Merge branch 'objtool/urgent'

Fixup conflicts.

# Conflicts:
#	tools/objtool/check.c

77 files changed, 1589 insertions, 426 deletions

diff --git a/tools/arch/x86/include/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h
index 60a89dba01b6..60a89dba01b6 100644
--- a/tools/arch/x86/include/asm/unistd_32.h
+++ b/tools/arch/x86/include/uapi/asm/unistd_32.h
diff --git a/tools/arch/x86/include/asm/unistd_64.h b/tools/arch/x86/include/uapi/asm/unistd_64.h
index 4205ed4158bf..cb52a3a8b8fc 100644
--- a/tools/arch/x86/include/asm/unistd_64.h
+++ b/tools/arch/x86/include/uapi/asm/unistd_64.h
@@ -1,7 +1,4 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __NR_userfaultfd
-#define __NR_userfaultfd 282
-#endif
 #ifndef __NR_perf_event_open
 # define __NR_perf_event_open 298
 #endif
diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c
index c41f95815480..797699462cd8 100644
--- a/tools/arch/x86/lib/insn.c
+++ b/tools/arch/x86/lib/insn.c
@@ -37,10 +37,10 @@
 	((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr)
 
 #define __get_next(t, insn)	\
-	({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); leXX_to_cpu(t, r); })
+	({ t r; memcpy(&r, insn->next_byte, sizeof(t)); insn->next_byte += sizeof(t); leXX_to_cpu(t, r); })
 
 #define __peek_nbyte_next(t, insn, n)	\
-	({ t r = *(t*)((insn)->next_byte + n); leXX_to_cpu(t, r); })
+	({ t r; memcpy(&r, (insn)->next_byte + n, sizeof(t)); leXX_to_cpu(t, r); })
 
 #define get_next(t, insn)	\
 	({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); })
diff --git a/tools/bootconfig/include/linux/memblock.h b/tools/bootconfig/include/linux/memblock.h
index 7862f217d85d..f2e506f7d57f 100644
--- a/tools/bootconfig/include/linux/memblock.h
+++ b/tools/bootconfig/include/linux/memblock.h
@@ -4,9 +4,8 @@
 
 #include <stdlib.h>
 
-#define __pa(addr)	(addr)
 #define SMP_CACHE_BYTES	0
 #define memblock_alloc(size, align)	malloc(size)
-#define memblock_free(paddr, size)	free(paddr)
+#define memblock_free_ptr(paddr, size)	free(paddr)
 
 #endif
diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
index 95c072b70d0e..8816f06fc6c7 100644
--- a/tools/include/linux/compiler-gcc.h
+++ b/tools/include/linux/compiler-gcc.h
@@ -16,9 +16,9 @@
 # define __fallthrough __attribute__ ((fallthrough))
 #endif
 
-#if GCC_VERSION >= 40300
+#if __has_attribute(__error__)
 # define __compiletime_error(message) __attribute__((error(message)))
-#endif /* GCC_VERSION >= 40300 */
+#endif
 
 /* &a[0] degrades to a pointer: a different type from an array */
 #define __must_be_array(a)	BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
@@ -38,7 +38,3 @@
 #endif
 #define __printf(a, b)	__attribute__((format(printf, a, b)))
 #define __scanf(a, b)	__attribute__((format(scanf, a, b)))
-
-#if GCC_VERSION >= 50100
-#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
-#endif
diff --git a/tools/include/linux/overflow.h b/tools/include/linux/overflow.h
index 8712ff70995f..dcb0c1bf6866 100644
--- a/tools/include/linux/overflow.h
+++ b/tools/include/linux/overflow.h
@@ -5,12 +5,9 @@
 #include <linux/compiler.h>
 
 /*
- * In the fallback code below, we need to compute the minimum and
- * maximum values representable in a given type. These macros may also
- * be useful elsewhere, so we provide them outside the
- * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block.
- *
- * It would seem more obvious to do something like
+ * We need to compute the minimum and maximum values representable in a given
+ * type. These macros may also be useful elsewhere. It would seem more obvious
+ * to do something like:
  *
  * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0)
  * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0)
@@ -36,8 +33,6 @@
 #define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T)))
 #define type_min(T) ((T)((T)-type_max(T)-(T)1))
 
-
-#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW
 /*
  * For simplicity and code hygiene, the fallback code below insists on
  * a, b and *d having the same type (similar to the min() and max()
@@ -73,135 +68,6 @@
 	__builtin_mul_overflow(__a, __b, __d);	\
 })
 
-#else
-
-
-/* Checking for unsigned overflow is relatively easy without causing UB. */
-#define __unsigned_add_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = __a + __b;			\
-	*__d < __a;				\
-})
-#define __unsigned_sub_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = __a - __b;			\
-	__a < __b;				\
-})
-/*
- * If one of a or b is a compile-time constant, this avoids a division.
- */
-#define __unsigned_mul_overflow(a, b, d) ({		\
-	typeof(a) __a = (a);				\
-	typeof(b) __b = (b);				\
-	typeof(d) __d = (d);				\
-	(void) (&__a == &__b);				\
-	(void) (&__a == __d);				\
-	*__d = __a * __b;				\
-	__builtin_constant_p(__b) ?			\
-	  __b > 0 && __a > type_max(typeof(__a)) / __b : \
-	  __a > 0 && __b > type_max(typeof(__b)) / __a;	 \
-})
-
-/*
- * For signed types, detecting overflow is much harder, especially if
- * we want to avoid UB. But the interface of these macros is such that
- * we must provide a result in *d, and in fact we must produce the
- * result promised by gcc's builtins, which is simply the possibly
- * wrapped-around value. Fortunately, we can just formally do the
- * operations in the widest relevant unsigned type (u64) and then
- * truncate the result - gcc is smart enough to generate the same code
- * with and without the (u64) casts.
- */
-
-/*
- * Adding two signed integers can overflow only if they have the same
- * sign, and overflow has happened iff the result has the opposite
- * sign.
- */
-#define __signed_add_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = (u64)__a + (u64)__b;		\
-	(((~(__a ^ __b)) & (*__d ^ __a))	\
-		& type_min(typeof(__a))) != 0;	\
-})
-
-/*
- * Subtraction is similar, except that overflow can now happen only
- * when the signs are opposite. In this case, overflow has happened if
- * the result has the opposite sign of a.
- */
-#define __signed_sub_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = (u64)__a - (u64)__b;		\
-	((((__a ^ __b)) & (*__d ^ __a))		\
-		& type_min(typeof(__a))) != 0;	\
-})
-
-/*
- * Signed multiplication is rather hard. gcc always follows C99, so
- * division is truncated towards 0. This means that we can write the
- * overflow check like this:
- *
- * (a > 0 && (b > MAX/a || b < MIN/a)) ||
- * (a < -1 && (b > MIN/a || b < MAX/a) ||
- * (a == -1 && b == MIN)
- *
- * The redundant casts of -1 are to silence an annoying -Wtype-limits
- * (included in -Wextra) warning: When the type is u8 or u16, the
- * __b_c_e in check_mul_overflow obviously selects
- * __unsigned_mul_overflow, but unfortunately gcc still parses this
- * code and warns about the limited range of __b.
- */
-
-#define __signed_mul_overflow(a, b, d) ({				\
-	typeof(a) __a = (a);						\
-	typeof(b) __b = (b);						\
-	typeof(d) __d = (d);						\
-	typeof(a) __tmax = type_max(typeof(a));				\
-	typeof(a) __tmin = type_min(typeof(a));				\
-	(void) (&__a == &__b);						\
-	(void) (&__a == __d);						\
-	*__d = (u64)__a * (u64)__b;					\
-	(__b > 0   && (__a > __tmax/__b || __a < __tmin/__b)) ||	\
-	(__b < (typeof(__b))-1  && (__a > __tmin/__b || __a < __tmax/__b)) || \
-	(__b == (typeof(__b))-1 && __a == __tmin);			\
-})
-
-
-#define check_add_overflow(a, b, d)					\
-	__builtin_choose_expr(is_signed_type(typeof(a)),		\
-			__signed_add_overflow(a, b, d),			\
-			__unsigned_add_overflow(a, b, d))
-
-#define check_sub_overflow(a, b, d)					\
-	__builtin_choose_expr(is_signed_type(typeof(a)),		\
-			__signed_sub_overflow(a, b, d),			\
-			__unsigned_sub_overflow(a, b, d))
-
-#define check_mul_overflow(a, b, d)					\
-	__builtin_choose_expr(is_signed_type(typeof(a)),		\
-			__signed_mul_overflow(a, b, d),			\
-			__unsigned_mul_overflow(a, b, d))
-
-
-#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */
-
 /**
  * array_size() - Calculate size of 2-dimensional array.
  *
diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
index 10911a8cad0f..2df880cefdae 100644
--- a/tools/lib/bpf/linker.c
+++ b/tools/lib/bpf/linker.c
@@ -1649,11 +1649,17 @@ static bool btf_is_non_static(const struct btf_type *t)
 static int find_glob_sym_btf(struct src_obj *obj, Elf64_Sym *sym, const char *sym_name,
 			     int *out_btf_sec_id, int *out_btf_id)
 {
-	int i, j, n = btf__get_nr_types(obj->btf), m, btf_id = 0;
+	int i, j, n, m, btf_id = 0;
 	const struct btf_type *t;
 	const struct btf_var_secinfo *vi;
 	const char *name;
 
+	if (!obj->btf) {
+		pr_warn("failed to find BTF info for object '%s'\n", obj->filename);
+		return -EINVAL;
+	}
+
+	n = btf__get_nr_types(obj->btf);
 	for (i = 1; i <= n; i++) {
 		t = btf__type_by_id(obj->btf, i);
 
diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index d8886720e83d..8441e3e1aaac 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -43,7 +43,7 @@ void perf_evsel__delete(struct perf_evsel *evsel)
 	free(evsel);
 }
 
-#define FD(e, x, y) (*(int *) xyarray__entry(e->fd, x, y))
+#define FD(e, x, y) ((int *) xyarray__entry(e->fd, x, y))
 #define MMAP(e, x, y) (e->mmap ? ((struct perf_mmap *) xyarray__entry(e->mmap, x, y)) : NULL)
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
@@ -54,7 +54,10 @@ int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 		int cpu, thread;
 		for (cpu = 0; cpu < ncpus; cpu++) {
 			for (thread = 0; thread < nthreads; thread++) {
-				FD(evsel, cpu, thread) = -1;
+				int *fd = FD(evsel, cpu, thread);
+
+				if (fd)
+					*fd = -1;
 			}
 		}
 	}
@@ -80,7 +83,7 @@ sys_perf_event_open(struct perf_event_attr *attr,
 static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *group_fd)
 {
 	struct perf_evsel *leader = evsel->leader;
-	int fd;
+	int *fd;
 
 	if (evsel == leader) {
 		*group_fd = -1;
@@ -95,10 +98,10 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *grou
 		return -ENOTCONN;
 
 	fd = FD(leader, cpu, thread);
-	if (fd == -1)
+	if (fd == NULL || *fd == -1)
 		return -EBADF;
 
-	*group_fd = fd;
+	*group_fd = *fd;
 
 	return 0;
 }
@@ -138,7 +141,11 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 		for (thread = 0; thread < threads->nr; thread++) {
-			int fd, group_fd;
+			int fd, group_fd, *evsel_fd;
+
+			evsel_fd = FD(evsel, cpu, thread);
+			if (evsel_fd == NULL)
+				return -EINVAL;
 
 			err = get_group_fd(evsel, cpu, thread, &group_fd);
 			if (err < 0)
@@ -151,7 +158,7 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 			if (fd < 0)
 				return -errno;
 
-			FD(evsel, cpu, thread) = fd;
+			*evsel_fd = fd;
 		}
 	}
 
@@ -163,9 +170,12 @@ static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu)
 	int thread;
 
 	for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) {
-		if (FD(evsel, cpu, thread) >= 0)
-			close(FD(evsel, cpu, thread));
-		FD(evsel, cpu, thread) = -1;
+		int *fd = FD(evsel, cpu, thread);
+
+		if (fd && *fd >= 0) {
+			close(*fd);
+			*fd = -1;
+		}
 	}
 }
 
@@ -209,13 +219,12 @@ void perf_evsel__munmap(struct perf_evsel *evsel)
 
 	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
 		for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
-			int fd = FD(evsel, cpu, thread);
-			struct perf_mmap *map = MMAP(evsel, cpu, thread);
+			int *fd = FD(evsel, cpu, thread);
 
-			if (fd < 0)
+			if (fd == NULL || *fd < 0)
 				continue;
 
-			perf_mmap__munmap(map);
+			perf_mmap__munmap(MMAP(evsel, cpu, thread));
 		}
 	}
 
@@ -239,15 +248,16 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
 
 	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
 		for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
-			int fd = FD(evsel, cpu, thread);
-			struct perf_mmap *map = MMAP(evsel, cpu, thread);
+			int *fd = FD(evsel, cpu, thread);
+			struct perf_mmap *map;
 
-			if (fd < 0)
+			if (fd == NULL || *fd < 0)
 				continue;
 
+			map = MMAP(evsel, cpu, thread);
 			perf_mmap__init(map, NULL, false, NULL);
 
-			ret = perf_mmap__mmap(map, &mp, fd, cpu);
+			ret = perf_mmap__mmap(map, &mp, *fd, cpu);
 			if (ret) {
 				perf_evsel__munmap(evsel);
 				return ret;
@@ -260,7 +270,9 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
 
 void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread)
 {
-	if (FD(evsel, cpu, thread) < 0 || MMAP(evsel, cpu, thread) == NULL)
+	int *fd = FD(evsel, cpu, thread);
+
+	if (fd == NULL || *fd < 0 || MMAP(evsel, cpu, thread) == NULL)
 		return NULL;
 
 	return MMAP(evsel, cpu, thread)->base;
@@ -295,17 +307,18 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
 		     struct perf_counts_values *count)
 {
 	size_t size = perf_evsel__read_size(evsel);
+	int *fd = FD(evsel, cpu, thread);
 
 	memset(count, 0, sizeof(*count));
 
-	if (FD(evsel, cpu, thread) < 0)
+	if (fd == NULL || *fd < 0)
 		return -EINVAL;
 
 	if (MMAP(evsel, cpu, thread) &&
 	    !perf_mmap__read_self(MMAP(evsel, cpu, thread), count))
 		return 0;
 
-	if (readn(FD(evsel, cpu, thread), count->values, size) <= 0)
+	if (readn(*fd, count->values, size) <= 0)
 		return -errno;
 
 	return 0;
@@ -318,8 +331,13 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
 	int thread;
 
 	for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
-		int fd = FD(evsel, cpu, thread),
-		    err = ioctl(fd, ioc, arg);
+		int err;
+		int *fd = FD(evsel, cpu, thread);
+
+		if (fd == NULL || *fd < 0)
+			return -1;
+
+		err = ioctl(*fd, ioc, arg);
 
 		if (err)
 			return err;
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 3172983bf808..1f2ae708b223 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -736,7 +736,7 @@ static int elf_add_alternative(struct elf *elf,
 	sec = find_section_by_name(elf, ".altinstructions");
 	if (!sec) {
 		sec = elf_create_section(elf, ".altinstructions",
-					 SHF_ALLOC, size, 0);
+					 SHF_ALLOC, 0, 0);
 
 		if (!sec) {
 			WARN_ELF("elf_create_section");
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 84e59a97bab6..7c865a10372a 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -369,7 +369,7 @@ static int decode_instructions(struct objtool_file *file)
 		    !strcmp(sec->name, ".entry.text"))
 			sec->noinstr = true;
 
-		for (offset = 0; offset < sec->len; offset += insn->len) {
+		for (offset = 0; offset < sec->sh.sh_size; offset += insn->len) {
 			insn = malloc(sizeof(*insn));
 			if (!insn) {
 				WARN("malloc failed");
@@ -383,7 +383,7 @@ static int decode_instructions(struct objtool_file *file)
 			insn->offset = offset;
 
 			ret = arch_decode_instruction(file, sec, offset,
-						      sec->len - offset,
+						      sec->sh.sh_size - offset,
 						      &insn->len, &insn->type,
 						      &insn->immediate,
 						      &insn->stack_ops);
@@ -501,9 +501,9 @@ static struct instruction *find_last_insn(struct objtool_file *file,
 {
 	struct instruction *insn = NULL;
 	unsigned int offset;
-	unsigned int end = (sec->len > 10) ? sec->len - 10 : 0;
+	unsigned int end = (sec->sh.sh_size > 10) ? sec->sh.sh_size - 10 : 0;
 
-	for (offset = sec->len - 1; offset >= end && !insn; offset--)
+	for (offset = sec->sh.sh_size - 1; offset >= end && !insn; offset--)
 		insn = find_insn(file, sec, offset);
 
 	return insn;
@@ -541,7 +541,7 @@ static int add_dead_ends(struct objtool_file *file)
 		insn = find_insn(file, reloc->sym->sec, reloc->addend);
 		if (insn)
 			insn = list_prev_entry(insn, list);
-		else if (reloc->addend == reloc->sym->sec->len) {
+		else if (reloc->addend == reloc->sym->sec->sh.sh_size) {
 			insn = find_last_insn(file, reloc->sym->sec);
 			if (!insn) {
 				WARN("can't find unreachable insn at %s+0x%x",
@@ -576,7 +576,7 @@ reachable:
 		insn = find_insn(file, reloc->sym->sec, reloc->addend);
 		if (insn)
 			insn = list_prev_entry(insn, list);
-		else if (reloc->addend == reloc->sym->sec->len) {
+		else if (reloc->addend == reloc->sym->sec->sh.sh_size) {
 			insn = find_last_insn(file, reloc->sym->sec);
 			if (!insn) {
 				WARN("can't find reachable insn at %s+0x%x",
@@ -1726,14 +1726,14 @@ static int read_unwind_hints(struct objtool_file *file)
 		return -1;
 	}
 
-	if (sec->len % sizeof(struct unwind_hint)) {
+	if (sec->sh.sh_size % sizeof(struct unwind_hint)) {
 		WARN("struct unwind_hint size mismatch");
 		return -1;
 	}
 
 	file->hints = true;
 
-	for (i = 0; i < sec->len / sizeof(struct unwind_hint); i++) {
+	for (i = 0; i < sec->sh.sh_size / sizeof(struct unwind_hint); i++) {
 		hint = (struct unwind_hint *)sec->data->d_buf + i;
 
 		reloc = find_reloc_by_dest(file->elf, sec, i * sizeof(*hint));
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 8676c7598728..b18f0055b50b 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -286,10 +286,9 @@ static int read_sections(struct elf *elf)
 				return -1;
 			}
 		}
-		sec->len = sec->sh.sh_size;
 
 		if (sec->sh.sh_flags & SHF_EXECINSTR)
-			elf->text_size += sec->len;
+			elf->text_size += sec->sh.sh_size;
 
 		list_add_tail(&sec->list, &elf->sections);
 		elf_hash_add(section, &sec->hash, sec->idx);
@@ -734,8 +733,8 @@ static int elf_add_string(struct elf *elf, struct section *strtab, char *str)
 	data->d_size = strlen(str) + 1;
 	data->d_align = 1;
 
-	len = strtab->len;
-	strtab->len += data->d_size;
+	len = strtab->sh.sh_size;
+	strtab->sh.sh_size += data->d_size;
 	strtab->changed = true;
 
 	return len;
@@ -790,9 +789,9 @@ struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name)
 	data->d_align = 1;
 	data->d_type = ELF_T_SYM;
 
-	sym->idx = symtab->len / sizeof(sym->sym);
+	sym->idx = symtab->sh.sh_size / sizeof(sym->sym);
 
-	symtab->len += data->d_size;
+	symtab->sh.sh_size += data->d_size;
 	symtab->changed = true;
 
 	symtab_shndx = find_section_by_name(elf, ".symtab_shndx");
@@ -814,7 +813,7 @@ struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name)
 		data->d_align = 4;
 		data->d_type = ELF_T_WORD;
 
-		symtab_shndx->len += 4;
+		symtab_shndx->sh.sh_size += 4;
 		symtab_shndx->changed = true;
 	}
 
@@ -855,7 +854,6 @@ struct section *elf_create_section(struct elf *elf, const char *name,
 	}
 
 	sec->idx = elf_ndxscn(s);
-	sec->len = size;
 	sec->changed = true;
 
 	sec->data = elf_newdata(s);
diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h
index c3857fadee7a..c48c1067797d 100644
--- a/tools/objtool/include/objtool/elf.h
+++ b/tools/objtool/include/objtool/elf.h
@@ -38,7 +38,6 @@ struct section {
 	Elf_Data *data;
 	char *name;
 	int idx;
-	unsigned int len;
 	bool changed, text, rodata, noinstr;
 };
 
diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index ddacb4215748..dd3c64af9db2 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -211,7 +211,7 @@ int orc_create(struct objtool_file *file)
 
 		/* Add a section terminator */
 		if (!empty) {
-			orc_list_add(&orc_list, &null, sec, sec->len);
+			orc_list_add(&orc_list, &null, sec, sec->sh.sh_size);
 			nr++;
 		}
 	}
diff --git a/tools/objtool/special.c b/tools/objtool/special.c
index bc925cf19e2d..06c3eacab3d5 100644
--- a/tools/objtool/special.c
+++ b/tools/objtool/special.c
@@ -58,6 +58,13 @@ void __weak arch_handle_alternative(unsigned short feature, struct special_alt *
 {
 }
 
+static void reloc_to_sec_off(struct reloc *reloc, struct section **sec,
+			     unsigned long *off)
+{
+	*sec = reloc->sym->sec;
+	*off = reloc->sym->offset + reloc->addend;
+}
+
 static int get_alt_entry(struct elf *elf, struct special_entry *entry,
 			 struct section *sec, int idx,
 			 struct special_alt *alt)
@@ -91,14 +98,8 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry,
 		WARN_FUNC("can't find orig reloc", sec, offset + entry->orig);
 		return -1;
 	}
-	if (orig_reloc->sym->type != STT_SECTION) {
-		WARN_FUNC("don't know how to handle non-section reloc symbol %s",
-			   sec, offset + entry->orig, orig_reloc->sym->name);
-		return -1;
-	}
 
-	alt->orig_sec = orig_reloc->sym->sec;
-	alt->orig_off = orig_reloc->addend;
+	reloc_to_sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off);
 
 	if (!entry->group || alt->new_len) {
 		new_reloc = find_reloc_by_dest(elf, sec, offset + entry->new);
@@ -116,8 +117,7 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry,
 		if (arch_is_retpoline(new_reloc->sym))
 			return 1;
 
-		alt->new_sec = new_reloc->sym->sec;
-		alt->new_off = (unsigned int)new_reloc->addend;
+		reloc_to_sec_off(new_reloc, &alt->new_sec, &alt->new_off);
 
 		/* _ASM_EXTABLE_EX hack */
 		if (alt->new_off >= 0x7ffffff0)
@@ -159,13 +159,13 @@ int special_get_alts(struct elf *elf, struct list_head *alts)
 		if (!sec)
 			continue;
 
-		if (sec->len % entry->size != 0) {
+		if (sec->sh.sh_size % entry->size != 0) {
 			WARN("%s size not a multiple of %d",
 			     sec->name, entry->size);
 			return -1;
 		}
 
-		nr_entries = sec->len / entry->size;
+		nr_entries = sec->sh.sh_size / entry->size;
 
 		for (idx = 0; idx < nr_entries; idx++) {
 			alt = malloc(sizeof(*alt));
diff --git a/tools/perf/Documentation/jitdump-specification.txt b/tools/perf/Documentation/jitdump-specification.txt
index 52152d156ad9..79936355d819 100644
--- a/tools/perf/Documentation/jitdump-specification.txt
+++ b/tools/perf/Documentation/jitdump-specification.txt
@@ -164,7 +164,7 @@ const char unwinding_data[n]: an array of unwinding data, consisting of the EH F
 The EH Frame header follows the Linux Standard Base (LSB) specification as described in the document at https://refspecs.linuxfoundation.org/LSB_1.3.0/gLSB/gLSB/ehframehdr.html
 
 
-The EH Frame follows the LSB specicfication as described in the document at https://refspecs.linuxbase.org/LSB_3.0.0/LSB-PDA/LSB-PDA/ehframechpt.html
+The EH Frame follows the LSB specification as described in the document at https://refspecs.linuxbase.org/LSB_3.0.0/LSB-PDA/LSB-PDA/ehframechpt.html
 
 
 NOTE: The mapped_size is generally either the same as unwind_data_size (if the unwinding data was mapped in memory by the running process) or zero (if the unwinding data is not mapped by the process). If the unwinding data was not mapped, then only the EH Frame Header will be read, which can be used to specify FP based unwinding for a function which does not have unwinding information.
diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt
index de6beedb7283..3b6a2c84ea02 100644
--- a/tools/perf/Documentation/perf-c2c.txt
+++ b/tools/perf/Documentation/perf-c2c.txt
@@ -261,7 +261,7 @@ COALESCE
 User can specify how to sort offsets for cacheline.
 
 Following fields are available and governs the final
-output fields set for caheline offsets output:
+output fields set for cacheline offsets output:
 
   tid   - coalesced by process TIDs
   pid   - coalesced by process PIDs
diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt
index 184ba62420f0..db465fa7ee91 100644
--- a/tools/perf/Documentation/perf-intel-pt.txt
+++ b/tools/perf/Documentation/perf-intel-pt.txt
@@ -883,7 +883,7 @@ and "r" can be combined to get calls and returns.
 
 "Transactions" events correspond to the start or end of transactions. The
 'flags' field can be used in perf script to determine whether the event is a
-tranasaction start, commit or abort.
+transaction start, commit or abort.
 
 Note that "instructions", "branches" and "transactions" events depend on code
 flow packets which can be disabled by using the config term "branch=0".  Refer
diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
index 74d774592196..1b4d452923d7 100644
--- a/tools/perf/Documentation/perf-lock.txt
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -44,7 +44,7 @@ COMMON OPTIONS
 
 -f::
 --force::
-	Don't complan, do it.
+	Don't complain, do it.
 
 REPORT OPTIONS
 --------------
diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt
index 5a1f68122f50..fa4f39d305a7 100644
--- a/tools/perf/Documentation/perf-script-perl.txt
+++ b/tools/perf/Documentation/perf-script-perl.txt
@@ -54,7 +54,7 @@ all sched_wakeup events in the system:
 Traces meant to be processed using a script should be recorded with
 the above option: -a to enable system-wide collection.
 
-The format file for the sched_wakep event defines the following fields
+The format file for the sched_wakeup event defines the following fields
 (see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format):
 
 ----
diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt
index 0250dc61cf98..cf4b7f4b625a 100644
--- a/tools/perf/Documentation/perf-script-python.txt
+++ b/tools/perf/Documentation/perf-script-python.txt
@@ -448,7 +448,7 @@ all sched_wakeup events in the system:
 Traces meant to be processed using a script should be recorded with
 the above option: -a to enable system-wide collection.
 
-The format file for the sched_wakep event defines the following fields
+The format file for the sched_wakeup event defines the following fields
 (see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format):
 
 ----
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 4c9310be6acc..7e6fb7cbc0f4 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -385,7 +385,7 @@ Aggregate counts per physical processor for system-wide mode measurements.
 Print metrics or metricgroups specified in a comma separated list.
 For a group all metrics from the group are added.
 The events from the metrics are automatically measured.
-See perf list output for the possble metrics and metricgroups.
+See perf list output for the possible metrics and metricgroups.
 
 -A::
 --no-aggr::
diff --git a/tools/perf/Documentation/topdown.txt b/tools/perf/Documentation/topdown.txt
index c6302df4cf29..a15b93fdcf50 100644
--- a/tools/perf/Documentation/topdown.txt
+++ b/tools/perf/Documentation/topdown.txt
@@ -2,7 +2,7 @@ Using TopDown metrics in user space
 -----------------------------------
 
 Intel CPUs (since Sandy Bridge and Silvermont) support a TopDown
-methology to break down CPU pipeline execution into 4 bottlenecks:
+methodology to break down CPU pipeline execution into 4 bottlenecks:
 frontend bound, backend bound, bad speculation, retiring.
 
 For more details on Topdown see [1][5]
diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c
index c7c7ec0812d5..5fc6a2a3dbc5 100644
--- a/tools/perf/arch/arm/util/auxtrace.c
+++ b/tools/perf/arch/arm/util/auxtrace.c
@@ -8,10 +8,10 @@
 #include <linux/coresight-pmu.h>
 #include <linux/zalloc.h>
 
-#include "../../util/auxtrace.h"
-#include "../../util/debug.h"
-#include "../../util/evlist.h"
-#include "../../util/pmu.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/debug.h"
+#include "../../../util/evlist.h"
+#include "../../../util/pmu.h"
 #include "cs-etm.h"
 #include "arm-spe.h"
 
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 515aae470e23..293a23bf8be3 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -16,19 +16,19 @@
 #include <linux/zalloc.h>
 
 #include "cs-etm.h"
-#include "../../util/debug.h"
-#include "../../util/record.h"
-#include "../../util/auxtrace.h"
-#include "../../util/cpumap.h"
-#include "../../util/event.h"
-#include "../../util/evlist.h"
-#include "../../util/evsel.h"
-#include "../../util/perf_api_probe.h"
-#include "../../util/evsel_config.h"
-#include "../../util/pmu.h"
-#include "../../util/cs-etm.h"
+#include "../../../util/debug.h"
+#include "../../../util/record.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/cpumap.h"
+#include "../../../util/event.h"
+#include "../../../util/evlist.h"
+#include "../../../util/evsel.h"
+#include "../../../util/perf_api_probe.h"
+#include "../../../util/evsel_config.h"
+#include "../../../util/pmu.h"
+#include "../../../util/cs-etm.h"
 #include <internal/lib.h> // page_size
-#include "../../util/session.h"
+#include "../../../util/session.h"
 
 #include <errno.h>
 #include <stdlib.h>
diff --git a/tools/perf/arch/arm/util/perf_regs.c b/tools/perf/arch/arm/util/perf_regs.c
index 2864e2e3776d..2833e101a7c6 100644
--- a/tools/perf/arch/arm/util/perf_regs.c
+++ b/tools/perf/arch/arm/util/perf_regs.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "../../util/perf_regs.h"
+#include "../../../util/perf_regs.h"
 
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG_END
diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c
index bbc297a7e2e3..b8b23b9dc598 100644
--- a/tools/perf/arch/arm/util/pmu.c
+++ b/tools/perf/arch/arm/util/pmu.c
@@ -10,7 +10,7 @@
 #include <linux/string.h>
 
 #include "arm-spe.h"
-#include "../../util/pmu.h"
+#include "../../../util/pmu.h"
 
 struct perf_event_attr
 *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
diff --git a/tools/perf/arch/arm/util/unwind-libdw.c b/tools/perf/arch/arm/util/unwind-libdw.c
index 36ba4c69c3c5..b7692cb0c733 100644
--- a/tools/perf/arch/arm/util/unwind-libdw.c
+++ b/tools/perf/arch/arm/util/unwind-libdw.c
@@ -1,8 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <elfutils/libdwfl.h>
-#include "../../util/unwind-libdw.h"
-#include "../../util/perf_regs.h"
-#include "../../util/event.h"
+#include "../../../util/unwind-libdw.h"
+#include "../../../util/perf_regs.h"
+#include "../../../util/event.h"
 
 bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
 {
diff --git a/tools/perf/arch/arm/util/unwind-libunwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c
index 3a550225dfaf..438906bf0014 100644
--- a/tools/perf/arch/arm/util/unwind-libunwind.c
+++ b/tools/perf/arch/arm/util/unwind-libunwind.c
@@ -3,8 +3,8 @@
 #include <errno.h>
 #include <libunwind.h>
 #include "perf_regs.h"
-#include "../../util/unwind.h"
-#include "../../util/debug.h"
+#include "../../../util/unwind.h"
+#include "../../../util/debug.h"
 
 int libunwind__arch_reg_id(int regnum)
 {
diff --git a/tools/perf/arch/x86/util/iostat.c b/tools/perf/arch/x86/util/iostat.c
index eeafe97b8105..792cd75ade33 100644
--- a/tools/perf/arch/x86/util/iostat.c
+++ b/tools/perf/arch/x86/util/iostat.c
@@ -432,7 +432,7 @@ void iostat_print_metric(struct perf_stat_config *config, struct evsel *evsel,
 	u8 die = ((struct iio_root_port *)evsel->priv)->die;
 	struct perf_counts_values *count = perf_counts(evsel->counts, die, 0);
 
-	if (count->run && count->ena) {
+	if (count && count->run && count->ena) {
 		if (evsel->prev_raw_counts && !out->force_header) {
 			struct perf_counts_values *prev_count =
 				perf_counts(evsel->prev_raw_counts, die, 0);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 0e824f7d8b19..6211d0b84b7a 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -368,16 +368,6 @@ static inline int output_type(unsigned int type)
 	return OUTPUT_TYPE_OTHER;
 }
 
-static inline unsigned int attr_type(unsigned int type)
-{
-	switch (type) {
-	case OUTPUT_TYPE_SYNTH:
-		return PERF_TYPE_SYNTH;
-	default:
-		return type;
-	}
-}
-
 static bool output_set_by_user(void)
 {
 	int j;
@@ -556,6 +546,18 @@ static void set_print_ip_opts(struct perf_event_attr *attr)
 		output[type].print_ip_opts |= EVSEL__PRINT_SRCLINE;
 }
 
+static struct evsel *find_first_output_type(struct evlist *evlist,
+					    unsigned int type)
+{
+	struct evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (output_type(evsel->core.attr.type) == (int)type)
+			return evsel;
+	}
+	return NULL;
+}
+
 /*
  * verify all user requested events exist and the samples
  * have the expected data
@@ -567,7 +569,7 @@ static int perf_session__check_output_opt(struct perf_session *session)
 	struct evsel *evsel;
 
 	for (j = 0; j < OUTPUT_TYPE_MAX; ++j) {
-		evsel = perf_session__find_first_evtype(session, attr_type(j));
+		evsel = find_first_output_type(session->evlist, j);
 
 		/*
 		 * even if fields is set to 0 (ie., show nothing) event must
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f6e87b7be5fa..f0ecfda34ece 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2408,6 +2408,8 @@ int cmd_stat(int argc, const char **argv)
 			goto out;
 		} else if (verbose)
 			iostat_list(evsel_list, &stat_config);
+		if (iostat_mode == IOSTAT_RUN && !target__has_cpu(&target))
+			target.system_wide = true;
 	}
 
 	if (add_default_attributes())
diff --git a/tools/perf/pmu-events/arch/powerpc/power8/other.json b/tools/perf/pmu-events/arch/powerpc/power8/other.json
index 84a0cedf1fd9..f1f2965f6775 100644
--- a/tools/perf/pmu-events/arch/powerpc/power8/other.json
+++ b/tools/perf/pmu-events/arch/powerpc/power8/other.json
@@ -1046,7 +1046,7 @@
   {
     "EventCode": "0x4e010",
     "EventName": "PM_GCT_NOSLOT_IC_L3MISS",
-    "BriefDescription": "Gct empty for this thread due to icach l3 miss",
+    "BriefDescription": "Gct empty for this thread due to icache l3 miss",
     "PublicDescription": ""
   },
   {
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 9866cddebf23..9b4a765e4b73 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -229,8 +229,8 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 			    struct thread *thread, struct state *state)
 {
 	struct addr_location al;
-	unsigned char buf1[BUFSZ];
-	unsigned char buf2[BUFSZ];
+	unsigned char buf1[BUFSZ] = {0};
+	unsigned char buf2[BUFSZ] = {0};
 	size_t ret_len;
 	u64 objdump_addr;
 	const char *objdump_name;
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index a288035eb362..c756284b3b13 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -20,6 +20,23 @@
 /* For bsearch. We try to unwind functions in shared object. */
 #include <stdlib.h>
 
+/*
+ * The test will assert frames are on the stack but tail call optimizations lose
+ * the frame of the caller. Clang can disable this optimization on a called
+ * function but GCC currently (11/2020) lacks this attribute. The barrier is
+ * used to inhibit tail calls in these cases.
+ */
+#ifdef __has_attribute
+#if __has_attribute(disable_tail_calls)
+#define NO_TAIL_CALL_ATTRIBUTE __attribute__((disable_tail_calls))
+#define NO_TAIL_CALL_BARRIER
+#endif
+#endif
+#ifndef NO_TAIL_CALL_ATTRIBUTE
+#define NO_TAIL_CALL_ATTRIBUTE
+#define NO_TAIL_CALL_BARRIER __asm__ __volatile__("" : : : "memory");
+#endif
+
 static int mmap_handler(struct perf_tool *tool __maybe_unused,
 			union perf_event *event,
 			struct perf_sample *sample,
@@ -91,7 +108,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	return strcmp((const char *) symbol, funcs[idx]);
 }
 
-noinline int test_dwarf_unwind__thread(struct thread *thread)
+NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thread)
 {
 	struct perf_sample sample;
 	unsigned long cnt = 0;
@@ -122,7 +139,7 @@ noinline int test_dwarf_unwind__thread(struct thread *thread)
 
 static int global_unwind_retval = -INT_MAX;
 
-noinline int test_dwarf_unwind__compare(void *p1, void *p2)
+NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__compare(void *p1, void *p2)
 {
 	/* Any possible value should be 'thread' */
 	struct thread *thread = *(struct thread **)p1;
@@ -141,7 +158,7 @@ noinline int test_dwarf_unwind__compare(void *p1, void *p2)
 	return p1 - p2;
 }
 
-noinline int test_dwarf_unwind__krava_3(struct thread *thread)
+NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_3(struct thread *thread)
 {
 	struct thread *array[2] = {thread, thread};
 	void *fp = &bsearch;
@@ -160,14 +177,22 @@ noinline int test_dwarf_unwind__krava_3(struct thread *thread)
 	return global_unwind_retval;
 }
 
-noinline int test_dwarf_unwind__krava_2(struct thread *thread)
+NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_2(struct thread *thread)
 {
-	return test_dwarf_unwind__krava_3(thread);
+	int ret;
+
+	ret =  test_dwarf_unwind__krava_3(thread);
+	NO_TAIL_CALL_BARRIER;
+	return ret;
 }
 
-noinline int test_dwarf_unwind__krava_1(struct thread *thread)
+NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_1(struct thread *thread)
 {
-	return test_dwarf_unwind__krava_2(thread);
+	int ret;
+
+	ret =  test_dwarf_unwind__krava_2(thread);
+	NO_TAIL_CALL_BARRIER;
+	return ret;
 }
 
 int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unused)
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 781afe42e90e..fa5bd5c20e96 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -757,25 +757,40 @@ void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column,
 }
 
 void ui_browser__mark_fused(struct ui_browser *browser, unsigned int column,
-			    unsigned int row, bool arrow_down)
+			    unsigned int row, int diff, bool arrow_down)
 {
-	unsigned int end_row;
+	int end_row;
 
-	if (row >= browser->top_idx)
-		end_row = row - browser->top_idx;
-	else
+	if (diff <= 0)
 		return;
 
 	SLsmg_set_char_set(1);
 
 	if (arrow_down) {
+		if (row + diff <= browser->top_idx)
+			return;
+
+		end_row = row + diff - browser->top_idx;
 		ui_browser__gotorc(browser, end_row, column - 1);
-		SLsmg_write_char(SLSMG_ULCORN_CHAR);
-		ui_browser__gotorc(browser, end_row, column);
-		SLsmg_draw_hline(2);
-		ui_browser__gotorc(browser, end_row + 1, column - 1);
 		SLsmg_write_char(SLSMG_LTEE_CHAR);
+
+		while (--end_row >= 0 && end_row > (int)(row - browser->top_idx)) {
+			ui_browser__gotorc(browser, end_row, column - 1);
+			SLsmg_draw_vline(1);
+		}
+
+		end_row = (int)(row - browser->top_idx);
+		if (end_row >= 0) {
+			ui_browser__gotorc(browser, end_row, column - 1);
+			SLsmg_write_char(SLSMG_ULCORN_CHAR);
+			ui_browser__gotorc(browser, end_row, column);
+			SLsmg_draw_hline(2);
+		}
 	} else {
+		if (row < browser->top_idx)
+			return;
+
+		end_row = row - browser->top_idx;
 		ui_browser__gotorc(browser, end_row, column - 1);
 		SLsmg_write_char(SLSMG_LTEE_CHAR);
 		ui_browser__gotorc(browser, end_row, column);
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index 3678eb88f119..510ce4554050 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -51,7 +51,7 @@ void ui_browser__write_graph(struct ui_browser *browser, int graph);
 void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column,
 			      u64 start, u64 end);
 void ui_browser__mark_fused(struct ui_browser *browser, unsigned int column,
-			    unsigned int row, bool arrow_down);
+			    unsigned int row, int diff, bool arrow_down);
 void __ui_browser__show_title(struct ui_browser *browser, const char *title);
 void ui_browser__show_title(struct ui_browser *browser, const char *title);
 int ui_browser__show(struct ui_browser *browser, const char *title,
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index ef4da4295bf7..e81c2493efdf 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -125,13 +125,20 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 		ab->selection = al;
 }
 
-static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor)
+static int is_fused(struct annotate_browser *ab, struct disasm_line *cursor)
 {
 	struct disasm_line *pos = list_prev_entry(cursor, al.node);
 	const char *name;
+	int diff = 1;
+
+	while (pos && pos->al.offset == -1) {
+		pos = list_prev_entry(pos, al.node);
+		if (!ab->opts->hide_src_code)
+			diff++;
+	}
 
 	if (!pos)
-		return false;
+		return 0;
 
 	if (ins__is_lock(&pos->ins))
 		name = pos->ops.locked.ins.name;
@@ -139,9 +146,11 @@ static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor)
 		name = pos->ins.name;
 
 	if (!name || !cursor->ins.name)
-		return false;
+		return 0;
 
-	return ins__is_fused(ab->arch, name, cursor->ins.name);
+	if (ins__is_fused(ab->arch, name, cursor->ins.name))
+		return diff;
+	return 0;
 }
 
 static void annotate_browser__draw_current_jump(struct ui_browser *browser)
@@ -155,6 +164,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 	struct annotation *notes = symbol__annotation(sym);
 	u8 pcnt_width = annotation__pcnt_width(notes);
 	int width;
+	int diff = 0;
 
 	/* PLT symbols contain external offsets */
 	if (strstr(sym->name, "@plt"))
@@ -205,11 +215,11 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 				 pcnt_width + 2 + notes->widths.addr + width,
 				 from, to);
 
-	if (is_fused(ab, cursor)) {
+	diff = is_fused(ab, cursor);
+	if (diff > 0) {
 		ui_browser__mark_fused(browser,
 				       pcnt_width + 3 + notes->widths.addr + width,
-				       from - 1,
-				       to > from);
+				       from - diff, diff, to > from);
 	}
 }
 
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 683f6d63560e..1a7112a87736 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -24,7 +24,10 @@
 struct btf * __weak btf__load_from_kernel_by_id(__u32 id)
 {
        struct btf *btf;
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
        int err = btf__get_from_id(id, &btf);
+#pragma GCC diagnostic pop
 
        return err ? ERR_PTR(err) : btf;
 }
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 4fb5e90d7a57..60ce5908c664 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -801,7 +801,7 @@ int perf_config_set(struct perf_config_set *set,
 				  section->name, item->name);
 			ret = fn(key, value, data);
 			if (ret < 0) {
-				pr_err("Error: wrong config key-value pair %s=%s\n",
+				pr_err("Error in the given config file: wrong config key-value pair %s=%s\n",
 				       key, value);
 				/*
 				 * Can't be just a 'break', as perf_config_set__for_each_entry()
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index da19be7da284..44e40bad0e33 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2149,6 +2149,7 @@ static int add_callchain_ip(struct thread *thread,
 
 	al.filtered = 0;
 	al.sym = NULL;
+	al.srcline = NULL;
 	if (!cpumode) {
 		thread__find_cpumode_addr_location(thread, ip, &al);
 	} else {
diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c
index 6836510a522f..22722abc9dfa 100644
--- a/tools/testing/selftests/arm64/signal/test_signals_utils.c
+++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c
@@ -266,16 +266,19 @@ int test_init(struct tdescr *td)
 			td->feats_supported |= FEAT_SSBS;
 		if (getauxval(AT_HWCAP) & HWCAP_SVE)
 			td->feats_supported |= FEAT_SVE;
-		if (feats_ok(td))
+		if (feats_ok(td)) {
 			fprintf(stderr,
 				"Required Features: [%s] supported\n",
 				feats_to_string(td->feats_required &
 						td->feats_supported));
-		else
+		} else {
 			fprintf(stderr,
 				"Required Features: [%s] NOT supported\n",
 				feats_to_string(td->feats_required &
 						~td->feats_supported));
+			td->result = KSFT_SKIP;
+			return 0;
+		}
 	}
 
 	/* Perform test specific additional initialization */
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 866531c08e4f..799b88152e9e 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -375,7 +375,8 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
 		     $(TRUNNER_BPF_PROGS_DIR)/%.c			\
 		     $(TRUNNER_BPF_PROGS_DIR)/*.h			\
 		     $$(INCLUDE_DIR)/vmlinux.h				\
-		     $(wildcard $(BPFDIR)/bpf_*.h) | $(TRUNNER_OUTPUT)
+		     $(wildcard $(BPFDIR)/bpf_*.h)			\
+		     | $(TRUNNER_OUTPUT) $$(BPFOBJ)
 	$$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@,			\
 					  $(TRUNNER_BPF_CFLAGS))
 
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index 033051717ba5..f3daa44a8266 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -12,27 +12,36 @@
 #include <unistd.h>
 #include <ftw.h>
 
-
 #include "cgroup_helpers.h"
 
 /*
  * To avoid relying on the system setup, when setup_cgroup_env is called
- * we create a new mount namespace, and cgroup namespace. The cgroup2
- * root is mounted at CGROUP_MOUNT_PATH
- *
- * Unfortunately, most people don't have cgroupv2 enabled at this point in time.
- * It's easier to create our own mount namespace and manage it ourselves.
+ * we create a new mount namespace, and cgroup namespace. The cgroupv2
+ * root is mounted at CGROUP_MOUNT_PATH. Unfortunately, most people don't
+ * have cgroupv2 enabled at this point in time. It's easier to create our
+ * own mount namespace and manage it ourselves. We assume /mnt exists.
  *
- * We assume /mnt exists.
+ * Related cgroupv1 helpers are named *classid*(), since we only use the
+ * net_cls controller for tagging net_cls.classid. We assume the default
+ * mount under /sys/fs/cgroup/net_cls, which should be the case for the
+ * vast majority of users.
  */
 
 #define WALK_FD_LIMIT			16
+
 #define CGROUP_MOUNT_PATH		"/mnt"
+#define CGROUP_MOUNT_DFLT		"/sys/fs/cgroup"
+#define NETCLS_MOUNT_PATH		CGROUP_MOUNT_DFLT "/net_cls"
 #define CGROUP_WORK_DIR			"/cgroup-test-work-dir"
+
 #define format_cgroup_path(buf, path) \
 	snprintf(buf, sizeof(buf), "%s%s%s", CGROUP_MOUNT_PATH, \
 		 CGROUP_WORK_DIR, path)
 
+#define format_classid_path(buf)				\
+	snprintf(buf, sizeof(buf), "%s%s", NETCLS_MOUNT_PATH,	\
+		 CGROUP_WORK_DIR)
+
 /**
  * enable_all_controllers() - Enable all available cgroup v2 controllers
  *
@@ -139,8 +148,7 @@ static int nftwfunc(const char *filename, const struct stat *statptr,
 	return 0;
 }
 
-
-static int join_cgroup_from_top(char *cgroup_path)
+static int join_cgroup_from_top(const char *cgroup_path)
 {
 	char cgroup_procs_path[PATH_MAX + 1];
 	pid_t pid = getpid();
@@ -313,3 +321,114 @@ int cgroup_setup_and_join(const char *path) {
 	}
 	return cg_fd;
 }
+
+/**
+ * setup_classid_environment() - Setup the cgroupv1 net_cls environment
+ *
+ * After calling this function, cleanup_classid_environment should be called
+ * once testing is complete.
+ *
+ * This function will print an error to stderr and return 1 if it is unable
+ * to setup the cgroup environment. If setup is successful, 0 is returned.
+ */
+int setup_classid_environment(void)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_classid_path(cgroup_workdir);
+
+	if (mount("tmpfs", CGROUP_MOUNT_DFLT, "tmpfs", 0, NULL) &&
+	    errno != EBUSY) {
+		log_err("mount cgroup base");
+		return 1;
+	}
+
+	if (mkdir(NETCLS_MOUNT_PATH, 0777) && errno != EEXIST) {
+		log_err("mkdir cgroup net_cls");
+		return 1;
+	}
+
+	if (mount("net_cls", NETCLS_MOUNT_PATH, "cgroup", 0, "net_cls") &&
+	    errno != EBUSY) {
+		log_err("mount cgroup net_cls");
+		return 1;
+	}
+
+	cleanup_classid_environment();
+
+	if (mkdir(cgroup_workdir, 0777) && errno != EEXIST) {
+		log_err("mkdir cgroup work dir");
+		return 1;
+	}
+
+	return 0;
+}
+
+/**
+ * set_classid() - Set a cgroupv1 net_cls classid
+ * @id: the numeric classid
+ *
+ * Writes the passed classid into the cgroup work dir's net_cls.classid
+ * file in order to later on trigger socket tagging.
+ *
+ * On success, it returns 0, otherwise on failure it returns 1. If there
+ * is a failure, it prints the error to stderr.
+ */
+int set_classid(unsigned int id)
+{
+	char cgroup_workdir[PATH_MAX - 42];
+	char cgroup_classid_path[PATH_MAX + 1];
+	int fd, rc = 0;
+
+	format_classid_path(cgroup_workdir);
+	snprintf(cgroup_classid_path, sizeof(cgroup_classid_path),
+		 "%s/net_cls.classid", cgroup_workdir);
+
+	fd = open(cgroup_classid_path, O_WRONLY);
+	if (fd < 0) {
+		log_err("Opening cgroup classid: %s", cgroup_classid_path);
+		return 1;
+	}
+
+	if (dprintf(fd, "%u\n", id) < 0) {
+		log_err("Setting cgroup classid");
+		rc = 1;
+	}
+
+	close(fd);
+	return rc;
+}
+
+/**
+ * join_classid() - Join a cgroupv1 net_cls classid
+ *
+ * This function expects the cgroup work dir to be already created, as we
+ * join it here. This causes the process sockets to be tagged with the given
+ * net_cls classid.
+ *
+ * On success, it returns 0, otherwise on failure it returns 1.
+ */
+int join_classid(void)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_classid_path(cgroup_workdir);
+	return join_cgroup_from_top(cgroup_workdir);
+}
+
+/**
+ * cleanup_classid_environment() - Cleanup the cgroupv1 net_cls environment
+ *
+ * At call time, it moves the calling process to the root cgroup, and then
+ * runs the deletion process.
+ *
+ * On failure, it will print an error to stderr, and try to continue.
+ */
+void cleanup_classid_environment(void)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_classid_path(cgroup_workdir);
+	join_cgroup_from_top(NETCLS_MOUNT_PATH);
+	nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT);
+}
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h
index 5fe3d88e4f0d..629da3854b3e 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.h
+++ b/tools/testing/selftests/bpf/cgroup_helpers.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __CGROUP_HELPERS_H
 #define __CGROUP_HELPERS_H
+
 #include <errno.h>
 #include <string.h>
 
@@ -8,12 +9,21 @@
 #define log_err(MSG, ...) fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \
 	__FILE__, __LINE__, clean_errno(), ##__VA_ARGS__)
 
-
+/* cgroupv2 related */
 int cgroup_setup_and_join(const char *path);
 int create_and_get_cgroup(const char *path);
+unsigned long long get_cgroup_id(const char *path);
+
 int join_cgroup(const char *path);
+
 int setup_cgroup_environment(void);
 void cleanup_cgroup_environment(void);
-unsigned long long get_cgroup_id(const char *path);
 
-#endif
+/* cgroupv1 related */
+int set_classid(unsigned int id);
+int join_classid(void);
+
+int setup_classid_environment(void);
+void cleanup_classid_environment(void);
+
+#endif /* __CGROUP_HELPERS_H */
diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index 7e9f6375757a..6db1af8fdee7 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -208,11 +208,26 @@ error_close:
 
 static int connect_fd_to_addr(int fd,
 			      const struct sockaddr_storage *addr,
-			      socklen_t addrlen)
+			      socklen_t addrlen, const bool must_fail)
 {
-	if (connect(fd, (const struct sockaddr *)addr, addrlen)) {
-		log_err("Failed to connect to server");
-		return -1;
+	int ret;
+
+	errno = 0;
+	ret = connect(fd, (const struct sockaddr *)addr, addrlen);
+	if (must_fail) {
+		if (!ret) {
+			log_err("Unexpected success to connect to server");
+			return -1;
+		}
+		if (errno != EPERM) {
+			log_err("Unexpected error from connect to server");
+			return -1;
+		}
+	} else {
+		if (ret) {
+			log_err("Failed to connect to server");
+			return -1;
+		}
 	}
 
 	return 0;
@@ -257,7 +272,7 @@ int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts)
 		       strlen(opts->cc) + 1))
 		goto error_close;
 
-	if (connect_fd_to_addr(fd, &addr, addrlen))
+	if (connect_fd_to_addr(fd, &addr, addrlen, opts->must_fail))
 		goto error_close;
 
 	return fd;
@@ -289,7 +304,7 @@ int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms)
 		return -1;
 	}
 
-	if (connect_fd_to_addr(client_fd, &addr, len))
+	if (connect_fd_to_addr(client_fd, &addr, len, false))
 		return -1;
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index da7e132657d5..d198181a5648 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -20,6 +20,7 @@ typedef __u16 __sum16;
 struct network_helper_opts {
 	const char *cc;
 	int timeout_ms;
+	bool must_fail;
 };
 
 /* ipv4 test vector */
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
new file mode 100644
index 000000000000..ab3b9bc5e6d1
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+
+#include "connect4_dropper.skel.h"
+
+#include "cgroup_helpers.h"
+#include "network_helpers.h"
+
+static int run_test(int cgroup_fd, int server_fd, bool classid)
+{
+	struct network_helper_opts opts = {
+		.must_fail = true,
+	};
+	struct connect4_dropper *skel;
+	int fd, err = 0;
+
+	skel = connect4_dropper__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return -1;
+
+	skel->links.connect_v4_dropper =
+		bpf_program__attach_cgroup(skel->progs.connect_v4_dropper,
+					   cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.connect_v4_dropper, "prog_attach")) {
+		err = -1;
+		goto out;
+	}
+
+	if (classid && !ASSERT_OK(join_classid(), "join_classid")) {
+		err = -1;
+		goto out;
+	}
+
+	fd = connect_to_fd_opts(server_fd, &opts);
+	if (fd < 0)
+		err = -1;
+	else
+		close(fd);
+out:
+	connect4_dropper__destroy(skel);
+	return err;
+}
+
+void test_cgroup_v1v2(void)
+{
+	struct network_helper_opts opts = {};
+	int server_fd, client_fd, cgroup_fd;
+	static const int port = 60123;
+
+	/* Step 1: Check base connectivity works without any BPF. */
+	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0);
+	if (!ASSERT_GE(server_fd, 0, "server_fd"))
+		return;
+	client_fd = connect_to_fd_opts(server_fd, &opts);
+	if (!ASSERT_GE(client_fd, 0, "client_fd")) {
+		close(server_fd);
+		return;
+	}
+	close(client_fd);
+	close(server_fd);
+
+	/* Step 2: Check BPF policy prog attached to cgroups drops connectivity. */
+	cgroup_fd = test__join_cgroup("/connect_dropper");
+	if (!ASSERT_GE(cgroup_fd, 0, "cgroup_fd"))
+		return;
+	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0);
+	if (!ASSERT_GE(server_fd, 0, "server_fd")) {
+		close(cgroup_fd);
+		return;
+	}
+	ASSERT_OK(run_test(cgroup_fd, server_fd, false), "cgroup-v2-only");
+	setup_classid_environment();
+	set_classid(42);
+	ASSERT_OK(run_test(cgroup_fd, server_fd, true), "cgroup-v1v2");
+	cleanup_classid_environment();
+	close(server_fd);
+	close(cgroup_fd);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c b/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c
index 53f0e0fa1a53..37c20b5ffa70 100644
--- a/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c
+++ b/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE
 #include <test_progs.h>
-#include <linux/ptrace.h>
 #include "test_task_pt_regs.skel.h"
 
 void test_task_pt_regs(void)
diff --git a/tools/testing/selftests/bpf/progs/connect4_dropper.c b/tools/testing/selftests/bpf/progs/connect4_dropper.c
new file mode 100644
index 000000000000..b565d997810a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/connect4_dropper.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <string.h>
+
+#include <linux/stddef.h>
+#include <linux/bpf.h>
+
+#include <sys/socket.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define VERDICT_REJECT	0
+#define VERDICT_PROCEED	1
+
+SEC("cgroup/connect4")
+int connect_v4_dropper(struct bpf_sock_addr *ctx)
+{
+	if (ctx->type != SOCK_STREAM)
+		return VERDICT_PROCEED;
+	if (ctx->user_port == bpf_htons(60123))
+		return VERDICT_REJECT;
+	return VERDICT_PROCEED;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_task_pt_regs.c b/tools/testing/selftests/bpf/progs/test_task_pt_regs.c
index 6c059f1cfa1b..e6cb09259408 100644
--- a/tools/testing/selftests/bpf/progs/test_task_pt_regs.c
+++ b/tools/testing/selftests/bpf/progs/test_task_pt_regs.c
@@ -1,12 +1,17 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <linux/ptrace.h>
-#include <linux/bpf.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
-struct pt_regs current_regs = {};
-struct pt_regs ctx_regs = {};
+#define PT_REGS_SIZE sizeof(struct pt_regs)
+
+/*
+ * The kernel struct pt_regs isn't exported in its entirety to userspace.
+ * Pass it as an array to task_pt_regs.c
+ */
+char current_regs[PT_REGS_SIZE] = {};
+char ctx_regs[PT_REGS_SIZE] = {};
 int uprobe_res = 0;
 
 SEC("uprobe/trigger_func")
@@ -17,8 +22,10 @@ int handle_uprobe(struct pt_regs *ctx)
 
 	current = bpf_get_current_task_btf();
 	regs = (struct pt_regs *) bpf_task_pt_regs(current);
-	__builtin_memcpy(&current_regs, regs, sizeof(*regs));
-	__builtin_memcpy(&ctx_regs, ctx, sizeof(*ctx));
+	if (bpf_probe_read_kernel(current_regs, PT_REGS_SIZE, regs))
+		return 0;
+	if (bpf_probe_read_kernel(ctx_regs, PT_REGS_SIZE, ctx))
+		return 0;
 
 	/* Prove that uprobe was run */
 	uprobe_res = 1;
diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh
index 59ea56945e6c..b497bb85b667 100755
--- a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh
+++ b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh
@@ -112,6 +112,14 @@ setup()
 	ip netns add "${NS2}"
 	ip netns add "${NS3}"
 
+	# rp_filter gets confused by what these tests are doing, so disable it
+	ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0
+	ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0
+	ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0
+	ip netns exec ${NS1} sysctl -wq net.ipv4.conf.default.rp_filter=0
+	ip netns exec ${NS2} sysctl -wq net.ipv4.conf.default.rp_filter=0
+	ip netns exec ${NS3} sysctl -wq net.ipv4.conf.default.rp_filter=0
+
 	ip link add veth1 type veth peer name veth2
 	ip link add veth3 type veth peer name veth4
 	ip link add veth5 type veth peer name veth6
@@ -236,11 +244,6 @@ setup()
 	ip -netns ${NS1} -6 route add ${IPv6_GRE}/128 dev veth5 via ${IPv6_6} ${VRF}
 	ip -netns ${NS2} -6 route add ${IPv6_GRE}/128 dev veth7 via ${IPv6_8} ${VRF}
 
-	# rp_filter gets confused by what these tests are doing, so disable it
-	ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0
-	ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0
-	ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0
-
 	TMPFILE=$(mktemp /tmp/test_lwt_ip_encap.XXXXXX)
 
 	sleep 1  # reduce flakiness
diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
index beee0d5646a6..f7d84549cc3e 100755
--- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
+++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
@@ -1,6 +1,6 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
-# Copyright 2020 NXP Semiconductors
+# Copyright 2020 NXP
 
 WAIT_TIME=1
 NUM_NETIFS=4
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 98053d3afbda..b8dbabe24ac2 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -24,6 +24,7 @@
 /x86_64/smm_test
 /x86_64/state_test
 /x86_64/svm_vmcall_test
+/x86_64/svm_int_ctl_test
 /x86_64/sync_regs_test
 /x86_64/tsc_msrs_test
 /x86_64/userspace_msr_exit_test
@@ -48,6 +49,7 @@
 /kvm_page_table_test
 /memslot_modification_stress_test
 /memslot_perf_test
+/rseq_test
 /set_memory_region_test
 /steal_time
 /kvm_binary_stats_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 5d05801ab816..d1774f461393 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -56,6 +56,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/smm_test
 TEST_GEN_PROGS_x86_64 += x86_64/state_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test
 TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test
+TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test
 TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
 TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test
@@ -80,6 +81,7 @@ TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
 TEST_GEN_PROGS_x86_64 += kvm_page_table_test
 TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test
 TEST_GEN_PROGS_x86_64 += memslot_perf_test
+TEST_GEN_PROGS_x86_64 += rseq_test
 TEST_GEN_PROGS_x86_64 += set_memory_region_test
 TEST_GEN_PROGS_x86_64 += steal_time
 TEST_GEN_PROGS_x86_64 += kvm_binary_stats_test
@@ -93,6 +95,7 @@ TEST_GEN_PROGS_aarch64 += dirty_log_test
 TEST_GEN_PROGS_aarch64 += dirty_log_perf_test
 TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus
 TEST_GEN_PROGS_aarch64 += kvm_page_table_test
+TEST_GEN_PROGS_aarch64 += rseq_test
 TEST_GEN_PROGS_aarch64 += set_memory_region_test
 TEST_GEN_PROGS_aarch64 += steal_time
 TEST_GEN_PROGS_aarch64 += kvm_binary_stats_test
@@ -104,6 +107,7 @@ TEST_GEN_PROGS_s390x += demand_paging_test
 TEST_GEN_PROGS_s390x += dirty_log_test
 TEST_GEN_PROGS_s390x += kvm_create_max_vcpus
 TEST_GEN_PROGS_s390x += kvm_page_table_test
+TEST_GEN_PROGS_s390x += rseq_test
 TEST_GEN_PROGS_s390x += set_memory_region_test
 TEST_GEN_PROGS_s390x += kvm_binary_stats_test
 
diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
index 71e277c7c3f3..5d95113c7b7c 100644
--- a/tools/testing/selftests/kvm/access_tracking_perf_test.c
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -371,9 +371,7 @@ static void help(char *name)
 	printf(" -v: specify the number of vCPUs to run.\n");
 	printf(" -o: Overlap guest memory accesses instead of partitioning\n"
 	       "     them into a separate region of memory for each vCPU.\n");
-	printf(" -s: specify the type of memory that should be used to\n"
-	       "     back the guest data region.\n\n");
-	backing_src_help();
+	backing_src_help("-s");
 	puts("");
 	exit(0);
 }
@@ -381,7 +379,7 @@ static void help(char *name)
 int main(int argc, char *argv[])
 {
 	struct test_params params = {
-		.backing_src = VM_MEM_SRC_ANONYMOUS,
+		.backing_src = DEFAULT_VM_MEM_SRC,
 		.vcpu_memory_bytes = DEFAULT_PER_VCPU_MEM_SIZE,
 		.vcpus = 1,
 	};
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index e79c1b64977f..1510b21e6306 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -179,7 +179,7 @@ static void *uffd_handler_thread_fn(void *arg)
 			return NULL;
 		}
 
-		if (!pollfd[0].revents & POLLIN)
+		if (!(pollfd[0].revents & POLLIN))
 			continue;
 
 		r = read(uffd, &msg, sizeof(msg));
@@ -416,7 +416,7 @@ static void help(char *name)
 {
 	puts("");
 	printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-d uffd_delay_usec]\n"
-	       "          [-b memory] [-t type] [-v vcpus] [-o]\n", name);
+	       "          [-b memory] [-s type] [-v vcpus] [-o]\n", name);
 	guest_modes_help();
 	printf(" -u: use userfaultfd to handle vCPU page faults. Mode is a\n"
 	       "     UFFD registration mode: 'MISSING' or 'MINOR'.\n");
@@ -426,8 +426,7 @@ static void help(char *name)
 	printf(" -b: specify the size of the memory region which should be\n"
 	       "     demand paged by each vCPU. e.g. 10M or 3G.\n"
 	       "     Default: 1G\n");
-	printf(" -t: The type of backing memory to use. Default: anonymous\n");
-	backing_src_help();
+	backing_src_help("-s");
 	printf(" -v: specify the number of vCPUs to run.\n");
 	printf(" -o: Overlap guest memory accesses instead of partitioning\n"
 	       "     them into a separate region of memory for each vCPU.\n");
@@ -439,14 +438,14 @@ int main(int argc, char *argv[])
 {
 	int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
 	struct test_params p = {
-		.src_type = VM_MEM_SRC_ANONYMOUS,
+		.src_type = DEFAULT_VM_MEM_SRC,
 		.partition_vcpu_memory_access = true,
 	};
 	int opt;
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "hm:u:d:b:t:v:o")) != -1) {
+	while ((opt = getopt(argc, argv, "hm:u:d:b:s:v:o")) != -1) {
 		switch (opt) {
 		case 'm':
 			guest_modes_cmdline(optarg);
@@ -465,7 +464,7 @@ int main(int argc, char *argv[])
 		case 'b':
 			guest_percpu_mem_size = parse_size(optarg);
 			break;
-		case 't':
+		case 's':
 			p.src_type = parse_backing_src_type(optarg);
 			break;
 		case 'v':
@@ -485,7 +484,7 @@ int main(int argc, char *argv[])
 
 	if (p.uffd_mode == UFFDIO_REGISTER_MODE_MINOR &&
 	    !backing_src_is_shared(p.src_type)) {
-		TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -t");
+		TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -s");
 	}
 
 	for_each_guest_mode(run_test, &p);
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 479868570d59..7ffab5bd5ce5 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -118,42 +118,64 @@ static inline void disable_dirty_logging(struct kvm_vm *vm, int slots)
 	toggle_dirty_logging(vm, slots, false);
 }
 
-static void get_dirty_log(struct kvm_vm *vm, int slots, unsigned long *bitmap,
-			  uint64_t nr_pages)
+static void get_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], int slots)
 {
-	uint64_t slot_pages = nr_pages / slots;
 	int i;
 
 	for (i = 0; i < slots; i++) {
 		int slot = PERF_TEST_MEM_SLOT_INDEX + i;
-		unsigned long *slot_bitmap = bitmap + i * slot_pages;
 
-		kvm_vm_get_dirty_log(vm, slot, slot_bitmap);
+		kvm_vm_get_dirty_log(vm, slot, bitmaps[i]);
 	}
 }
 
-static void clear_dirty_log(struct kvm_vm *vm, int slots, unsigned long *bitmap,
-			    uint64_t nr_pages)
+static void clear_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[],
+			    int slots, uint64_t pages_per_slot)
 {
-	uint64_t slot_pages = nr_pages / slots;
 	int i;
 
 	for (i = 0; i < slots; i++) {
 		int slot = PERF_TEST_MEM_SLOT_INDEX + i;
-		unsigned long *slot_bitmap = bitmap + i * slot_pages;
 
-		kvm_vm_clear_dirty_log(vm, slot, slot_bitmap, 0, slot_pages);
+		kvm_vm_clear_dirty_log(vm, slot, bitmaps[i], 0, pages_per_slot);
 	}
 }
 
+static unsigned long **alloc_bitmaps(int slots, uint64_t pages_per_slot)
+{
+	unsigned long **bitmaps;
+	int i;
+
+	bitmaps = malloc(slots * sizeof(bitmaps[0]));
+	TEST_ASSERT(bitmaps, "Failed to allocate bitmaps array.");
+
+	for (i = 0; i < slots; i++) {
+		bitmaps[i] = bitmap_zalloc(pages_per_slot);
+		TEST_ASSERT(bitmaps[i], "Failed to allocate slot bitmap.");
+	}
+
+	return bitmaps;
+}
+
+static void free_bitmaps(unsigned long *bitmaps[], int slots)
+{
+	int i;
+
+	for (i = 0; i < slots; i++)
+		free(bitmaps[i]);
+
+	free(bitmaps);
+}
+
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *p = arg;
 	pthread_t *vcpu_threads;
 	struct kvm_vm *vm;
-	unsigned long *bmap;
+	unsigned long **bitmaps;
 	uint64_t guest_num_pages;
 	uint64_t host_num_pages;
+	uint64_t pages_per_slot;
 	int vcpu_id;
 	struct timespec start;
 	struct timespec ts_diff;
@@ -171,7 +193,9 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm);
 	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
 	host_num_pages = vm_num_host_pages(mode, guest_num_pages);
-	bmap = bitmap_zalloc(host_num_pages);
+	pages_per_slot = host_num_pages / p->slots;
+
+	bitmaps = alloc_bitmaps(p->slots, pages_per_slot);
 
 	if (dirty_log_manual_caps) {
 		cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
@@ -239,7 +263,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 			iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
 
 		clock_gettime(CLOCK_MONOTONIC, &start);
-		get_dirty_log(vm, p->slots, bmap, host_num_pages);
+		get_dirty_log(vm, bitmaps, p->slots);
 		ts_diff = timespec_elapsed(start);
 		get_dirty_log_total = timespec_add(get_dirty_log_total,
 						   ts_diff);
@@ -248,7 +272,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 		if (dirty_log_manual_caps) {
 			clock_gettime(CLOCK_MONOTONIC, &start);
-			clear_dirty_log(vm, p->slots, bmap, host_num_pages);
+			clear_dirty_log(vm, bitmaps, p->slots, pages_per_slot);
 			ts_diff = timespec_elapsed(start);
 			clear_dirty_log_total = timespec_add(clear_dirty_log_total,
 							     ts_diff);
@@ -281,7 +305,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 			clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
 	}
 
-	free(bmap);
+	free_bitmaps(bitmaps, p->slots);
 	free(vcpu_threads);
 	perf_test_destroy_vm(vm);
 }
@@ -308,11 +332,9 @@ static void help(char *name)
 	printf(" -v: specify the number of vCPUs to run.\n");
 	printf(" -o: Overlap guest memory accesses instead of partitioning\n"
 	       "     them into a separate region of memory for each vCPU.\n");
-	printf(" -s: specify the type of memory that should be used to\n"
-	       "     back the guest data region.\n\n");
+	backing_src_help("-s");
 	printf(" -x: Split the memory region into this number of memslots.\n"
-	       "     (default: 1)");
-	backing_src_help();
+	       "     (default: 1)\n");
 	puts("");
 	exit(0);
 }
@@ -324,7 +346,7 @@ int main(int argc, char *argv[])
 		.iterations = TEST_HOST_LOOP_N,
 		.wr_fract = 1,
 		.partition_vcpu_memory_access = true,
-		.backing_src = VM_MEM_SRC_ANONYMOUS,
+		.backing_src = DEFAULT_VM_MEM_SRC,
 		.slots = 1,
 	};
 	int opt;
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index d79be15dd3d2..f8fddc84c0d3 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -90,18 +90,23 @@ enum vm_mem_backing_src_type {
 	NUM_SRC_TYPES,
 };
 
+#define DEFAULT_VM_MEM_SRC VM_MEM_SRC_ANONYMOUS
+
 struct vm_mem_backing_src_alias {
 	const char *name;
 	uint32_t flag;
 };
 
+#define MIN_RUN_DELAY_NS	200000UL
+
 bool thp_configured(void);
 size_t get_trans_hugepagesz(void);
 size_t get_def_hugetlb_pagesz(void);
 const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i);
 size_t get_backing_src_pagesz(uint32_t i);
-void backing_src_help(void);
+void backing_src_help(const char *flag);
 enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name);
+long get_run_delay(void);
 
 /*
  * Whether or not the given source type is shared memory (as opposed to
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 242ae8e09a65..05e65ca1c30c 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -312,37 +312,37 @@ static inline void set_xmm(int n, unsigned long val)
 	}
 }
 
-typedef unsigned long v1di __attribute__ ((vector_size (8)));
+#define GET_XMM(__xmm)							\
+({									\
+	unsigned long __val;						\
+	asm volatile("movq %%"#__xmm", %0" : "=r"(__val));		\
+	__val;								\
+})
+
 static inline unsigned long get_xmm(int n)
 {
 	assert(n >= 0 && n <= 7);
 
-	register v1di xmm0 __asm__("%xmm0");
-	register v1di xmm1 __asm__("%xmm1");
-	register v1di xmm2 __asm__("%xmm2");
-	register v1di xmm3 __asm__("%xmm3");
-	register v1di xmm4 __asm__("%xmm4");
-	register v1di xmm5 __asm__("%xmm5");
-	register v1di xmm6 __asm__("%xmm6");
-	register v1di xmm7 __asm__("%xmm7");
 	switch (n) {
 	case 0:
-		return (unsigned long)xmm0;
+		return GET_XMM(xmm0);
 	case 1:
-		return (unsigned long)xmm1;
+		return GET_XMM(xmm1);
 	case 2:
-		return (unsigned long)xmm2;
+		return GET_XMM(xmm2);
 	case 3:
-		return (unsigned long)xmm3;
+		return GET_XMM(xmm3);
 	case 4:
-		return (unsigned long)xmm4;
+		return GET_XMM(xmm4);
 	case 5:
-		return (unsigned long)xmm5;
+		return GET_XMM(xmm5);
 	case 6:
-		return (unsigned long)xmm6;
+		return GET_XMM(xmm6);
 	case 7:
-		return (unsigned long)xmm7;
+		return GET_XMM(xmm7);
 	}
+
+	/* never reached */
 	return 0;
 }
 
diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c
index 0d04a7db7f24..36407cb0ec85 100644
--- a/tools/testing/selftests/kvm/kvm_page_table_test.c
+++ b/tools/testing/selftests/kvm/kvm_page_table_test.c
@@ -456,10 +456,7 @@ static void help(char *name)
 	       "     (default: 1G)\n");
 	printf(" -v: specify the number of vCPUs to run\n"
 	       "     (default: 1)\n");
-	printf(" -s: specify the type of memory that should be used to\n"
-	       "     back the guest data region.\n"
-	       "     (default: anonymous)\n\n");
-	backing_src_help();
+	backing_src_help("-s");
 	puts("");
 }
 
@@ -468,7 +465,7 @@ int main(int argc, char *argv[])
 	int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
 	struct test_params p = {
 		.test_mem_size = DEFAULT_TEST_MEM_SIZE,
-		.src_type = VM_MEM_SRC_ANONYMOUS,
+		.src_type = DEFAULT_VM_MEM_SRC,
 	};
 	int opt;
 
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index af1031fed97f..b72429108993 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -11,6 +11,7 @@
 #include <stdlib.h>
 #include <time.h>
 #include <sys/stat.h>
+#include <sys/syscall.h>
 #include <linux/mman.h>
 #include "linux/kernel.h"
 
@@ -129,13 +130,16 @@ size_t get_trans_hugepagesz(void)
 {
 	size_t size;
 	FILE *f;
+	int ret;
 
 	TEST_ASSERT(thp_configured(), "THP is not configured in host kernel");
 
 	f = fopen("/sys/kernel/mm/transparent_hugepage/hpage_pmd_size", "r");
 	TEST_ASSERT(f != NULL, "Error in opening transparent_hugepage/hpage_pmd_size");
 
-	fscanf(f, "%ld", &size);
+	ret = fscanf(f, "%ld", &size);
+	ret = fscanf(f, "%ld", &size);
+	TEST_ASSERT(ret < 1, "Error reading transparent_hugepage/hpage_pmd_size");
 	fclose(f);
 
 	return size;
@@ -279,13 +283,22 @@ size_t get_backing_src_pagesz(uint32_t i)
 	}
 }
 
-void backing_src_help(void)
+static void print_available_backing_src_types(const char *prefix)
 {
 	int i;
 
-	printf("Available backing src types:\n");
+	printf("%sAvailable backing src types:\n", prefix);
+
 	for (i = 0; i < NUM_SRC_TYPES; i++)
-		printf("\t%s\n", vm_mem_backing_src_alias(i)->name);
+		printf("%s    %s\n", prefix, vm_mem_backing_src_alias(i)->name);
+}
+
+void backing_src_help(const char *flag)
+{
+	printf(" %s: specify the type of memory that should be used to\n"
+	       "     back the guest data region. (default: %s)\n",
+	       flag, vm_mem_backing_src_alias(DEFAULT_VM_MEM_SRC)->name);
+	print_available_backing_src_types("     ");
 }
 
 enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name)
@@ -296,7 +309,23 @@ enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name)
 		if (!strcmp(type_name, vm_mem_backing_src_alias(i)->name))
 			return i;
 
-	backing_src_help();
+	print_available_backing_src_types("");
 	TEST_FAIL("Unknown backing src type: %s", type_name);
 	return -1;
 }
+
+long get_run_delay(void)
+{
+	char path[64];
+	long val[2];
+	FILE *fp;
+
+	sprintf(path, "/proc/%ld/schedstat", syscall(SYS_gettid));
+	fp = fopen(path, "r");
+	/* Return MIN_RUN_DELAY_NS upon failure just to be safe */
+	if (fscanf(fp, "%ld %ld ", &val[0], &val[1]) < 2)
+		val[1] = MIN_RUN_DELAY_NS;
+	fclose(fp);
+
+	return val[1];
+}
diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c
new file mode 100644
index 000000000000..4158da0da2bb
--- /dev/null
+++ b/tools/testing/selftests/kvm/rseq_test.c
@@ -0,0 +1,286 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <errno.h>
+#include <fcntl.h>
+#include <pthread.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+#include <syscall.h>
+#include <sys/ioctl.h>
+#include <sys/sysinfo.h>
+#include <asm/barrier.h>
+#include <linux/atomic.h>
+#include <linux/rseq.h>
+#include <linux/unistd.h>
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "test_util.h"
+
+#define VCPU_ID 0
+
+static __thread volatile struct rseq __rseq = {
+	.cpu_id = RSEQ_CPU_ID_UNINITIALIZED,
+};
+
+/*
+ * Use an arbitrary, bogus signature for configuring rseq, this test does not
+ * actually enter an rseq critical section.
+ */
+#define RSEQ_SIG 0xdeadbeef
+
+/*
+ * Any bug related to task migration is likely to be timing-dependent; perform
+ * a large number of migrations to reduce the odds of a false negative.
+ */
+#define NR_TASK_MIGRATIONS 100000
+
+static pthread_t migration_thread;
+static cpu_set_t possible_mask;
+static int min_cpu, max_cpu;
+static bool done;
+
+static atomic_t seq_cnt;
+
+static void guest_code(void)
+{
+	for (;;)
+		GUEST_SYNC(0);
+}
+
+static void sys_rseq(int flags)
+{
+	int r;
+
+	r = syscall(__NR_rseq, &__rseq, sizeof(__rseq), flags, RSEQ_SIG);
+	TEST_ASSERT(!r, "rseq failed, errno = %d (%s)", errno, strerror(errno));
+}
+
+static int next_cpu(int cpu)
+{
+	/*
+	 * Advance to the next CPU, skipping those that weren't in the original
+	 * affinity set.  Sadly, there is no CPU_SET_FOR_EACH, and cpu_set_t's
+	 * data storage is considered as opaque.  Note, if this task is pinned
+	 * to a small set of discontigous CPUs, e.g. 2 and 1023, this loop will
+	 * burn a lot cycles and the test will take longer than normal to
+	 * complete.
+	 */
+	do {
+		cpu++;
+		if (cpu > max_cpu) {
+			cpu = min_cpu;
+			TEST_ASSERT(CPU_ISSET(cpu, &possible_mask),
+				    "Min CPU = %d must always be usable", cpu);
+			break;
+		}
+	} while (!CPU_ISSET(cpu, &possible_mask));
+
+	return cpu;
+}
+
+static void *migration_worker(void *ign)
+{
+	cpu_set_t allowed_mask;
+	int r, i, cpu;
+
+	CPU_ZERO(&allowed_mask);
+
+	for (i = 0, cpu = min_cpu; i < NR_TASK_MIGRATIONS; i++, cpu = next_cpu(cpu)) {
+		CPU_SET(cpu, &allowed_mask);
+
+		/*
+		 * Bump the sequence count twice to allow the reader to detect
+		 * that a migration may have occurred in between rseq and sched
+		 * CPU ID reads.  An odd sequence count indicates a migration
+		 * is in-progress, while a completely different count indicates
+		 * a migration occurred since the count was last read.
+		 */
+		atomic_inc(&seq_cnt);
+
+		/*
+		 * Ensure the odd count is visible while sched_getcpu() isn't
+		 * stable, i.e. while changing affinity is in-progress.
+		 */
+		smp_wmb();
+		r = sched_setaffinity(0, sizeof(allowed_mask), &allowed_mask);
+		TEST_ASSERT(!r, "sched_setaffinity failed, errno = %d (%s)",
+			    errno, strerror(errno));
+		smp_wmb();
+		atomic_inc(&seq_cnt);
+
+		CPU_CLR(cpu, &allowed_mask);
+
+		/*
+		 * Wait 1-10us before proceeding to the next iteration and more
+		 * specifically, before bumping seq_cnt again.  A delay is
+		 * needed on three fronts:
+		 *
+		 *  1. To allow sched_setaffinity() to prompt migration before
+		 *     ioctl(KVM_RUN) enters the guest so that TIF_NOTIFY_RESUME
+		 *     (or TIF_NEED_RESCHED, which indirectly leads to handling
+		 *     NOTIFY_RESUME) is handled in KVM context.
+		 *
+		 *     If NOTIFY_RESUME/NEED_RESCHED is set after KVM enters
+		 *     the guest, the guest will trigger a IO/MMIO exit all the
+		 *     way to userspace and the TIF flags will be handled by
+		 *     the generic "exit to userspace" logic, not by KVM.  The
+		 *     exit to userspace is necessary to give the test a chance
+		 *     to check the rseq CPU ID (see #2).
+		 *
+		 *     Alternatively, guest_code() could include an instruction
+		 *     to trigger an exit that is handled by KVM, but any such
+		 *     exit requires architecture specific code.
+		 *
+		 *  2. To let ioctl(KVM_RUN) make its way back to the test
+		 *     before the next round of migration.  The test's check on
+		 *     the rseq CPU ID must wait for migration to complete in
+		 *     order to avoid false positive, thus any kernel rseq bug
+		 *     will be missed if the next migration starts before the
+		 *     check completes.
+		 *
+		 *  3. To ensure the read-side makes efficient forward progress,
+		 *     e.g. if sched_getcpu() involves a syscall.  Stalling the
+		 *     read-side means the test will spend more time waiting for
+		 *     sched_getcpu() to stabilize and less time trying to hit
+		 *     the timing-dependent bug.
+		 *
+		 * Because any bug in this area is likely to be timing-dependent,
+		 * run with a range of delays at 1us intervals from 1us to 10us
+		 * as a best effort to avoid tuning the test to the point where
+		 * it can hit _only_ the original bug and not detect future
+		 * regressions.
+		 *
+		 * The original bug can reproduce with a delay up to ~500us on
+		 * x86-64, but starts to require more iterations to reproduce
+		 * as the delay creeps above ~10us, and the average runtime of
+		 * each iteration obviously increases as well.  Cap the delay
+		 * at 10us to keep test runtime reasonable while minimizing
+		 * potential coverage loss.
+		 *
+		 * The lower bound for reproducing the bug is likely below 1us,
+		 * e.g. failures occur on x86-64 with nanosleep(0), but at that
+		 * point the overhead of the syscall likely dominates the delay.
+		 * Use usleep() for simplicity and to avoid unnecessary kernel
+		 * dependencies.
+		 */
+		usleep((i % 10) + 1);
+	}
+	done = true;
+	return NULL;
+}
+
+static int calc_min_max_cpu(void)
+{
+	int i, cnt, nproc;
+
+	if (CPU_COUNT(&possible_mask) < 2)
+		return -EINVAL;
+
+	/*
+	 * CPU_SET doesn't provide a FOR_EACH helper, get the min/max CPU that
+	 * this task is affined to in order to reduce the time spent querying
+	 * unusable CPUs, e.g. if this task is pinned to a small percentage of
+	 * total CPUs.
+	 */
+	nproc = get_nprocs_conf();
+	min_cpu = -1;
+	max_cpu = -1;
+	cnt = 0;
+
+	for (i = 0; i < nproc; i++) {
+		if (!CPU_ISSET(i, &possible_mask))
+			continue;
+		if (min_cpu == -1)
+			min_cpu = i;
+		max_cpu = i;
+		cnt++;
+	}
+
+	return (cnt < 2) ? -EINVAL : 0;
+}
+
+int main(int argc, char *argv[])
+{
+	int r, i, snapshot;
+	struct kvm_vm *vm;
+	u32 cpu, rseq_cpu;
+
+	/* Tell stdout not to buffer its content */
+	setbuf(stdout, NULL);
+
+	r = sched_getaffinity(0, sizeof(possible_mask), &possible_mask);
+	TEST_ASSERT(!r, "sched_getaffinity failed, errno = %d (%s)", errno,
+		    strerror(errno));
+
+	if (calc_min_max_cpu()) {
+		print_skip("Only one usable CPU, task migration not possible");
+		exit(KSFT_SKIP);
+	}
+
+	sys_rseq(0);
+
+	/*
+	 * Create and run a dummy VM that immediately exits to userspace via
+	 * GUEST_SYNC, while concurrently migrating the process by setting its
+	 * CPU affinity.
+	 */
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+	ucall_init(vm, NULL);
+
+	pthread_create(&migration_thread, NULL, migration_worker, 0);
+
+	for (i = 0; !done; i++) {
+		vcpu_run(vm, VCPU_ID);
+		TEST_ASSERT(get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC,
+			    "Guest failed?");
+
+		/*
+		 * Verify rseq's CPU matches sched's CPU.  Ensure migration
+		 * doesn't occur between sched_getcpu() and reading the rseq
+		 * cpu_id by rereading both if the sequence count changes, or
+		 * if the count is odd (migration in-progress).
+		 */
+		do {
+			/*
+			 * Drop bit 0 to force a mismatch if the count is odd,
+			 * i.e. if a migration is in-progress.
+			 */
+			snapshot = atomic_read(&seq_cnt) & ~1;
+
+			/*
+			 * Ensure reading sched_getcpu() and rseq.cpu_id
+			 * complete in a single "no migration" window, i.e. are
+			 * not reordered across the seq_cnt reads.
+			 */
+			smp_rmb();
+			cpu = sched_getcpu();
+			rseq_cpu = READ_ONCE(__rseq.cpu_id);
+			smp_rmb();
+		} while (snapshot != atomic_read(&seq_cnt));
+
+		TEST_ASSERT(rseq_cpu == cpu,
+			    "rseq CPU = %d, sched CPU = %d\n", rseq_cpu, cpu);
+	}
+
+	/*
+	 * Sanity check that the test was able to enter the guest a reasonable
+	 * number of times, e.g. didn't get stalled too often/long waiting for
+	 * sched_getcpu() to stabilize.  A 2:1 migration:KVM_RUN ratio is a
+	 * fairly conservative ratio on x86-64, which can do _more_ KVM_RUNs
+	 * than migrations given the 1us+ delay in the migration task.
+	 */
+	TEST_ASSERT(i > (NR_TASK_MIGRATIONS / 2),
+		    "Only performed %d KVM_RUNs, task stalled too much?\n", i);
+
+	pthread_join(migration_thread, NULL);
+
+	kvm_vm_free(vm);
+
+	sys_rseq(RSEQ_FLAG_UNREGISTER);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c
index ecec30865a74..62f2eb9ee3d5 100644
--- a/tools/testing/selftests/kvm/steal_time.c
+++ b/tools/testing/selftests/kvm/steal_time.c
@@ -10,7 +10,6 @@
 #include <sched.h>
 #include <pthread.h>
 #include <linux/kernel.h>
-#include <sys/syscall.h>
 #include <asm/kvm.h>
 #include <asm/kvm_para.h>
 
@@ -20,7 +19,6 @@
 
 #define NR_VCPUS		4
 #define ST_GPA_BASE		(1 << 30)
-#define MIN_RUN_DELAY_NS	200000UL
 
 static void *st_gva[NR_VCPUS];
 static uint64_t guest_stolen_time[NR_VCPUS];
@@ -118,12 +116,12 @@ struct st_time {
 	uint64_t st_time;
 };
 
-static int64_t smccc(uint32_t func, uint32_t arg)
+static int64_t smccc(uint32_t func, uint64_t arg)
 {
 	unsigned long ret;
 
 	asm volatile(
-		"mov	x0, %1\n"
+		"mov	w0, %w1\n"
 		"mov	x1, %2\n"
 		"hvc	#0\n"
 		"mov	%0, x0\n"
@@ -217,20 +215,6 @@ static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpuid)
 
 #endif
 
-static long get_run_delay(void)
-{
-	char path[64];
-	long val[2];
-	FILE *fp;
-
-	sprintf(path, "/proc/%ld/schedstat", syscall(SYS_gettid));
-	fp = fopen(path, "r");
-	fscanf(fp, "%ld %ld ", &val[0], &val[1]);
-	fclose(fp);
-
-	return val[1];
-}
-
 static void *do_steal_time(void *arg)
 {
 	struct timespec ts, stop;
diff --git a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c
index e6480fd5c4bd..8039e1eff938 100644
--- a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c
+++ b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c
@@ -82,7 +82,8 @@ int get_warnings_count(void)
 	FILE *f;
 
 	f = popen("dmesg | grep \"WARNING:\" | wc -l", "r");
-	fscanf(f, "%d", &warnings);
+	if (fscanf(f, "%d", &warnings) < 1)
+		warnings = 0;
 	fclose(f);
 
 	return warnings;
diff --git a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c
new file mode 100644
index 000000000000..df04f56ce859
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * svm_int_ctl_test
+ *
+ * Copyright (C) 2021, Red Hat, Inc.
+ *
+ * Nested SVM testing: test simultaneous use of V_IRQ from L1 and L0.
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "svm_util.h"
+#include "apic.h"
+
+#define VCPU_ID		0
+
+static struct kvm_vm *vm;
+
+bool vintr_irq_called;
+bool intr_irq_called;
+
+#define VINTR_IRQ_NUMBER 0x20
+#define INTR_IRQ_NUMBER 0x30
+
+static void vintr_irq_handler(struct ex_regs *regs)
+{
+	vintr_irq_called = true;
+}
+
+static void intr_irq_handler(struct ex_regs *regs)
+{
+	x2apic_write_reg(APIC_EOI, 0x00);
+	intr_irq_called = true;
+}
+
+static void l2_guest_code(struct svm_test_data *svm)
+{
+	/* This code raises interrupt INTR_IRQ_NUMBER in the L1's LAPIC,
+	 * and since L1 didn't enable virtual interrupt masking,
+	 * L2 should receive it and not L1.
+	 *
+	 * L2 also has virtual interrupt 'VINTR_IRQ_NUMBER' pending in V_IRQ
+	 * so it should also receive it after the following 'sti'.
+	 */
+	x2apic_write_reg(APIC_ICR,
+		APIC_DEST_SELF | APIC_INT_ASSERT | INTR_IRQ_NUMBER);
+
+	__asm__ __volatile__(
+		"sti\n"
+		"nop\n"
+	);
+
+	GUEST_ASSERT(vintr_irq_called);
+	GUEST_ASSERT(intr_irq_called);
+
+	__asm__ __volatile__(
+		"vmcall\n"
+	);
+}
+
+static void l1_guest_code(struct svm_test_data *svm)
+{
+	#define L2_GUEST_STACK_SIZE 64
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	struct vmcb *vmcb = svm->vmcb;
+
+	x2apic_enable();
+
+	/* Prepare for L2 execution. */
+	generic_svm_setup(svm, l2_guest_code,
+			  &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	/* No virtual interrupt masking */
+	vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK;
+
+	/* No intercepts for real and virtual interrupts */
+	vmcb->control.intercept &= ~(1ULL << INTERCEPT_INTR | INTERCEPT_VINTR);
+
+	/* Make a virtual interrupt VINTR_IRQ_NUMBER pending */
+	vmcb->control.int_ctl |= V_IRQ_MASK | (0x1 << V_INTR_PRIO_SHIFT);
+	vmcb->control.int_vector = VINTR_IRQ_NUMBER;
+
+	run_guest(vmcb, svm->vmcb_gpa);
+	GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL);
+	GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+	vm_vaddr_t svm_gva;
+
+	nested_svm_check_supported();
+
+	vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
+
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vm, VCPU_ID);
+
+	vm_install_exception_handler(vm, VINTR_IRQ_NUMBER, vintr_irq_handler);
+	vm_install_exception_handler(vm, INTR_IRQ_NUMBER, intr_irq_handler);
+
+	vcpu_alloc_svm(vm, &svm_gva);
+	vcpu_args_set(vm, VCPU_ID, 1, svm_gva);
+
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+	struct ucall uc;
+
+	vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+		    "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n",
+		    run->exit_reason,
+		    exit_reason_str(run->exit_reason));
+
+	switch (get_ucall(vm, VCPU_ID, &uc)) {
+	case UCALL_ABORT:
+		TEST_FAIL("%s", (const char *)uc.args[0]);
+		break;
+		/* NOT REACHED */
+	case UCALL_DONE:
+		goto done;
+	default:
+		TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd);
+	}
+done:
+	kvm_vm_free(vm);
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index 117bf49a3d79..eda0d2a51224 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -14,7 +14,6 @@
 #include <stdint.h>
 #include <time.h>
 #include <sched.h>
-#include <sys/syscall.h>
 
 #define VCPU_ID		5
 
@@ -98,20 +97,6 @@ static void guest_code(void)
 	GUEST_DONE();
 }
 
-static long get_run_delay(void)
-{
-        char path[64];
-        long val[2];
-        FILE *fp;
-
-        sprintf(path, "/proc/%ld/schedstat", syscall(SYS_gettid));
-        fp = fopen(path, "r");
-        fscanf(fp, "%ld %ld ", &val[0], &val[1]);
-        fclose(fp);
-
-        return val[1];
-}
-
 static int cmp_timespec(struct timespec *a, struct timespec *b)
 {
 	if (a->tv_sec > b->tv_sec)
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index fa2ac0e56b43..fe7ee2b0f29c 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -48,6 +48,7 @@ ARCH		?= $(SUBARCH)
 # When local build is done, headers are installed in the default
 # INSTALL_HDR_PATH usr/include.
 .PHONY: khdr
+.NOTPARALLEL:
 khdr:
 ifndef KSFT_KHDR_INSTALL_DONE
 ifeq (1,$(DEFAULT_INSTALL_HDR_PATH))
diff --git a/tools/testing/selftests/nci/nci_dev.c b/tools/testing/selftests/nci/nci_dev.c
index e1bf55dabdf6..162c41e9bcae 100644
--- a/tools/testing/selftests/nci/nci_dev.c
+++ b/tools/testing/selftests/nci/nci_dev.c
@@ -746,7 +746,7 @@ int read_write_nci_cmd(int nfc_sock, int virtual_fd, const __u8 *cmd, __u32 cmd_
 		       const __u8 *rsp, __u32 rsp_len)
 {
 	char buf[256];
-	unsigned int len;
+	int len;
 
 	send(nfc_sock, &cmd[3], cmd_len - 3, 0);
 	len = read(virtual_fd, buf, cmd_len);
diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile
index cfc7f4f97fd1..df341648f818 100644
--- a/tools/testing/selftests/net/af_unix/Makefile
+++ b/tools/testing/selftests/net/af_unix/Makefile
@@ -1,5 +1,2 @@
-##TEST_GEN_FILES := test_unix_oob
-TEST_PROGS := test_unix_oob
+TEST_GEN_PROGS := test_unix_oob
 include ../../lib.mk
-
-all: $(TEST_PROGS)
diff --git a/tools/testing/selftests/net/af_unix/test_unix_oob.c b/tools/testing/selftests/net/af_unix/test_unix_oob.c
index 0f3e3763f4f8..3dece8b29253 100644
--- a/tools/testing/selftests/net/af_unix/test_unix_oob.c
+++ b/tools/testing/selftests/net/af_unix/test_unix_oob.c
@@ -271,8 +271,9 @@ main(int argc, char **argv)
 	read_oob(pfd, &oob);
 
 	if (!signal_recvd || len != 127 || oob != '%' || atmark != 1) {
-		fprintf(stderr, "Test 3 failed, sigurg %d len %d OOB %c ",
-		"atmark %d\n", signal_recvd, len, oob, atmark);
+		fprintf(stderr,
+			"Test 3 failed, sigurg %d len %d OOB %c atmark %d\n",
+			signal_recvd, len, oob, atmark);
 		die(1);
 	}
 
diff --git a/tools/testing/selftests/net/altnames.sh b/tools/testing/selftests/net/altnames.sh
index 4254ddc3f70b..1ef9e4159bba 100755
--- a/tools/testing/selftests/net/altnames.sh
+++ b/tools/testing/selftests/net/altnames.sh
@@ -45,7 +45,7 @@ altnames_test()
 	check_err $? "Got unexpected long alternative name from link show JSON"
 
 	ip link property del $DUMMY_DEV altname $SHORT_NAME
-	check_err $? "Failed to add short alternative name"
+	check_err $? "Failed to delete short alternative name"
 
 	ip -j -p link show $SHORT_NAME &>/dev/null
 	check_fail $? "Unexpected success while trying to do link show with deleted short alternative name"
diff --git a/tools/testing/selftests/netfilter/nft_nat_zones.sh b/tools/testing/selftests/netfilter/nft_nat_zones.sh
new file mode 100755
index 000000000000..b9ab37380f33
--- /dev/null
+++ b/tools/testing/selftests/netfilter/nft_nat_zones.sh
@@ -0,0 +1,309 @@
+#!/bin/bash
+#
+# Test connection tracking zone and NAT source port reallocation support.
+#
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+# Don't increase too much, 2000 clients should work
+# just fine but script can then take several minutes with
+# KASAN/debug builds.
+maxclients=100
+
+have_iperf=1
+ret=0
+
+# client1---.
+#            veth1-.
+#                  |
+#               NAT Gateway --veth0--> Server
+#                  | |
+#            veth2-' |
+# client2---'        |
+#  ....              |
+# clientX----vethX---'
+
+# All clients share identical IP address.
+# NAT Gateway uses policy routing and conntrack zones to isolate client
+# namespaces.  Each client connects to Server, each with colliding tuples:
+#   clientsaddr:10000 -> serveraddr:dport
+#   NAT Gateway is supposed to do port reallocation for each of the
+#   connections.
+
+sfx=$(mktemp -u "XXXXXXXX")
+gw="ns-gw-$sfx"
+cl1="ns-cl1-$sfx"
+cl2="ns-cl2-$sfx"
+srv="ns-srv-$sfx"
+
+v4gc1=$(sysctl -n net.ipv4.neigh.default.gc_thresh1 2>/dev/null)
+v4gc2=$(sysctl -n net.ipv4.neigh.default.gc_thresh2 2>/dev/null)
+v4gc3=$(sysctl -n net.ipv4.neigh.default.gc_thresh3 2>/dev/null)
+v6gc1=$(sysctl -n net.ipv6.neigh.default.gc_thresh1 2>/dev/null)
+v6gc2=$(sysctl -n net.ipv6.neigh.default.gc_thresh2 2>/dev/null)
+v6gc3=$(sysctl -n net.ipv6.neigh.default.gc_thresh3 2>/dev/null)
+
+cleanup()
+{
+	ip netns del $gw
+	ip netns del $srv
+	for i in $(seq 1 $maxclients); do
+		ip netns del ns-cl$i-$sfx 2>/dev/null
+	done
+
+	sysctl -q net.ipv4.neigh.default.gc_thresh1=$v4gc1 2>/dev/null
+	sysctl -q net.ipv4.neigh.default.gc_thresh2=$v4gc2 2>/dev/null
+	sysctl -q net.ipv4.neigh.default.gc_thresh3=$v4gc3 2>/dev/null
+	sysctl -q net.ipv6.neigh.default.gc_thresh1=$v6gc1 2>/dev/null
+	sysctl -q net.ipv6.neigh.default.gc_thresh2=$v6gc2 2>/dev/null
+	sysctl -q net.ipv6.neigh.default.gc_thresh3=$v6gc3 2>/dev/null
+}
+
+nft --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without nft tool"
+	exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+conntrack -V > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without conntrack tool"
+	exit $ksft_skip
+fi
+
+iperf3 -v >/dev/null 2>&1
+if [ $? -ne 0 ];then
+	have_iperf=0
+fi
+
+ip netns add "$gw"
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not create net namespace $gw"
+	exit $ksft_skip
+fi
+ip -net "$gw" link set lo up
+
+trap cleanup EXIT
+
+ip netns add "$srv"
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not create server netns $srv"
+	exit $ksft_skip
+fi
+
+ip link add veth0 netns "$gw" type veth peer name eth0 netns "$srv"
+ip -net "$gw" link set veth0 up
+ip -net "$srv" link set lo up
+ip -net "$srv" link set eth0 up
+
+sysctl -q net.ipv6.neigh.default.gc_thresh1=512  2>/dev/null
+sysctl -q net.ipv6.neigh.default.gc_thresh2=1024 2>/dev/null
+sysctl -q net.ipv6.neigh.default.gc_thresh3=4096 2>/dev/null
+sysctl -q net.ipv4.neigh.default.gc_thresh1=512  2>/dev/null
+sysctl -q net.ipv4.neigh.default.gc_thresh2=1024 2>/dev/null
+sysctl -q net.ipv4.neigh.default.gc_thresh3=4096 2>/dev/null
+
+for i in $(seq 1 $maxclients);do
+  cl="ns-cl$i-$sfx"
+
+  ip netns add "$cl"
+  if [ $? -ne 0 ];then
+     echo "SKIP: Could not create client netns $cl"
+     exit $ksft_skip
+  fi
+  ip link add veth$i netns "$gw" type veth peer name eth0 netns "$cl" > /dev/null 2>&1
+  if [ $? -ne 0 ];then
+    echo "SKIP: No virtual ethernet pair device support in kernel"
+    exit $ksft_skip
+  fi
+done
+
+for i in $(seq 1 $maxclients);do
+  cl="ns-cl$i-$sfx"
+  echo netns exec "$cl" ip link set lo up
+  echo netns exec "$cl" ip link set eth0 up
+  echo netns exec "$cl" sysctl -q net.ipv4.tcp_syn_retries=2
+  echo netns exec "$gw" ip link set veth$i up
+  echo netns exec "$gw" sysctl -q net.ipv4.conf.veth$i.arp_ignore=2
+  echo netns exec "$gw" sysctl -q net.ipv4.conf.veth$i.rp_filter=0
+
+  # clients have same IP addresses.
+  echo netns exec "$cl" ip addr add 10.1.0.3/24 dev eth0
+  echo netns exec "$cl" ip addr add dead:1::3/64 dev eth0
+  echo netns exec "$cl" ip route add default via 10.1.0.2 dev eth0
+  echo netns exec "$cl" ip route add default via dead:1::2 dev eth0
+
+  # NB: same addresses on client-facing interfaces.
+  echo netns exec "$gw" ip addr add 10.1.0.2/24 dev veth$i
+  echo netns exec "$gw" ip addr add dead:1::2/64 dev veth$i
+
+  # gw: policy routing
+  echo netns exec "$gw" ip route add 10.1.0.0/24 dev veth$i table $((1000+i))
+  echo netns exec "$gw" ip route add dead:1::0/64 dev veth$i table $((1000+i))
+  echo netns exec "$gw" ip route add 10.3.0.0/24 dev veth0 table $((1000+i))
+  echo netns exec "$gw" ip route add dead:3::0/64 dev veth0 table $((1000+i))
+  echo netns exec "$gw" ip rule add fwmark $i lookup $((1000+i))
+done | ip -batch /dev/stdin
+
+ip -net "$gw" addr add 10.3.0.1/24 dev veth0
+ip -net "$gw" addr add dead:3::1/64 dev veth0
+
+ip -net "$srv" addr add 10.3.0.99/24 dev eth0
+ip -net "$srv" addr add dead:3::99/64 dev eth0
+
+ip netns exec $gw nft -f /dev/stdin<<EOF
+table inet raw {
+	map iiftomark {
+		type ifname : mark
+	}
+
+	map iiftozone {
+		typeof iifname : ct zone
+	}
+
+	set inicmp {
+		flags dynamic
+		type ipv4_addr . ifname . ipv4_addr
+	}
+	set inflows {
+		flags dynamic
+		type ipv4_addr . inet_service . ifname . ipv4_addr . inet_service
+	}
+
+	set inflows6 {
+		flags dynamic
+		type ipv6_addr . inet_service . ifname . ipv6_addr . inet_service
+	}
+
+	chain prerouting {
+		type filter hook prerouting priority -64000; policy accept;
+		ct original zone set meta iifname map @iiftozone
+		meta mark set meta iifname map @iiftomark
+
+		tcp flags & (syn|ack) == ack add @inflows { ip saddr . tcp sport . meta iifname . ip daddr . tcp dport counter }
+		add @inflows6 { ip6 saddr . tcp sport . meta iifname . ip6 daddr . tcp dport counter }
+		ip protocol icmp add @inicmp { ip saddr . meta iifname . ip daddr counter }
+	}
+
+	chain nat_postrouting {
+		type nat hook postrouting priority 0; policy accept;
+                ct mark set meta mark meta oifname veth0 masquerade
+	}
+
+	chain mangle_prerouting {
+		type filter hook prerouting priority -100; policy accept;
+		ct direction reply meta mark set ct mark
+	}
+}
+EOF
+
+( echo add element inet raw iiftomark \{
+	for i in $(seq 1 $((maxclients-1))); do
+		echo \"veth$i\" : $i,
+	done
+	echo \"veth$maxclients\" : $maxclients \}
+	echo add element inet raw iiftozone \{
+	for i in $(seq 1 $((maxclients-1))); do
+		echo \"veth$i\" : $i,
+	done
+	echo \"veth$maxclients\" : $maxclients \}
+) | ip netns exec $gw nft -f /dev/stdin
+
+ip netns exec "$gw" sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null
+ip netns exec "$gw" sysctl -q net.ipv6.conf.all.forwarding=1 > /dev/null
+ip netns exec "$gw" sysctl -q net.ipv4.conf.all.rp_filter=0 >/dev/null
+
+# useful for debugging: allows to use 'ping' from clients to gateway.
+ip netns exec "$gw" sysctl -q net.ipv4.fwmark_reflect=1 > /dev/null
+ip netns exec "$gw" sysctl -q net.ipv6.fwmark_reflect=1 > /dev/null
+
+for i in $(seq 1 $maxclients); do
+  cl="ns-cl$i-$sfx"
+  ip netns exec $cl ping -i 0.5 -q -c 3 10.3.0.99 > /dev/null 2>&1 &
+  if [ $? -ne 0 ]; then
+     echo FAIL: Ping failure from $cl 1>&2
+     ret=1
+     break
+  fi
+done
+
+wait
+
+for i in $(seq 1 $maxclients); do
+   ip netns exec $gw nft get element inet raw inicmp "{ 10.1.0.3 . \"veth$i\" . 10.3.0.99 }" | grep -q "{ 10.1.0.3 . \"veth$i\" . 10.3.0.99 counter packets 3 bytes 252 }"
+   if [ $? -ne 0 ];then
+      ret=1
+      echo "FAIL: counter icmp mismatch for veth$i" 1>&2
+      ip netns exec $gw nft get element inet raw inicmp "{ 10.1.0.3 . \"veth$i\" . 10.3.0.99 }" 1>&2
+      break
+   fi
+done
+
+ip netns exec $gw nft get element inet raw inicmp "{ 10.3.0.99 . \"veth0\" . 10.3.0.1 }" | grep -q "{ 10.3.0.99 . \"veth0\" . 10.3.0.1 counter packets $((3 * $maxclients)) bytes $((252 * $maxclients)) }"
+if [ $? -ne 0 ];then
+    ret=1
+    echo "FAIL: counter icmp mismatch for veth0: { 10.3.0.99 . \"veth0\" . 10.3.0.1 counter packets $((3 * $maxclients)) bytes $((252 * $maxclients)) }"
+    ip netns exec $gw nft get element inet raw inicmp "{ 10.3.99 . \"veth0\" . 10.3.0.1 }" 1>&2
+fi
+
+if  [ $ret -eq 0 ]; then
+	echo "PASS: ping test from all $maxclients namespaces"
+fi
+
+if [ $have_iperf -eq 0 ];then
+	echo "SKIP: iperf3 not installed"
+	if [ $ret -ne 0 ];then
+	    exit $ret
+	fi
+	exit $ksft_skip
+fi
+
+ip netns exec $srv iperf3 -s > /dev/null 2>&1 &
+iperfpid=$!
+sleep 1
+
+for i in $(seq 1 $maxclients); do
+  if [ $ret -ne 0 ]; then
+     break
+  fi
+  cl="ns-cl$i-$sfx"
+  ip netns exec $cl iperf3 -c 10.3.0.99 --cport 10000 -n 1 > /dev/null
+  if [ $? -ne 0 ]; then
+     echo FAIL: Failure to connect for $cl 1>&2
+     ip netns exec $gw conntrack -S 1>&2
+     ret=1
+  fi
+done
+if [ $ret -eq 0 ];then
+	echo "PASS: iperf3 connections for all $maxclients net namespaces"
+fi
+
+kill $iperfpid
+wait
+
+for i in $(seq 1 $maxclients); do
+   ip netns exec $gw nft get element inet raw inflows "{ 10.1.0.3 . 10000 . \"veth$i\" . 10.3.0.99 . 5201 }" > /dev/null
+   if [ $? -ne 0 ];then
+      ret=1
+      echo "FAIL: can't find expected tcp entry for veth$i" 1>&2
+      break
+   fi
+done
+if [ $ret -eq 0 ];then
+	echo "PASS: Found client connection for all $maxclients net namespaces"
+fi
+
+ip netns exec $gw nft get element inet raw inflows "{ 10.3.0.99 . 5201 . \"veth0\" . 10.3.0.1 . 10000 }" > /dev/null
+if [ $? -ne 0 ];then
+    ret=1
+    echo "FAIL: cannot find return entry on veth0" 1>&2
+fi
+
+exit $ret
diff --git a/tools/testing/selftests/netfilter/nft_zones_many.sh b/tools/testing/selftests/netfilter/nft_zones_many.sh
new file mode 100755
index 000000000000..ac646376eb01
--- /dev/null
+++ b/tools/testing/selftests/netfilter/nft_zones_many.sh
@@ -0,0 +1,156 @@
+#!/bin/bash
+
+# Test insertion speed for packets with identical addresses/ports
+# that are all placed in distinct conntrack zones.
+
+sfx=$(mktemp -u "XXXXXXXX")
+ns="ns-$sfx"
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+zones=20000
+have_ct_tool=0
+ret=0
+
+cleanup()
+{
+	ip netns del $ns
+}
+
+ip netns add $ns
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not create net namespace $gw"
+	exit $ksft_skip
+fi
+
+trap cleanup EXIT
+
+conntrack -V > /dev/null 2>&1
+if [ $? -eq 0 ];then
+	have_ct_tool=1
+fi
+
+ip -net "$ns" link set lo up
+
+test_zones() {
+	local max_zones=$1
+
+ip netns exec $ns sysctl -q net.netfilter.nf_conntrack_udp_timeout=3600
+ip netns exec $ns nft -f /dev/stdin<<EOF
+flush ruleset
+table inet raw {
+	map rndzone {
+		typeof numgen inc mod $max_zones : ct zone
+	}
+
+	chain output {
+		type filter hook output priority -64000; policy accept;
+		udp dport 12345  ct zone set numgen inc mod 65536 map @rndzone
+	}
+}
+EOF
+	(
+		echo "add element inet raw rndzone {"
+	for i in $(seq 1 $max_zones);do
+		echo -n "$i : $i"
+		if [ $i -lt $max_zones ]; then
+			echo ","
+		else
+			echo "}"
+		fi
+	done
+	) | ip netns exec $ns nft -f /dev/stdin
+
+	local i=0
+	local j=0
+	local outerstart=$(date +%s%3N)
+	local stop=$outerstart
+
+	while [ $i -lt $max_zones ]; do
+		local start=$(date +%s%3N)
+		i=$((i + 10000))
+		j=$((j + 1))
+		dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" nc -w 1 -q 1 -u -p 12345 127.0.0.1 12345 > /dev/null
+		if [ $? -ne 0 ] ;then
+			ret=1
+			break
+		fi
+
+		stop=$(date +%s%3N)
+		local duration=$((stop-start))
+		echo "PASS: added 10000 entries in $duration ms (now $i total, loop $j)"
+	done
+
+	if [ $have_ct_tool -eq 1 ]; then
+		local count=$(ip netns exec "$ns" conntrack -C)
+		local duration=$((stop-outerstart))
+
+		if [ $count -eq $max_zones ]; then
+			echo "PASS: inserted $count entries from packet path in $duration ms total"
+		else
+			ip netns exec $ns conntrack -S 1>&2
+			echo "FAIL: inserted $count entries from packet path in $duration ms total, expected $max_zones entries"
+			ret=1
+		fi
+	fi
+
+	if [ $ret -ne 0 ];then
+		echo "FAIL: insert $max_zones entries from packet path" 1>&2
+	fi
+}
+
+test_conntrack_tool() {
+	local max_zones=$1
+
+	ip netns exec $ns conntrack -F >/dev/null 2>/dev/null
+
+	local outerstart=$(date +%s%3N)
+	local start=$(date +%s%3N)
+	local stop=$start
+	local i=0
+	while [ $i -lt $max_zones ]; do
+		i=$((i + 1))
+		ip netns exec "$ns" conntrack -I -s 1.1.1.1 -d 2.2.2.2 --protonum 6 \
+	                 --timeout 3600 --state ESTABLISHED --sport 12345 --dport 1000 --zone $i >/dev/null 2>&1
+		if [ $? -ne 0 ];then
+			ip netns exec "$ns" conntrack -I -s 1.1.1.1 -d 2.2.2.2 --protonum 6 \
+	                 --timeout 3600 --state ESTABLISHED --sport 12345 --dport 1000 --zone $i > /dev/null
+			echo "FAIL: conntrack -I returned an error"
+			ret=1
+			break
+		fi
+
+		if [ $((i%10000)) -eq 0 ];then
+			stop=$(date +%s%3N)
+
+			local duration=$((stop-start))
+			echo "PASS: added 10000 entries in $duration ms (now $i total)"
+			start=$stop
+		fi
+	done
+
+	local count=$(ip netns exec "$ns" conntrack -C)
+	local duration=$((stop-outerstart))
+
+	if [ $count -eq $max_zones ]; then
+		echo "PASS: inserted $count entries via ctnetlink in $duration ms"
+	else
+		ip netns exec $ns conntrack -S 1>&2
+		echo "FAIL: inserted $count entries via ctnetlink in $duration ms, expected $max_zones entries ($duration ms)"
+		ret=1
+	fi
+}
+
+test_zones $zones
+
+if [ $have_ct_tool -eq 1 ];then
+	test_conntrack_tool $zones
+else
+	echo "SKIP: Could not run ctnetlink insertion test without conntrack tool"
+	if [ $ret -eq 0 ];then
+		exit $ksft_skip
+	fi
+fi
+
+exit $ret
diff --git a/tools/testing/selftests/powerpc/tm/tm-syscall-asm.S b/tools/testing/selftests/powerpc/tm/tm-syscall-asm.S
index bd1ca25febe4..aed632d29fff 100644
--- a/tools/testing/selftests/powerpc/tm/tm-syscall-asm.S
+++ b/tools/testing/selftests/powerpc/tm/tm-syscall-asm.S
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#include <ppc-asm.h>
+#include <basic_asm.h>
 #include <asm/unistd.h>
 
 	.text
@@ -26,3 +26,38 @@ FUNC_START(getppid_tm_suspended)
 1:
 	li	r3, -1
 	blr
+
+
+.macro scv level
+	.long (0x44000001 | (\level) << 5)
+.endm
+
+FUNC_START(getppid_scv_tm_active)
+	PUSH_BASIC_STACK(0)
+	tbegin.
+	beq 1f
+	li	r0, __NR_getppid
+	scv	0
+	tend.
+	POP_BASIC_STACK(0)
+	blr
+1:
+	li	r3, -1
+	POP_BASIC_STACK(0)
+	blr
+
+FUNC_START(getppid_scv_tm_suspended)
+	PUSH_BASIC_STACK(0)
+	tbegin.
+	beq 1f
+	li	r0, __NR_getppid
+	tsuspend.
+	scv	0
+	tresume.
+	tend.
+	POP_BASIC_STACK(0)
+	blr
+1:
+	li	r3, -1
+	POP_BASIC_STACK(0)
+	blr
diff --git a/tools/testing/selftests/powerpc/tm/tm-syscall.c b/tools/testing/selftests/powerpc/tm/tm-syscall.c
index 467a6b3134b2..b763354c2eb4 100644
--- a/tools/testing/selftests/powerpc/tm/tm-syscall.c
+++ b/tools/testing/selftests/powerpc/tm/tm-syscall.c
@@ -19,23 +19,36 @@
 #include "utils.h"
 #include "tm.h"
 
+#ifndef PPC_FEATURE2_SCV
+#define PPC_FEATURE2_SCV               0x00100000 /* scv syscall */
+#endif
+
 extern int getppid_tm_active(void);
 extern int getppid_tm_suspended(void);
+extern int getppid_scv_tm_active(void);
+extern int getppid_scv_tm_suspended(void);
 
 unsigned retries = 0;
 
 #define TEST_DURATION 10 /* seconds */
 
-pid_t getppid_tm(bool suspend)
+pid_t getppid_tm(bool scv, bool suspend)
 {
 	int i;
 	pid_t pid;
 
 	for (i = 0; i < TM_RETRIES; i++) {
-		if (suspend)
-			pid = getppid_tm_suspended();
-		else
-			pid = getppid_tm_active();
+		if (suspend) {
+			if (scv)
+				pid = getppid_scv_tm_suspended();
+			else
+				pid = getppid_tm_suspended();
+		} else {
+			if (scv)
+				pid = getppid_scv_tm_active();
+			else
+				pid = getppid_tm_active();
+		}
 
 		if (pid >= 0)
 			return pid;
@@ -82,15 +95,24 @@ int tm_syscall(void)
 		 * Test a syscall within a suspended transaction and verify
 		 * that it succeeds.
 		 */
-		FAIL_IF(getppid_tm(true) == -1); /* Should succeed. */
+		FAIL_IF(getppid_tm(false, true) == -1); /* Should succeed. */
 
 		/*
 		 * Test a syscall within an active transaction and verify that
 		 * it fails with the correct failure code.
 		 */
-		FAIL_IF(getppid_tm(false) != -1);  /* Should fail... */
+		FAIL_IF(getppid_tm(false, false) != -1);  /* Should fail... */
 		FAIL_IF(!failure_is_persistent()); /* ...persistently... */
 		FAIL_IF(!failure_is_syscall());    /* ...with code syscall. */
+
+		/* Now do it all again with scv if it is available. */
+		if (have_hwcap2(PPC_FEATURE2_SCV)) {
+			FAIL_IF(getppid_tm(true, true) == -1); /* Should succeed. */
+			FAIL_IF(getppid_tm(true, false) != -1);  /* Should fail... */
+			FAIL_IF(!failure_is_persistent()); /* ...persistently... */
+			FAIL_IF(!failure_is_syscall());    /* ...with code syscall. */
+		}
+
 		gettimeofday(&now, 0);
 	}
 
diff --git a/tools/usb/testusb.c b/tools/usb/testusb.c
index ee8208b2f946..69c3ead25313 100644
--- a/tools/usb/testusb.c
+++ b/tools/usb/testusb.c
@@ -265,12 +265,6 @@ nomem:
 	}
 
 	entry->ifnum = ifnum;
-
-	/* FIXME update USBDEVFS_CONNECTINFO so it tells about high speed etc */
-
-	fprintf(stderr, "%s speed\t%s\t%u\n",
-		speed(entry->speed), entry->name, entry->ifnum);
-
 	entry->next = testdevs;
 	testdevs = entry;
 	return 0;
@@ -299,6 +293,14 @@ static void *handle_testdev (void *arg)
 		return 0;
 	}
 
+	status  =  ioctl(fd, USBDEVFS_GET_SPEED, NULL);
+	if (status < 0)
+		fprintf(stderr, "USBDEVFS_GET_SPEED failed %d\n", status);
+	else
+		dev->speed = status;
+	fprintf(stderr, "%s speed\t%s\t%u\n",
+			speed(dev->speed), dev->name, dev->ifnum);
+
 restart:
 	for (i = 0; i < TEST_CASES; i++) {
 		if (dev->test != -1 && dev->test != i)
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index 0517c744b04e..f62f10c988db 100644
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -1331,7 +1331,7 @@ int main(int argc, char *argv[])
 	if (opt_list && opt_list_mapcnt)
 		kpagecount_fd = checked_open(PROC_KPAGECOUNT, O_RDONLY);
 
-	if (opt_mark_idle && opt_file)
+	if (opt_mark_idle)
 		page_idle_fd = checked_open(SYS_KERNEL_MM_PAGE_IDLE, O_RDWR);
 
 	if (opt_list && opt_pid)