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>

36 files changed, 860 insertions, 224 deletions

diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index 404d4b9ffe76..df1153cea0b7 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -32,6 +32,7 @@
 
 #ifndef __KERNEL__
 #include <stdlib.h>
+#include <time.h>
 #endif
 
 /*
diff --git a/tools/io_uring/io_uring-bench.c b/tools/io_uring/io_uring-bench.c
index 512306a37531..0f257139b003 100644
--- a/tools/io_uring/io_uring-bench.c
+++ b/tools/io_uring/io_uring-bench.c
@@ -32,10 +32,6 @@
 #include "liburing.h"
 #include "barrier.h"
 
-#ifndef IOCQE_FLAG_CACHEHIT
-#define IOCQE_FLAG_CACHEHIT	(1U << 0)
-#endif
-
 #define min(a, b)		((a < b) ? (a) : (b))
 
 struct io_sq_ring {
@@ -85,7 +81,6 @@ struct submitter {
 	unsigned long reaps;
 	unsigned long done;
 	unsigned long calls;
-	unsigned long cachehit, cachemiss;
 	volatile int finish;
 
 	__s32 *fds;
@@ -270,10 +265,6 @@ static int reap_events(struct submitter *s)
 				return -1;
 			}
 		}
-		if (cqe->flags & IOCQE_FLAG_CACHEHIT)
-			s->cachehit++;
-		else
-			s->cachemiss++;
 		reaped++;
 		head++;
 	} while (1);
@@ -489,7 +480,7 @@ static void file_depths(char *buf)
 int main(int argc, char *argv[])
 {
 	struct submitter *s = &submitters[0];
-	unsigned long done, calls, reap, cache_hit, cache_miss;
+	unsigned long done, calls, reap;
 	int err, i, flags, fd;
 	char *fdepths;
 	void *ret;
@@ -569,44 +560,29 @@ int main(int argc, char *argv[])
 	pthread_create(&s->thread, NULL, submitter_fn, s);
 
 	fdepths = malloc(8 * s->nr_files);
-	cache_hit = cache_miss = reap = calls = done = 0;
+	reap = calls = done = 0;
 	do {
 		unsigned long this_done = 0;
 		unsigned long this_reap = 0;
 		unsigned long this_call = 0;
-		unsigned long this_cache_hit = 0;
-		unsigned long this_cache_miss = 0;
 		unsigned long rpc = 0, ipc = 0;
-		double hit = 0.0;
 
 		sleep(1);
 		this_done += s->done;
 		this_call += s->calls;
 		this_reap += s->reaps;
-		this_cache_hit += s->cachehit;
-		this_cache_miss += s->cachemiss;
-		if (this_cache_hit && this_cache_miss) {
-			unsigned long hits, total;
-
-			hits = this_cache_hit - cache_hit;
-			total = hits + this_cache_miss - cache_miss;
-			hit = (double) hits / (double) total;
-			hit *= 100.0;
-		}
 		if (this_call - calls) {
 			rpc = (this_done - done) / (this_call - calls);
 			ipc = (this_reap - reap) / (this_call - calls);
 		} else
 			rpc = ipc = -1;
 		file_depths(fdepths);
-		printf("IOPS=%lu, IOS/call=%ld/%ld, inflight=%u (%s), Cachehit=%0.2f%%\n",
+		printf("IOPS=%lu, IOS/call=%ld/%ld, inflight=%u (%s)\n",
 				this_done - done, rpc, ipc, s->inflight,
-				fdepths, hit);
+				fdepths);
 		done = this_done;
 		calls = this_call;
 		reap = this_reap;
-		cache_hit = s->cachehit;
-		cache_miss = s->cachemiss;
 	} while (!finish);
 
 	pthread_join(s->thread, &ret);
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 5bf8e52c41fc..8e7c56e9590f 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -177,7 +177,7 @@ $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
 
 $(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN)
 	$(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(VERSION) \
-				    -Wl,--version-script=$(VERSION_SCRIPT) $^ -o $@
+				    -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@
 	@ln -sf $(@F) $(OUTPUT)libbpf.so
 	@ln -sf $(@F) $(OUTPUT)libbpf.so.$(VERSION)
 
@@ -220,8 +220,9 @@ install_lib: all_cmd
 install_headers:
 	$(call QUIET_INSTALL, headers) \
 		$(call do_install,bpf.h,$(prefix)/include/bpf,644); \
-		$(call do_install,libbpf.h,$(prefix)/include/bpf,644);
-		$(call do_install,btf.h,$(prefix)/include/bpf,644);
+		$(call do_install,libbpf.h,$(prefix)/include/bpf,644); \
+		$(call do_install,btf.h,$(prefix)/include/bpf,644); \
+		$(call do_install,xsk.h,$(prefix)/include/bpf,644);
 
 install: install_lib
 
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 87e3020ac1bc..cf119c9b6f27 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -2107,6 +2107,9 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 		return fwd_kind == real_kind;
 	}
 
+	if (cand_kind != canon_kind)
+		return 0;
+
 	switch (cand_kind) {
 	case BTF_KIND_INT:
 		return btf_equal_int(cand_type, canon_type);
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 87494c7c619d..981c6ce2da2c 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -2233,7 +2233,7 @@ eval_type_str(unsigned long long val, const char *type, int pointer)
 		return val & 0xffffffff;
 
 	if (strcmp(type, "u64") == 0 ||
-	    strcmp(type, "s64"))
+	    strcmp(type, "s64") == 0)
 		return val;
 
 	if (strcmp(type, "s8") == 0)
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 5dde107083c6..479196aeb409 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -165,6 +165,7 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func,
 		"fortify_panic",
 		"usercopy_abort",
 		"machine_real_restart",
+		"rewind_stack_do_exit",
 	};
 
 	if (func->bind == STB_WEAK)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 49ee3c2033ec..c3625ec374e0 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1308,6 +1308,7 @@ static void init_features(struct perf_session *session)
 	for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++)
 		perf_header__set_feat(&session->header, feat);
 
+	perf_header__clear_feat(&session->header, HEADER_DIR_FORMAT);
 	perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
 	perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
 	perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 1999d6533d12..fbbb0da43abb 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1377,6 +1377,7 @@ int cmd_top(int argc, const char **argv)
 			 * */
 			.overwrite	= 0,
 			.sample_time	= true,
+			.sample_time_set = true,
 		},
 		.max_stack	     = sysctl__max_stack(),
 		.annotation_opts     = annotation__default_options,
diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py
index 3b71902a5a21..bf271fbc3a88 100644
--- a/tools/perf/scripts/python/export-to-sqlite.py
+++ b/tools/perf/scripts/python/export-to-sqlite.py
@@ -331,7 +331,7 @@ if perf_db_export_calls:
 			'return_id,'
 			'CASE WHEN flags=0 THEN \'\' WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' WHEN flags=6 THEN \'jump\' ELSE flags END AS flags,'
 			'parent_call_path_id,'
-			'parent_id'
+			'calls.parent_id'
 		' FROM calls INNER JOIN call_paths ON call_paths.id = call_path_id')
 
 do_query(query, 'CREATE VIEW samples_view AS '
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index c6351b557bb0..9494f9dc61ec 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -57,9 +57,11 @@ struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
 		else if (prog_id > node->info_linear->info.id)
 			n = n->rb_right;
 		else
-			break;
+			goto out;
 	}
+	node = NULL;
 
+out:
 	up_read(&env->bpf_progs.lock);
 	return node;
 }
@@ -109,10 +111,12 @@ struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id)
 		else if (btf_id > node->id)
 			n = n->rb_right;
 		else
-			break;
+			goto out;
 	}
+	node = NULL;
 
 	up_read(&env->bpf_progs.lock);
+out:
 	return node;
 }
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 6689378ee577..51ead577533f 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1868,12 +1868,12 @@ static void *perf_evlist__poll_thread(void *arg)
 {
 	struct perf_evlist *evlist = arg;
 	bool draining = false;
-	int i;
+	int i, done = 0;
+
+	while (!done) {
+		bool got_data = false;
 
-	while (draining || !(evlist->thread.done)) {
-		if (draining)
-			draining = false;
-		else if (evlist->thread.done)
+		if (evlist->thread.done)
 			draining = true;
 
 		if (!draining)
@@ -1894,9 +1894,13 @@ static void *perf_evlist__poll_thread(void *arg)
 					pr_warning("cannot locate proper evsel for the side band event\n");
 
 				perf_mmap__consume(map);
+				got_data = true;
 			}
 			perf_mmap__read_done(map);
 		}
+
+		if (draining && !got_data)
+			break;
 	}
 	return NULL;
 }
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 66d066f18b5b..966360844fff 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2368,7 +2368,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		if (data->user_regs.abi) {
 			u64 mask = evsel->attr.sample_regs_user;
 
-			sz = hweight_long(mask) * sizeof(u64);
+			sz = hweight64(mask) * sizeof(u64);
 			OVERFLOW_CHECK(array, sz, max_size);
 			data->user_regs.mask = mask;
 			data->user_regs.regs = (u64 *)array;
@@ -2424,7 +2424,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) {
 			u64 mask = evsel->attr.sample_regs_intr;
 
-			sz = hweight_long(mask) * sizeof(u64);
+			sz = hweight64(mask) * sizeof(u64);
 			OVERFLOW_CHECK(array, sz, max_size);
 			data->intr_regs.mask = mask;
 			data->intr_regs.regs = (u64 *)array;
@@ -2552,7 +2552,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 	if (type & PERF_SAMPLE_REGS_USER) {
 		if (sample->user_regs.abi) {
 			result += sizeof(u64);
-			sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
+			sz = hweight64(sample->user_regs.mask) * sizeof(u64);
 			result += sz;
 		} else {
 			result += sizeof(u64);
@@ -2580,7 +2580,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 	if (type & PERF_SAMPLE_REGS_INTR) {
 		if (sample->intr_regs.abi) {
 			result += sizeof(u64);
-			sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
+			sz = hweight64(sample->intr_regs.mask) * sizeof(u64);
 			result += sz;
 		} else {
 			result += sizeof(u64);
@@ -2710,7 +2710,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 	if (type & PERF_SAMPLE_REGS_USER) {
 		if (sample->user_regs.abi) {
 			*array++ = sample->user_regs.abi;
-			sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
+			sz = hweight64(sample->user_regs.mask) * sizeof(u64);
 			memcpy(array, sample->user_regs.regs, sz);
 			array = (void *)array + sz;
 		} else {
@@ -2746,7 +2746,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 	if (type & PERF_SAMPLE_REGS_INTR) {
 		if (sample->intr_regs.abi) {
 			*array++ = sample->intr_regs.abi;
-			sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
+			sz = hweight64(sample->intr_regs.mask) * sizeof(u64);
 			memcpy(array, sample->intr_regs.regs, sz);
 			array = (void *)array + sz;
 		} else {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index b9e693825873..2d2af2ac2b1e 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2606,6 +2606,7 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused)
 		perf_env__insert_bpf_prog_info(env, info_node);
 	}
 
+	up_write(&env->bpf_progs.lock);
 	return 0;
 out:
 	free(info_linear);
@@ -2623,7 +2624,9 @@ static int process_bpf_prog_info(struct feat_fd *ff __maybe_unused, void *data _
 static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused)
 {
 	struct perf_env *env = &ff->ph->env;
+	struct btf_node *node = NULL;
 	u32 count, i;
+	int err = -1;
 
 	if (ff->ph->needs_swap) {
 		pr_warning("interpreting btf from systems with endianity is not yet supported\n");
@@ -2636,31 +2639,32 @@ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused)
 	down_write(&env->bpf_progs.lock);
 
 	for (i = 0; i < count; ++i) {
-		struct btf_node *node;
 		u32 id, data_size;
 
 		if (do_read_u32(ff, &id))
-			return -1;
+			goto out;
 		if (do_read_u32(ff, &data_size))
-			return -1;
+			goto out;
 
 		node = malloc(sizeof(struct btf_node) + data_size);
 		if (!node)
-			return -1;
+			goto out;
 
 		node->id = id;
 		node->data_size = data_size;
 
-		if (__do_read(ff, node->data, data_size)) {
-			free(node);
-			return -1;
-		}
+		if (__do_read(ff, node->data, data_size))
+			goto out;
 
 		perf_env__insert_btf(env, node);
+		node = NULL;
 	}
 
+	err = 0;
+out:
 	up_write(&env->bpf_progs.lock);
-	return 0;
+	free(node);
+	return err;
 }
 
 struct feature_ops {
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index e32628cd20a7..ee71efb9db62 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -261,6 +261,22 @@ bool __map__is_extra_kernel_map(const struct map *map)
 	return kmap && kmap->name[0];
 }
 
+bool __map__is_bpf_prog(const struct map *map)
+{
+	const char *name;
+
+	if (map->dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
+		return true;
+
+	/*
+	 * If PERF_RECORD_BPF_EVENT is not included, the dso will not have
+	 * type of DSO_BINARY_TYPE__BPF_PROG_INFO. In such cases, we can
+	 * guess the type based on name.
+	 */
+	name = map->dso->short_name;
+	return name && (strstr(name, "bpf_prog_") == name);
+}
+
 bool map__has_symbols(const struct map *map)
 {
 	return dso__has_symbols(map->dso);
@@ -910,10 +926,8 @@ static void __maps__insert_name(struct maps *maps, struct map *map)
 		rc = strcmp(m->dso->short_name, map->dso->short_name);
 		if (rc < 0)
 			p = &(*p)->rb_left;
-		else if (rc  > 0)
-			p = &(*p)->rb_right;
 		else
-			return;
+			p = &(*p)->rb_right;
 	}
 	rb_link_node(&map->rb_node_name, parent, p);
 	rb_insert_color(&map->rb_node_name, &maps->names);
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 0e20749f2c55..dc93787c74f0 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -159,10 +159,12 @@ int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name,
 
 bool __map__is_kernel(const struct map *map);
 bool __map__is_extra_kernel_map(const struct map *map);
+bool __map__is_bpf_prog(const struct map *map);
 
 static inline bool __map__is_kmodule(const struct map *map)
 {
-	return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map);
+	return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map) &&
+	       !__map__is_bpf_prog(map);
 }
 
 bool map__has_symbols(const struct map *map);
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index c3fad065c89c..c7727be9719f 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -44,6 +44,7 @@
 #include <cpuid.h>
 #include <linux/capability.h>
 #include <errno.h>
+#include <math.h>
 
 char *proc_stat = "/proc/stat";
 FILE *outf;
@@ -63,7 +64,6 @@ unsigned int dump_only;
 unsigned int do_snb_cstates;
 unsigned int do_knl_cstates;
 unsigned int do_slm_cstates;
-unsigned int do_cnl_cstates;
 unsigned int use_c1_residency_msr;
 unsigned int has_aperf;
 unsigned int has_epb;
@@ -141,9 +141,21 @@ unsigned int first_counter_read = 1;
 
 #define RAPL_CORES_ENERGY_STATUS	(1 << 9)
 					/* 0x639 MSR_PP0_ENERGY_STATUS */
+#define RAPL_PER_CORE_ENERGY	(1 << 10)
+					/* Indicates cores energy collection is per-core,
+					 * not per-package. */
+#define RAPL_AMD_F17H		(1 << 11)
+					/* 0xc0010299 MSR_RAPL_PWR_UNIT */
+					/* 0xc001029a MSR_CORE_ENERGY_STAT */
+					/* 0xc001029b MSR_PKG_ENERGY_STAT */
 #define RAPL_CORES (RAPL_CORES_ENERGY_STATUS | RAPL_CORES_POWER_LIMIT)
 #define	TJMAX_DEFAULT	100
 
+/* MSRs that are not yet in the kernel-provided header. */
+#define MSR_RAPL_PWR_UNIT	0xc0010299
+#define MSR_CORE_ENERGY_STAT	0xc001029a
+#define MSR_PKG_ENERGY_STAT	0xc001029b
+
 #define MAX(a, b) ((a) > (b) ? (a) : (b))
 
 /*
@@ -187,6 +199,7 @@ struct core_data {
 	unsigned long long c7;
 	unsigned long long mc6_us;	/* duplicate as per-core for now, even though per module */
 	unsigned int core_temp_c;
+	unsigned int core_energy;	/* MSR_CORE_ENERGY_STAT */
 	unsigned int core_id;
 	unsigned long long counter[MAX_ADDED_COUNTERS];
 } *core_even, *core_odd;
@@ -273,6 +286,7 @@ struct system_summary {
 
 struct cpu_topology {
 	int physical_package_id;
+	int die_id;
 	int logical_cpu_id;
 	int physical_node_id;
 	int logical_node_id;	/* 0-based count within the package */
@@ -283,6 +297,7 @@ struct cpu_topology {
 
 struct topo_params {
 	int num_packages;
+	int num_die;
 	int num_cpus;
 	int num_cores;
 	int max_cpu_num;
@@ -314,9 +329,8 @@ int for_all_cpus(int (func)(struct thread_data *, struct core_data *, struct pkg
 	int retval, pkg_no, core_no, thread_no, node_no;
 
 	for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) {
-		for (core_no = 0; core_no < topo.cores_per_node; ++core_no) {
-			for (node_no = 0; node_no < topo.nodes_per_pkg;
-			     node_no++) {
+		for (node_no = 0; node_no < topo.nodes_per_pkg; node_no++) {
+			for (core_no = 0; core_no < topo.cores_per_node; ++core_no) {
 				for (thread_no = 0; thread_no <
 					topo.threads_per_core; ++thread_no) {
 					struct thread_data *t;
@@ -442,6 +456,7 @@ struct msr_counter bic[] = {
 	{ 0x0, "CPU" },
 	{ 0x0, "APIC" },
 	{ 0x0, "X2APIC" },
+	{ 0x0, "Die" },
 };
 
 #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
@@ -495,6 +510,7 @@ struct msr_counter bic[] = {
 #define	BIC_CPU		(1ULL << 47)
 #define	BIC_APIC	(1ULL << 48)
 #define	BIC_X2APIC	(1ULL << 49)
+#define	BIC_Die		(1ULL << 50)
 
 #define BIC_DISABLED_BY_DEFAULT	(BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
 
@@ -621,6 +637,8 @@ void print_header(char *delim)
 		outp += sprintf(outp, "%sTime_Of_Day_Seconds", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Package))
 		outp += sprintf(outp, "%sPackage", (printed++ ? delim : ""));
+	if (DO_BIC(BIC_Die))
+		outp += sprintf(outp, "%sDie", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Node))
 		outp += sprintf(outp, "%sNode", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Core))
@@ -667,7 +685,7 @@ void print_header(char *delim)
 
 	if (DO_BIC(BIC_CPU_c1))
 		outp += sprintf(outp, "%sCPU%%c1", (printed++ ? delim : ""));
-	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates)
+	if (DO_BIC(BIC_CPU_c3))
 		outp += sprintf(outp, "%sCPU%%c3", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_CPU_c6))
 		outp += sprintf(outp, "%sCPU%%c6", (printed++ ? delim : ""));
@@ -680,6 +698,14 @@ void print_header(char *delim)
 	if (DO_BIC(BIC_CoreTmp))
 		outp += sprintf(outp, "%sCoreTmp", (printed++ ? delim : ""));
 
+	if (do_rapl && !rapl_joules) {
+		if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY))
+			outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : ""));
+	} else if (do_rapl && rapl_joules) {
+		if (DO_BIC(BIC_Cor_J) && (do_rapl & RAPL_PER_CORE_ENERGY))
+			outp += sprintf(outp, "%sCor_J", (printed++ ? delim : ""));
+	}
+
 	for (mp = sys.cp; mp; mp = mp->next) {
 		if (mp->format == FORMAT_RAW) {
 			if (mp->width == 64)
@@ -734,7 +760,7 @@ void print_header(char *delim)
 	if (do_rapl && !rapl_joules) {
 		if (DO_BIC(BIC_PkgWatt))
 			outp += sprintf(outp, "%sPkgWatt", (printed++ ? delim : ""));
-		if (DO_BIC(BIC_CorWatt))
+		if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY))
 			outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_GFXWatt))
 			outp += sprintf(outp, "%sGFXWatt", (printed++ ? delim : ""));
@@ -747,7 +773,7 @@ void print_header(char *delim)
 	} else if (do_rapl && rapl_joules) {
 		if (DO_BIC(BIC_Pkg_J))
 			outp += sprintf(outp, "%sPkg_J", (printed++ ? delim : ""));
-		if (DO_BIC(BIC_Cor_J))
+		if (DO_BIC(BIC_Cor_J) && !(do_rapl & RAPL_PER_CORE_ENERGY))
 			outp += sprintf(outp, "%sCor_J", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_GFX_J))
 			outp += sprintf(outp, "%sGFX_J", (printed++ ? delim : ""));
@@ -808,6 +834,7 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "c6: %016llX\n", c->c6);
 		outp += sprintf(outp, "c7: %016llX\n", c->c7);
 		outp += sprintf(outp, "DTS: %dC\n", c->core_temp_c);
+		outp += sprintf(outp, "Joules: %0X\n", c->core_energy);
 
 		for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 			outp += sprintf(outp, "cADDED [%d] msr0x%x: %08llX\n",
@@ -904,6 +931,8 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (t == &average.threads) {
 		if (DO_BIC(BIC_Package))
 			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+		if (DO_BIC(BIC_Die))
+			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_Node))
 			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_Core))
@@ -921,6 +950,12 @@ int format_counters(struct thread_data *t, struct core_data *c,
 			else
 				outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 		}
+		if (DO_BIC(BIC_Die)) {
+			if (c)
+				outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), cpus[t->cpu_id].die_id);
+			else
+				outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+		}
 		if (DO_BIC(BIC_Node)) {
 			if (t)
 				outp += sprintf(outp, "%s%d",
@@ -1003,7 +1038,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		goto done;
 
-	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates)
+	if (DO_BIC(BIC_CPU_c3))
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c3/tsc);
 	if (DO_BIC(BIC_CPU_c6))
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c6/tsc);
@@ -1033,6 +1068,20 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		}
 	}
 
+	/*
+	 * If measurement interval exceeds minimum RAPL Joule Counter range,
+	 * indicate that results are suspect by printing "**" in fraction place.
+	 */
+	if (interval_float < rapl_joule_counter_range)
+		fmt8 = "%s%.2f";
+	else
+		fmt8 = "%6.0f**";
+
+	if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY))
+		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float);
+	if (DO_BIC(BIC_Cor_J) && (do_rapl & RAPL_PER_CORE_ENERGY))
+		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units);
+
 	/* print per-package data only for 1st core in package */
 	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
 		goto done;
@@ -1085,18 +1134,9 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (DO_BIC(BIC_SYS_LPI))
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->sys_lpi / 1000000.0 / interval_float);
 
-	/*
- 	 * If measurement interval exceeds minimum RAPL Joule Counter range,
- 	 * indicate that results are suspect by printing "**" in fraction place.
- 	 */
-	if (interval_float < rapl_joule_counter_range)
-		fmt8 = "%s%.2f";
-	else
-		fmt8 = "%6.0f**";
-
 	if (DO_BIC(BIC_PkgWatt))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float);
-	if (DO_BIC(BIC_CorWatt))
+	if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float);
 	if (DO_BIC(BIC_GFXWatt))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units / interval_float);
@@ -1104,7 +1144,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_dram * rapl_dram_energy_units / interval_float);
 	if (DO_BIC(BIC_Pkg_J))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units);
-	if (DO_BIC(BIC_Cor_J))
+	if (DO_BIC(BIC_Cor_J) && !(do_rapl & RAPL_PER_CORE_ENERGY))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units);
 	if (DO_BIC(BIC_GFX_J))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units);
@@ -1249,6 +1289,8 @@ delta_core(struct core_data *new, struct core_data *old)
 	old->core_temp_c = new->core_temp_c;
 	old->mc6_us = new->mc6_us - old->mc6_us;
 
+	DELTA_WRAP32(new->core_energy, old->core_energy);
+
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
 			old->counter[i] = new->counter[i];
@@ -1391,6 +1433,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	c->c7 = 0;
 	c->mc6_us = 0;
 	c->core_temp_c = 0;
+	c->core_energy = 0;
 
 	p->pkg_wtd_core_c0 = 0;
 	p->pkg_any_core_c0 = 0;
@@ -1473,6 +1516,8 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 
 	average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c);
 
+	average.cores.core_energy += c->core_energy;
+
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
 			continue;
@@ -1818,7 +1863,7 @@ retry:
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		goto done;
 
-	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates) {
+	if (DO_BIC(BIC_CPU_c3)) {
 		if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3))
 			return -6;
 	}
@@ -1845,6 +1890,12 @@ retry:
 		c->core_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F);
 	}
 
+	if (do_rapl & RAPL_AMD_F17H) {
+		if (get_msr(cpu, MSR_CORE_ENERGY_STAT, &msr))
+			return -14;
+		c->core_energy = msr & 0xFFFFFFFF;
+	}
+
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 		if (get_mp(cpu, mp, &c->counter[i]))
 			return -10;
@@ -1934,6 +1985,11 @@ retry:
 			return -16;
 		p->rapl_dram_perf_status = msr & 0xFFFFFFFF;
 	}
+	if (do_rapl & RAPL_AMD_F17H) {
+		if (get_msr(cpu, MSR_PKG_ENERGY_STAT, &msr))
+			return -13;
+		p->energy_pkg = msr & 0xFFFFFFFF;
+	}
 	if (DO_BIC(BIC_PkgTmp)) {
 		if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr))
 			return -17;
@@ -2456,6 +2512,8 @@ void free_all_buffers(void)
 
 /*
  * Parse a file containing a single int.
+ * Return 0 if file can not be opened
+ * Exit if file can be opened, but can not be parsed
  */
 int parse_int_file(const char *fmt, ...)
 {
@@ -2467,7 +2525,9 @@ int parse_int_file(const char *fmt, ...)
 	va_start(args, fmt);
 	vsnprintf(path, sizeof(path), fmt, args);
 	va_end(args);
-	filep = fopen_or_die(path, "r");
+	filep = fopen(path, "r");
+	if (!filep)
+		return 0;
 	if (fscanf(filep, "%d", &value) != 1)
 		err(1, "%s: failed to parse number from file", path);
 	fclose(filep);
@@ -2488,6 +2548,11 @@ int get_physical_package_id(int cpu)
 	return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/physical_package_id", cpu);
 }
 
+int get_die_id(int cpu)
+{
+	return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/die_id", cpu);
+}
+
 int get_core_id(int cpu)
 {
 	return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/core_id", cpu);
@@ -2578,7 +2643,8 @@ int get_thread_siblings(struct cpu_topology *thiscpu)
 	filep = fopen_or_die(path, "r");
 	do {
 		offset -= BITMASK_SIZE;
-		fscanf(filep, "%lx%c", &map, &character);
+		if (fscanf(filep, "%lx%c", &map, &character) != 2)
+			err(1, "%s: failed to parse file", path);
 		for (shift = 0; shift < BITMASK_SIZE; shift++) {
 			if ((map >> shift) & 0x1) {
 				so = shift + offset;
@@ -2855,8 +2921,11 @@ int snapshot_cpu_lpi_us(void)
 	fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", "r");
 
 	retval = fscanf(fp, "%lld", &cpuidle_cur_cpu_lpi_us);
-	if (retval != 1)
-		err(1, "CPU LPI");
+	if (retval != 1) {
+		fprintf(stderr, "Disabling Low Power Idle CPU output\n");
+		BIC_NOT_PRESENT(BIC_CPU_LPI);
+		return -1;
+	}
 
 	fclose(fp);
 
@@ -2878,9 +2947,11 @@ int snapshot_sys_lpi_us(void)
 	fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", "r");
 
 	retval = fscanf(fp, "%lld", &cpuidle_cur_sys_lpi_us);
-	if (retval != 1)
-		err(1, "SYS LPI");
-
+	if (retval != 1) {
+		fprintf(stderr, "Disabling Low Power Idle System output\n");
+		BIC_NOT_PRESENT(BIC_SYS_LPI);
+		return -1;
+	}
 	fclose(fp);
 
 	return 0;
@@ -3410,14 +3481,14 @@ dump_sysfs_cstate_config(void)
 		input = fopen(path, "r");
 		if (input == NULL)
 			continue;
-		fgets(name_buf, sizeof(name_buf), input);
+		if (!fgets(name_buf, sizeof(name_buf), input))
+			err(1, "%s: failed to read file", path);
 
 		 /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
 		sp = strchr(name_buf, '-');
 		if (!sp)
 			sp = strchrnul(name_buf, '\n');
 		*sp = '\0';
-
 		fclose(input);
 
 		sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/desc",
@@ -3425,7 +3496,8 @@ dump_sysfs_cstate_config(void)
 		input = fopen(path, "r");
 		if (input == NULL)
 			continue;
-		fgets(desc, sizeof(desc), input);
+		if (!fgets(desc, sizeof(desc), input))
+			err(1, "%s: failed to read file", path);
 
 		fprintf(outf, "cpu%d: %s: %s", base_cpu, name_buf, desc);
 		fclose(input);
@@ -3444,20 +3516,22 @@ dump_sysfs_pstate_config(void)
 			base_cpu);
 	input = fopen(path, "r");
 	if (input == NULL) {
-		fprintf(stderr, "NSFOD %s\n", path);
+		fprintf(outf, "NSFOD %s\n", path);
 		return;
 	}
-	fgets(driver_buf, sizeof(driver_buf), input);
+	if (!fgets(driver_buf, sizeof(driver_buf), input))
+		err(1, "%s: failed to read file", path);
 	fclose(input);
 
 	sprintf(path, "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_governor",
 			base_cpu);
 	input = fopen(path, "r");
 	if (input == NULL) {
-		fprintf(stderr, "NSFOD %s\n", path);
+		fprintf(outf, "NSFOD %s\n", path);
 		return;
 	}
-	fgets(governor_buf, sizeof(governor_buf), input);
+	if (!fgets(governor_buf, sizeof(governor_buf), input))
+		err(1, "%s: failed to read file", path);
 	fclose(input);
 
 	fprintf(outf, "cpu%d: cpufreq driver: %s", base_cpu, driver_buf);
@@ -3466,7 +3540,8 @@ dump_sysfs_pstate_config(void)
 	sprintf(path, "/sys/devices/system/cpu/cpufreq/boost");
 	input = fopen(path, "r");
 	if (input != NULL) {
-		fscanf(input, "%d", &turbo);
+		if (fscanf(input, "%d", &turbo) != 1)
+			err(1, "%s: failed to parse number from file", path);
 		fprintf(outf, "cpufreq boost: %d\n", turbo);
 		fclose(input);
 	}
@@ -3474,7 +3549,8 @@ dump_sysfs_pstate_config(void)
 	sprintf(path, "/sys/devices/system/cpu/intel_pstate/no_turbo");
 	input = fopen(path, "r");
 	if (input != NULL) {
-		fscanf(input, "%d", &turbo);
+		if (fscanf(input, "%d", &turbo) != 1)
+			err(1, "%s: failed to parse number from file", path);
 		fprintf(outf, "cpufreq intel_pstate no_turbo: %d\n", turbo);
 		fclose(input);
 	}
@@ -3718,7 +3794,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 #define	RAPL_POWER_GRANULARITY	0x7FFF	/* 15 bit power granularity */
 #define	RAPL_TIME_GRANULARITY	0x3F /* 6 bit time granularity */
 
-double get_tdp(unsigned int model)
+double get_tdp_intel(unsigned int model)
 {
 	unsigned long long msr;
 
@@ -3735,6 +3811,16 @@ double get_tdp(unsigned int model)
 	}
 }
 
+double get_tdp_amd(unsigned int family)
+{
+	switch (family) {
+	case 0x17:
+	default:
+		/* This is the max stock TDP of HEDT/Server Fam17h chips */
+		return 250.0;
+	}
+}
+
 /*
  * rapl_dram_energy_units_probe()
  * Energy units are either hard-coded, or come from RAPL Energy Unit MSR.
@@ -3754,21 +3840,12 @@ rapl_dram_energy_units_probe(int  model, double rapl_energy_units)
 	}
 }
 
-
-/*
- * rapl_probe()
- *
- * sets do_rapl, rapl_power_units, rapl_energy_units, rapl_time_units
- */
-void rapl_probe(unsigned int family, unsigned int model)
+void rapl_probe_intel(unsigned int family, unsigned int model)
 {
 	unsigned long long msr;
 	unsigned int time_unit;
 	double tdp;
 
-	if (!genuine_intel)
-		return;
-
 	if (family != 6)
 		return;
 
@@ -3892,13 +3969,69 @@ void rapl_probe(unsigned int family, unsigned int model)
 
 	rapl_time_units = 1.0 / (1 << (time_unit));
 
-	tdp = get_tdp(model);
+	tdp = get_tdp_intel(model);
 
 	rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
 	if (!quiet)
 		fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
+}
 
-	return;
+void rapl_probe_amd(unsigned int family, unsigned int model)
+{
+	unsigned long long msr;
+	unsigned int eax, ebx, ecx, edx;
+	unsigned int has_rapl = 0;
+	double tdp;
+
+	if (max_extended_level >= 0x80000007) {
+		__cpuid(0x80000007, eax, ebx, ecx, edx);
+		/* RAPL (Fam 17h) */
+		has_rapl = edx & (1 << 14);
+	}
+
+	if (!has_rapl)
+		return;
+
+	switch (family) {
+	case 0x17: /* Zen, Zen+ */
+		do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY;
+		if (rapl_joules) {
+			BIC_PRESENT(BIC_Pkg_J);
+			BIC_PRESENT(BIC_Cor_J);
+		} else {
+			BIC_PRESENT(BIC_PkgWatt);
+			BIC_PRESENT(BIC_CorWatt);
+		}
+		break;
+	default:
+		return;
+	}
+
+	if (get_msr(base_cpu, MSR_RAPL_PWR_UNIT, &msr))
+		return;
+
+	rapl_time_units = ldexp(1.0, -(msr >> 16 & 0xf));
+	rapl_energy_units = ldexp(1.0, -(msr >> 8 & 0x1f));
+	rapl_power_units = ldexp(1.0, -(msr & 0xf));
+
+	tdp = get_tdp_amd(model);
+
+	rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
+	if (!quiet)
+		fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
+}
+
+/*
+ * rapl_probe()
+ *
+ * sets do_rapl, rapl_power_units, rapl_energy_units, rapl_time_units
+ */
+void rapl_probe(unsigned int family, unsigned int model)
+{
+	if (genuine_intel)
+		rapl_probe_intel(family, model);
+	if (authentic_amd)
+		rapl_probe_amd(family, model);
 }
 
 void perf_limit_reasons_probe(unsigned int family, unsigned int model)
@@ -4003,6 +4136,7 @@ void print_power_limit_msr(int cpu, unsigned long long msr, char *label)
 int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 {
 	unsigned long long msr;
+	const char *msr_name;
 	int cpu;
 
 	if (!do_rapl)
@@ -4018,10 +4152,17 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		return -1;
 	}
 
-	if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr))
-		return -1;
+	if (do_rapl & RAPL_AMD_F17H) {
+		msr_name = "MSR_RAPL_PWR_UNIT";
+		if (get_msr(cpu, MSR_RAPL_PWR_UNIT, &msr))
+			return -1;
+	} else {
+		msr_name = "MSR_RAPL_POWER_UNIT";
+		if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr))
+			return -1;
+	}
 
-	fprintf(outf, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr,
+	fprintf(outf, "cpu%d: %s: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr_name, msr,
 		rapl_power_units, rapl_energy_units, rapl_time_units);
 
 	if (do_rapl & RAPL_PKG_POWER_INFO) {
@@ -4451,6 +4592,9 @@ unsigned int intel_model_duplicates(unsigned int model)
 	case INTEL_FAM6_KABYLAKE_MOBILE:
 	case INTEL_FAM6_KABYLAKE_DESKTOP:
 		return INTEL_FAM6_SKYLAKE_MOBILE;
+
+	case INTEL_FAM6_ICELAKE_MOBILE:
+		return INTEL_FAM6_CANNONLAKE_MOBILE;
 	}
 	return model;
 }
@@ -4702,7 +4846,9 @@ void process_cpuid()
 	}
 	do_slm_cstates = is_slm(family, model);
 	do_knl_cstates  = is_knl(family, model);
-	do_cnl_cstates = is_cnl(family, model);
+
+	if (do_slm_cstates || do_knl_cstates || is_cnl(family, model))
+		BIC_NOT_PRESENT(BIC_CPU_c3);
 
 	if (!quiet)
 		decode_misc_pwr_mgmt_msr();
@@ -4769,6 +4915,7 @@ void topology_probe()
 	int i;
 	int max_core_id = 0;
 	int max_package_id = 0;
+	int max_die_id = 0;
 	int max_siblings = 0;
 
 	/* Initialize num_cpus, max_cpu_num */
@@ -4835,6 +4982,11 @@ void topology_probe()
 		if (cpus[i].physical_package_id > max_package_id)
 			max_package_id = cpus[i].physical_package_id;
 
+		/* get die information */
+		cpus[i].die_id = get_die_id(i);
+		if (cpus[i].die_id > max_die_id)
+			max_die_id = cpus[i].die_id;
+
 		/* get numa node information */
 		cpus[i].physical_node_id = get_physical_node_id(&cpus[i]);
 		if (cpus[i].physical_node_id > topo.max_node_num)
@@ -4860,6 +5012,13 @@ void topology_probe()
 	if (!summary_only && topo.cores_per_node > 1)
 		BIC_PRESENT(BIC_Core);
 
+	topo.num_die = max_die_id + 1;
+	if (debug > 1)
+		fprintf(outf, "max_die_id %d, sizing for %d die\n",
+				max_die_id, topo.num_die);
+	if (!summary_only && topo.num_die > 1)
+		BIC_PRESENT(BIC_Die);
+
 	topo.num_packages = max_package_id + 1;
 	if (debug > 1)
 		fprintf(outf, "max_package_id %d, sizing for %d packages\n",
@@ -4884,8 +5043,8 @@ void topology_probe()
 		if (cpu_is_not_present(i))
 			continue;
 		fprintf(outf,
-			"cpu %d pkg %d node %d lnode %d core %d thread %d\n",
-			i, cpus[i].physical_package_id,
+			"cpu %d pkg %d die %d node %d lnode %d core %d thread %d\n",
+			i, cpus[i].physical_package_id, cpus[i].die_id,
 			cpus[i].physical_node_id,
 			cpus[i].logical_node_id,
 			cpus[i].physical_core_id,
@@ -5122,7 +5281,7 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-	fprintf(outf, "turbostat version 18.07.27"
+	fprintf(outf, "turbostat version 19.03.20"
 		" - Len Brown <lenb@kernel.org>\n");
 }
 
@@ -5319,7 +5478,8 @@ void probe_sysfs(void)
 		input = fopen(path, "r");
 		if (input == NULL)
 			continue;
-		fgets(name_buf, sizeof(name_buf), input);
+		if (!fgets(name_buf, sizeof(name_buf), input))
+			err(1, "%s: failed to read file", path);
 
 		 /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
 		sp = strchr(name_buf, '-');
@@ -5346,7 +5506,8 @@ void probe_sysfs(void)
 		input = fopen(path, "r");
 		if (input == NULL)
 			continue;
-		fgets(name_buf, sizeof(name_buf), input);
+		if (!fgets(name_buf, sizeof(name_buf), input))
+			err(1, "%s: failed to read file", path);
 		 /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
 		sp = strchr(name_buf, '-');
 		if (!sp)
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index b579f962451d..85ffdcfa596b 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/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
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index bcbd928c96ab..fc818bc1d729 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/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);
 }
diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c
index 284660f5aa95..75b17cada539 100644
--- a/tools/testing/selftests/bpf/progs/bpf_flow.c
+++ b/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);
 }
 
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 23e3b314ca60..ec5794e4205b 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -5777,6 +5777,53 @@ const struct btf_dedup_test dedup_tests[] = {
 	},
 },
 {
+	.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 = {
 		.raw_types = {
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index f2ccae39ee66..fb11240b758b 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -908,6 +908,44 @@
 	.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 = {
 	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
index c4cf6e6d800e..a6c196c8534c 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
+++ b/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
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 7514fcea91a7..f8588cca2bef 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/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)/
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index e2884c2b81ff..6063d5b2f356 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/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
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index efa0aad8b3c6..4ca96b228e46 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/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);
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index f28127f4a3af..dc7fae9fa424 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/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);
+	}
 }
diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
index c49c2a28b0eb..36669684eca5 100644
--- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c
+++ b/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.  */
diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c
new file mode 100644
index 000000000000..fb8086964d83
--- /dev/null
+++ b/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);
+}
diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c
index 30f75856cf39..e0a3c0204b7c 100644
--- a/tools/testing/selftests/kvm/x86_64/state_test.c
+++ b/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.  */
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 1080ff55a788..0d2a5f4f1e63 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/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"
diff --git a/tools/testing/selftests/proc/proc-pid-vm.c b/tools/testing/selftests/proc/proc-pid-vm.c
index 7202bbac976e..853aa164a401 100644
--- a/tools/testing/selftests/proc/proc-pid-vm.c
+++ b/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);
diff --git a/tools/testing/selftests/proc/proc-self-map-files-002.c b/tools/testing/selftests/proc/proc-self-map-files-002.c
index 762cb01f2ca7..47b7473dedef 100644
--- a/tools/testing/selftests/proc/proc-self-map-files-002.c
+++ b/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;
 	}
 
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json
index 27f0acaed880..ddabb160a11b 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json
@@ -144,6 +144,30 @@
         ]
     },
     {
+        "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",
         "category": [
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
index 99a5ffca1088..2d096b2abf2c 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
@@ -19,6 +19,26 @@
         ]
     },
     {
+        "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",
         "category": [
diff --git a/tools/testing/selftests/tpm2/tpm2.py b/tools/testing/selftests/tpm2/tpm2.py
index 40ea95ce2ead..828c18584624 100644
--- a/tools/testing/selftests/tpm2/tpm2.py
+++ b/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()
diff --git a/tools/testing/selftests/tpm2/tpm2_tests.py b/tools/testing/selftests/tpm2/tpm2_tests.py
index 3bb066fea4a0..d4973be53493 100644
--- a/tools/testing/selftests/tpm2/tpm2_tests.py
+++ b/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)