + topo.num_cpus) * 1024);
+	output_buffer = calloc(1, (1 + topo.num_cpus) * 2048);
 	outp = output_buffer;
 	if (outp == NULL)
 		err(-1, "calloc output buffer");
@@ -5269,7 +5306,7 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-	fprintf(outf, "turbostat version 19.03.20"
+	fprintf(outf, "turbostat version 19.08.31"
 		" - Len Brown <lenb@kernel.org>\n");
 }
 
diff --git a/tools/power/x86/x86_energy_perf_policy/Makefile b/tools/power/x86/x86_energy_perf_policy/Makefile
index 1fdeef864e7c..666b325a62a2 100644
--- a/tools/power/x86/x86_energy_perf_policy/Makefile
+++ b/tools/power/x86/x86_energy_perf_policy/Makefile
@@ -9,8 +9,9 @@ ifeq ("$(origin O)", "command line")
 endif
 
 x86_energy_perf_policy : x86_energy_perf_policy.c
-override CFLAGS +=	-Wall -I../../../include
+override CFLAGS +=	-O2 -Wall -I../../../include
 override CFLAGS +=	-DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"'
+override CFLAGS +=	-D_FORTIFY_SOURCE=2
 
 %: %.c
 	@mkdir -p $(BUILD_OUTPUT)
diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.8 b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.8
index 17db1c3af4d0..78c6361898b1 100644
--- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.8
+++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.8
@@ -40,7 +40,7 @@ in the same processor package.
 Hardware P-States (HWP) are effectively an expansion of hardware
 P-state control from the opportunistic turbo-mode P-state range
 to include the entire range of available P-states.
-On Broadwell Xeon, the initial HWP implementation, EBP influenced HWP.
+On Broadwell Xeon, the initial HWP implementation, EPB influenced HWP.
 That influence was removed in subsequent generations,
 where it was moved to the
 Energy_Performance_Preference (EPP) field in
diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
index 34a796b303fe..3fe1eed900d4 100644
--- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
+++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
@@ -545,7 +545,7 @@ void cmdline(int argc, char **argv)
 
 	progname = argv[0];
 
-	while ((opt = getopt_long_only(argc, argv, "+a:c:dD:E:e:f:m:M:rt:u:vw",
+	while ((opt = getopt_long_only(argc, argv, "+a:c:dD:E:e:f:m:M:rt:u:vw:",
 				long_options, &option_index)) != -1) {
 		switch (opt) {
 		case 'a':
@@ -1259,6 +1259,15 @@ void probe_dev_msr(void)
 		if (system("/sbin/modprobe msr > /dev/null 2>&1"))
 			err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" ");
 }
+
+static void get_cpuid_or_exit(unsigned int leaf,
+			     unsigned int *eax, unsigned int *ebx,
+			     unsigned int *ecx, unsigned int *edx)
+{
+	if (!__get_cpuid(leaf, eax, ebx, ecx, edx))
+		errx(1, "Processor not supported\n");
+}
+
 /*
  * early_cpuid()
  * initialize turbo_is_enabled, has_hwp, has_epb
@@ -1266,15 +1275,10 @@ void probe_dev_msr(void)
  */
 void early_cpuid(void)
 {
-	unsigned int eax, ebx, ecx, edx, max_level;
+	unsigned int eax, ebx, ecx, edx;
 	unsigned int fms, family, model;
 
-	__get_cpuid(0, &max_level, &ebx, &ecx, &edx);
-
-	if (max_level < 6)
-		errx(1, "Processor not supported\n");
-
-	__get_cpuid(1, &fms, &ebx, &ecx, &edx);
+	get_cpuid_or_exit(1, &fms, &ebx, &ecx, &edx);
 	family = (fms >> 8) & 0xf;
 	model = (fms >> 4) & 0xf;
 	if (family == 6 || family == 0xf)
@@ -1288,7 +1292,7 @@ void early_cpuid(void)
 		bdx_highest_ratio = msr & 0xFF;
 	}
 
-	__get_cpuid(0x6, &eax, &ebx, &ecx, &edx);
+	get_cpuid_or_exit(0x6, &eax, &ebx, &ecx, &edx);
 	turbo_is_enabled = (eax >> 1) & 1;
 	has_hwp = (eax >> 7) & 1;
 	has_epb = (ecx >> 3) & 1;
@@ -1306,7 +1310,7 @@ void parse_cpuid(void)
 
 	eax = ebx = ecx = edx = 0;
 
-	__get_cpuid(0, &max_level, &ebx, &ecx, &edx);
+	get_cpuid_or_exit(0, &max_level, &ebx, &ecx, &edx);
 
 	if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e)
 		genuine_intel = 1;
@@ -1315,7 +1319,7 @@ void parse_cpuid(void)
 		fprintf(stderr, "CPUID(0): %.4s%.4s%.4s ",
 			(char *)&ebx, (char *)&edx, (char *)&ecx);
 
-	__get_cpuid(1, &fms, &ebx, &ecx, &edx);
+	get_cpuid_or_exit(1, &fms, &ebx, &ecx, &edx);
 	family = (fms >> 8) & 0xf;
 	model = (fms >> 4) & 0xf;
 	stepping = fms & 0xf;
@@ -1340,7 +1344,7 @@ void parse_cpuid(void)
 		errx(1, "CPUID: no MSR");
 
 
-	__get_cpuid(0x6, &eax, &ebx, &ecx, &edx);
+	get_cpuid_or_exit(0x6, &eax, &ebx, &ecx, &edx);
 	/* turbo_is_enabled already set */
 	/* has_hwp already set */
 	has_hwp_notify = eax & (1 << 8);
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index c085964e1d05..96752ebd938f 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -34,6 +34,9 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
 BPF_OBJ_FILES = $(patsubst %.c,%.o, $(notdir $(wildcard progs/*.c)))
 TEST_GEN_FILES = $(BPF_OBJ_FILES)
 
+BTF_C_FILES = $(wildcard progs/btf_dump_test_case_*.c)
+TEST_FILES = $(BTF_C_FILES)
+
 # Also test sub-register code-gen if LLVM has eBPF v3 processor support which
 # contains both ALU32 and JMP32 instructions.
 SUBREG_CODEGEN := $(shell echo "int cal(int a) { return a > 0; }" | \
@@ -68,7 +71,8 @@ TEST_PROGS := test_kmod.sh \
 TEST_PROGS_EXTENDED := with_addr.sh \
 	with_tunnels.sh \
 	tcp_client.py \
-	tcp_server.py
+	tcp_server.py \
+	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/config b/tools/testing/selftests/bpf/config
index f7a0744db31e..5dc109f4c097 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -34,3 +34,4 @@ CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
 CONFIG_IPV6_SIT=m
+CONFIG_BPF_JIT=y
diff --git a/tools/testing/selftests/bpf/test_btf_dump.c b/tools/testing/selftests/bpf/test_btf_dump.c
index 8f850823d35f..6e75dd3cb14f 100644
--- a/tools/testing/selftests/bpf/test_btf_dump.c
+++ b/tools/testing/selftests/bpf/test_btf_dump.c
@@ -97,6 +97,13 @@ int test_btf_dump_case(int n, struct btf_dump_test_case *test_case)
 	}
 
 	snprintf(test_file, sizeof(test_file), "progs/%s.c", test_case->name);
+	if (access(test_file, R_OK) == -1)
+		/*
+		 * When the test is run with O=, kselftest copies TEST_FILES
+		 * without preserving the directory structure.
+		 */
+		snprintf(test_file, sizeof(test_file), "%s.c",
+			test_case->name);
 	/*
 	 * Diff test output and expected test output, contained between
 	 * START-EXPECTED-OUTPUT and END-EXPECTED-OUTPUT lines in test case.
diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c
index 2fc4625c1a15..655729004391 100644
--- a/tools/testing/selftests/bpf/test_cgroup_storage.c
+++ b/tools/testing/selftests/bpf/test_cgroup_storage.c
@@ -20,9 +20,9 @@ int main(int argc, char **argv)
 		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_LDX_MEM(BPF_DW, 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_STX_MEM(BPF_DW, 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 */
@@ -30,7 +30,7 @@ int main(int argc, char **argv)
 			     BPF_FUNC_get_local_storage),
 		BPF_MOV64_IMM(BPF_REG_1, 1),
 		BPF_STX_XADD(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
-		BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+		BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
 		BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x1),
 		BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
 		BPF_EXIT_INSN(),
diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c
index fb679ac3d4b0..0e6652733462 100644
--- a/tools/testing/selftests/bpf/test_sock.c
+++ b/tools/testing/selftests/bpf/test_sock.c
@@ -13,6 +13,7 @@
 #include <bpf/bpf.h>
 
 #include "cgroup_helpers.h"
+#include "bpf_endian.h"
 #include "bpf_rlimit.h"
 #include "bpf_util.h"
 
@@ -232,7 +233,8 @@ static struct sock_test tests[] = {
 			/* if (ip == expected && port == expected) */
 			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
 				    offsetof(struct bpf_sock, src_ip6[3])),
-			BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x01000000, 4),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_7,
+				    __bpf_constant_ntohl(0x00000001), 4),
 			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
 				    offsetof(struct bpf_sock, src_port)),
 			BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x2001, 2),
@@ -261,7 +263,8 @@ static struct sock_test tests[] = {
 			/* if (ip == expected && port == expected) */
 			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
 				    offsetof(struct bpf_sock, src_ip4)),
-			BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x0100007F, 4),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_7,
+				    __bpf_constant_ntohl(0x7F000001), 4),
 			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
 				    offsetof(struct bpf_sock, src_port)),
 			BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x1002, 2),
diff --git a/tools/testing/selftests/bpf/verifier/loops1.c b/tools/testing/selftests/bpf/verifier/loops1.c
index 5e980a5ab69d..1fc4e61e9f9f 100644
--- a/tools/testing/selftests/bpf/verifier/loops1.c
+++ b/tools/testing/selftests/bpf/verifier/loops1.c
@@ -159,3 +159,31 @@
 	.errstr = "loop detected",
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 },
+{
+	"not-taken loop with back jump to 1st insn",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 123),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 4, -2),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.retval = 123,
+},
+{
+	"taken loop with back jump to 1st insn",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_1, 10),
+	BPF_MOV64_IMM(BPF_REG_2, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1),
+	BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 1),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, -3),
+	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.retval = 55,
+},
diff --git a/tools/testing/selftests/kvm/include/evmcs.h b/tools/testing/selftests/kvm/include/evmcs.h
index 4059014d93ea..4912d23844bc 100644
--- a/tools/testing/selftests/kvm/include/evmcs.h
+++ b/tools/testing/selftests/kvm/include/evmcs.h
@@ -220,6 +220,8 @@ struct hv_enlightened_vmcs {
 struct hv_enlightened_vmcs *current_evmcs;
 struct hv_vp_assist_page *current_vp_assist;
 
+int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id);
+
 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) |
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 6cb34a0fa200..0a5e487dbc50 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -1060,9 +1060,11 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
         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);
+	if (kvm_check_cap(KVM_CAP_XCRS)) {
+		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",
@@ -1103,9 +1105,11 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s
         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);
+	if (kvm_check_cap(KVM_CAP_XCRS)) {
+		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",
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index 204f847bd065..9cef0455b819 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -12,6 +12,26 @@
 
 bool enable_evmcs;
 
+int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id)
+{
+	uint16_t evmcs_ver;
+
+	struct kvm_enable_cap enable_evmcs_cap = {
+		.cap = KVM_CAP_HYPERV_ENLIGHTENED_VMCS,
+		 .args[0] = (unsigned long)&evmcs_ver
+	};
+
+	vcpu_ioctl(vm, vcpu_id, KVM_ENABLE_CAP, &enable_evmcs_cap);
+
+	/* KVM should return supported EVMCS version range */
+	TEST_ASSERT(((evmcs_ver >> 8) >= (evmcs_ver & 0xff)) &&
+		    (evmcs_ver & 0xff) > 0,
+		    "Incorrect EVMCS version range: %x:%x\n",
+		    evmcs_ver & 0xff, evmcs_ver >> 8);
+
+	return evmcs_ver;
+}
+
 /* Allocate memory regions for nested VMX tests.
  *
  * Input Args:
diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
index f95c08343b48..92915e6408e7 100644
--- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
@@ -79,11 +79,6 @@ int main(int argc, char *argv[])
 	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
-	};
 
 	/* Create VM */
 	vm = vm_create_default(VCPU_ID, 0, guest_code);
@@ -96,13 +91,7 @@ int main(int argc, char *argv[])
 		exit(KSFT_SKIP);
 	}
 
-	vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap);
-
-	/* KVM should return supported EVMCS version range */
-	TEST_ASSERT(((evmcs_ver >> 8) >= (evmcs_ver & 0xff)) &&
-		    (evmcs_ver & 0xff) > 0,
-		    "Incorrect EVMCS version range: %x:%x\n",
-		    evmcs_ver & 0xff, evmcs_ver >> 8);
+	vcpu_enable_evmcs(vm, VCPU_ID);
 
 	run = vcpu_state(vm, VCPU_ID);
 
@@ -146,7 +135,7 @@ int main(int argc, char *argv[])
 		kvm_vm_restart(vm, O_RDWR);
 		vm_vcpu_add(vm, VCPU_ID);
 		vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
-		vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap);
+		vcpu_enable_evmcs(vm, VCPU_ID);
 		vcpu_load_state(vm, VCPU_ID, state);
 		run = vcpu_state(vm, VCPU_ID);
 		free(state);
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
index f72b3043db0e..ee59831fbc98 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
@@ -18,6 +18,7 @@
 #include "test_util.h"
 #include "kvm_util.h"
 #include "processor.h"
+#include "vmx.h"
 
 #define VCPU_ID 0
 
@@ -106,12 +107,7 @@ int main(int argc, char *argv[])
 {
 	struct kvm_vm *vm;
 	int rv;
-	uint16_t evmcs_ver;
 	struct kvm_cpuid2 *hv_cpuid_entries;
-	struct kvm_enable_cap enable_evmcs_cap = {
-		.cap = KVM_CAP_HYPERV_ENLIGHTENED_VMCS,
-		 .args[0] = (unsigned long)&evmcs_ver
-	};
 
 	/* Tell stdout not to buffer its content */
 	setbuf(stdout, NULL);
@@ -136,14 +132,14 @@ int main(int argc, char *argv[])
 
 	free(hv_cpuid_entries);
 
-	rv = _vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap);
-
-	if (rv) {
+	if (!kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) {
 		fprintf(stderr,
 			"Enlightened VMCS is unsupported, skip related test\n");
 		goto vm_free;
 	}
 
+	vcpu_enable_evmcs(vm, VCPU_ID);
+
 	hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm);
 	if (!hv_cpuid_entries)
 		return 1;
diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
index 40050e44ec0a..f9334bd3cce9 100644
--- a/tools/testing/selftests/kvm/x86_64/platform_info_test.c
+++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
@@ -99,8 +99,8 @@ int main(int argc, char *argv[])
 	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);
+	test_msr_platform_info_disabled(vm);
 	vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, msr_platform_info);
 
 	kvm_vm_free(vm);
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
index ed7218d166da..853e370e8a39 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
@@ -25,24 +25,17 @@
 #define VMCS12_REVISION 0x11e57ed0
 #define VCPU_ID 5
 
+bool have_evmcs;
+
 void test_nested_state(struct kvm_vm *vm, struct kvm_nested_state *state)
 {
-	volatile struct kvm_run *run;
-
 	vcpu_nested_state_set(vm, VCPU_ID, state, false);
-	run = vcpu_state(vm, VCPU_ID);
-	vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN,
-		"Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s),\n",
-		run->exit_reason,
-		exit_reason_str(run->exit_reason));
 }
 
 void test_nested_state_expect_errno(struct kvm_vm *vm,
 				    struct kvm_nested_state *state,
 				    int expected_errno)
 {
-	volatile struct kvm_run *run;
 	int rv;
 
 	rv = vcpu_nested_state_set(vm, VCPU_ID, state, true);
@@ -50,12 +43,6 @@ void test_nested_state_expect_errno(struct kvm_vm *vm,
 		"Expected %s (%d) from vcpu_nested_state_set but got rv: %i errno: %s (%d)",
 		strerror(expected_errno), expected_errno, rv, strerror(errno),
 		errno);
-	run = vcpu_state(vm, VCPU_ID);
-	vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN,
-		"Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s),\n",
-		run->exit_reason,
-		exit_reason_str(run->exit_reason));
 }
 
 void test_nested_state_expect_einval(struct kvm_vm *vm,
@@ -90,8 +77,9 @@ void set_default_vmx_state(struct kvm_nested_state *state, int size)
 {
 	memset(state, 0, size);
 	state->flags = KVM_STATE_NESTED_GUEST_MODE  |
-			KVM_STATE_NESTED_RUN_PENDING |
-			KVM_STATE_NESTED_EVMCS;
+			KVM_STATE_NESTED_RUN_PENDING;
+	if (have_evmcs)
+		state->flags |= KVM_STATE_NESTED_EVMCS;
 	state->format = 0;
 	state->size = size;
 	state->hdr.vmx.vmxon_pa = 0x1000;
@@ -141,13 +129,19 @@ void test_vmx_nested_state(struct kvm_vm *vm)
 	/*
 	 * Setting vmxon_pa == -1ull and vmcs_pa == -1ull exits early without
 	 * setting the nested state but flags other than eVMCS must be clear.
+	 * The eVMCS flag can be set if the enlightened VMCS capability has
+	 * been enabled.
 	 */
 	set_default_vmx_state(state, state_sz);
 	state->hdr.vmx.vmxon_pa = -1ull;
 	state->hdr.vmx.vmcs12_pa = -1ull;
 	test_nested_state_expect_einval(vm, state);
 
-	state->flags = KVM_STATE_NESTED_EVMCS;
+	state->flags &= KVM_STATE_NESTED_EVMCS;
+	if (have_evmcs) {
+		test_nested_state_expect_einval(vm, state);
+		vcpu_enable_evmcs(vm, VCPU_ID);
+	}
 	test_nested_state(vm, state);
 
 	/* It is invalid to have vmxon_pa == -1ull and SMM flags non-zero. */
@@ -232,6 +226,8 @@ int main(int argc, char *argv[])
 	struct kvm_nested_state state;
 	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
 
+	have_evmcs = kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS);
+
 	if (!kvm_check_cap(KVM_CAP_NESTED_STATE)) {
 		printf("KVM_CAP_NESTED_STATE not available, skipping test\n");
 		exit(KSFT_SKIP);
diff --git a/tools/testing/selftests/net/tcp_fastopen_backup_key.sh b/tools/testing/selftests/net/tcp_fastopen_backup_key.sh
index 41476399e184..f6e65674b83c 100755
--- a/tools/testing/selftests/net/tcp_fastopen_backup_key.sh
+++ b/tools/testing/selftests/net/tcp_fastopen_backup_key.sh
@@ -30,7 +30,7 @@ do_test() {
 	ip netns exec "${NETNS}" ./tcp_fastopen_backup_key "$1"
 	val=$(ip netns exec "${NETNS}" nstat -az | \
 		grep TcpExtTCPFastOpenPassiveFail | awk '{print $2}')
-	if [ $val -ne 0 ]; then
+	if [ "$val" != 0 ]; then
 		echo "FAIL: TcpExtTCPFastOpenPassiveFail non-zero"
 		return 1
 	fi
diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh
index fe52488a6f72..16571ac1dab4 100755
--- a/tools/testing/selftests/netfilter/nft_flowtable.sh
+++ b/tools/testing/selftests/netfilter/nft_flowtable.sh
@@ -321,4 +321,52 @@ else
 	ip netns exec nsr1 nft list ruleset
 fi
 
+KEY_SHA="0x"$(ps -xaf | sha1sum | cut -d " " -f 1)
+KEY_AES="0x"$(ps -xaf | md5sum | cut -d " " -f 1)
+SPI1=$RANDOM
+SPI2=$RANDOM
+
+if [ $SPI1 -eq $SPI2 ]; then
+	SPI2=$((SPI2+1))
+fi
+
+do_esp() {
+    local ns=$1
+    local me=$2
+    local remote=$3
+    local lnet=$4
+    local rnet=$5
+    local spi_out=$6
+    local spi_in=$7
+
+    ip -net $ns xfrm state add src $remote dst $me proto esp spi $spi_in  enc aes $KEY_AES  auth sha1 $KEY_SHA mode tunnel sel src $rnet dst $lnet
+    ip -net $ns xfrm state add src $me  dst $remote proto esp spi $spi_out enc aes $KEY_AES auth sha1 $KEY_SHA mode tunnel sel src $lnet dst $rnet
+
+    # to encrypt packets as they go out (includes forwarded packets that need encapsulation)
+    ip -net $ns xfrm policy add src $lnet dst $rnet dir out tmpl src $me dst $remote proto esp mode tunnel priority 1 action allow
+    # to fwd decrypted packets after esp processing:
+    ip -net $ns xfrm policy add src $rnet dst $lnet dir fwd tmpl src $remote dst $me proto esp mode tunnel priority 1 action allow
+
+}
+
+do_esp nsr1 192.168.10.1 192.168.10.2 10.0.1.0/24 10.0.2.0/24 $SPI1 $SPI2
+
+do_esp nsr2 192.168.10.2 192.168.10.1 10.0.2.0/24 10.0.1.0/24 $SPI2 $SPI1
+
+ip netns exec nsr1 nft delete table ip nat
+
+# restore default routes
+ip -net ns2 route del 192.168.10.1 via 10.0.2.1
+ip -net ns2 route add default via 10.0.2.1
+ip -net ns2 route add default via dead:2::1
+
+test_tcp_forwarding ns1 ns2
+if [ $? -eq 0 ] ;then
+	echo "PASS: ipsec tunnel mode for ns1/ns2"
+else
+	echo "FAIL: ipsec tunnel mode for ns1/ns2"
+	ip netns exec nsr1 nft list ruleset 1>&2
+	ip netns exec nsr1 cat /proc/net/xfrm_stat 1>&2
+fi
+
 exit $ret
diff --git a/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py
index affa7f2d9670..9539cffa9e5e 100644
--- a/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py
+++ b/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py
@@ -64,7 +64,7 @@ class SubPlugin(TdcPlugin):
             cmdlist.insert(0, self.args.NAMES['NS'])
             cmdlist.insert(0, 'exec')
             cmdlist.insert(0, 'netns')
-            cmdlist.insert(0, 'ip')
+            cmdlist.insert(0, self.args.NAMES['IP'])
         else:
             pass
 
@@ -78,16 +78,16 @@ class SubPlugin(TdcPlugin):
         return command
 
     def _ports_create(self):
-        cmd = 'ip link add $DEV0 type veth peer name $DEV1'
+        cmd = '$IP link add $DEV0 type veth peer name $DEV1'
         self._exec_cmd('pre', cmd)
-        cmd = 'ip link set $DEV0 up'
+        cmd = '$IP link set $DEV0 up'
         self._exec_cmd('pre', cmd)
         if not self.args.namespace:
-            cmd = 'ip link set $DEV1 up'
+            cmd = '$IP link set $DEV1 up'
             self._exec_cmd('pre', cmd)
 
     def _ports_destroy(self):
-        cmd = 'ip link del $DEV0'
+        cmd = '$IP link del $DEV0'
         self._exec_cmd('post', cmd)
 
     def _ns_create(self):
@@ -97,16 +97,16 @@ class SubPlugin(TdcPlugin):
         '''
         self._ports_create()
         if self.args.namespace:
-            cmd = 'ip netns add {}'.format(self.args.NAMES['NS'])
+            cmd = '$IP netns add {}'.format(self.args.NAMES['NS'])
             self._exec_cmd('pre', cmd)
-            cmd = 'ip link set $DEV1 netns {}'.format(self.args.NAMES['NS'])
+            cmd = '$IP link set $DEV1 netns {}'.format(self.args.NAMES['NS'])
             self._exec_cmd('pre', cmd)
-            cmd = 'ip -n {} link set $DEV1 up'.format(self.args.NAMES['NS'])
+            cmd = '$IP -n {} link set $DEV1 up'.format(self.args.NAMES['NS'])
             self._exec_cmd('pre', cmd)
             if self.args.device:
-                cmd = 'ip link set $DEV2 netns {}'.format(self.args.NAMES['NS'])
+                cmd = '$IP link set $DEV2 netns {}'.format(self.args.NAMES['NS'])
                 self._exec_cmd('pre', cmd)
-                cmd = 'ip -n {} link set $DEV2 up'.format(self.args.NAMES['NS'])
+                cmd = '$IP -n {} link set $DEV2 up'.format(self.args.NAMES['NS'])
                 self._exec_cmd('pre', cmd)
 
     def _ns_destroy(self):
@@ -115,7 +115,7 @@ class SubPlugin(TdcPlugin):
         devices as well)
         '''
         if self.args.namespace:
-            cmd = 'ip netns delete {}'.format(self.args.NAMES['NS'])
+            cmd = '$IP netns delete {}'.format(self.args.NAMES['NS'])
             self._exec_cmd('post', cmd)
 
     def _exec_cmd(self, stage, command):
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
index bf5ebf59c2d4..9cdd2e31ac2c 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
@@ -670,5 +670,52 @@
         "teardown": [
             "$TC actions flush action skbedit"
         ]
+    },
+    {
+        "id": "630c",
+        "name": "Add batch of 32 skbedit actions with all parameters and cookie",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action skbedit queue_mapping 2 priority 10 mark 7/0xaabbccdd ptype host inheritdsfield index \\$i cookie aabbccddeeff112233445566778800a1 \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "^[ \t]+index [0-9]+ ref",
+        "matchCount": "32",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "706d",
+        "name": "Delete batch of 32 skbedit actions with all parameters",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ],
+            "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action skbedit queue_mapping 2 priority 10 mark 7/0xaabbccdd ptype host inheritdsfield index \\$i \\\"; args=\\\"\\$args\\$cmd\\\"; done && $TC actions add \\$args\""
+        ],
+        "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action skbedit index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "^[ \t]+index [0-9]+ ref",
+        "matchCount": "0",
+        "teardown": []
     }
 ]