Merge 5.18-rc5 into driver-core-next

We need the kernfs/driver core fixes in here as well.

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

56 files changed, 907 insertions, 359 deletions

diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 0eb90d21049e..ee15311b6be1 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -128,9 +128,9 @@
 #define TSX_CTRL_RTM_DISABLE		BIT(0)	/* Disable RTM feature */
 #define TSX_CTRL_CPUID_CLEAR		BIT(1)	/* Disable TSX enumeration */
 
-/* SRBDS support */
 #define MSR_IA32_MCU_OPT_CTRL		0x00000123
-#define RNGDS_MITG_DIS			BIT(0)
+#define RNGDS_MITG_DIS			BIT(0)	/* SRBDS support */
+#define RTM_ALLOW			BIT(1)	/* TSX development mode */
 
 #define MSR_IA32_SYSENTER_CS		0x00000174
 #define MSR_IA32_SYSENTER_ESP		0x00000175
diff --git a/tools/include/linux/slab.h b/tools/include/linux/slab.h
index f41d8a0eb1a4..0616409513eb 100644
--- a/tools/include/linux/slab.h
+++ b/tools/include/linux/slab.h
@@ -28,7 +28,13 @@ static inline void *kzalloc(size_t size, gfp_t gfp)
 	return kmalloc(size, gfp | __GFP_ZERO);
 }
 
-void *kmem_cache_alloc(struct kmem_cache *cachep, int flags);
+struct list_lru;
+
+void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *, int flags);
+static inline void *kmem_cache_alloc(struct kmem_cache *cachep, int flags)
+{
+	return kmem_cache_alloc_lru(cachep, NULL, flags);
+}
 void kmem_cache_free(struct kmem_cache *cachep, void *objp);
 
 struct kmem_cache *kmem_cache_create(const char *name, unsigned int size,
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 1b15ba13c477..a09315538a30 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -577,7 +577,6 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 {
 	struct perf_evsel *evsel;
 	const struct perf_cpu_map *cpus = evlist->user_requested_cpus;
-	const struct perf_thread_map *threads = evlist->threads;
 
 	if (!ops || !ops->get || !ops->mmap)
 		return -EINVAL;
@@ -589,7 +588,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 	perf_evlist__for_each_entry(evlist, evsel) {
 		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
 		    evsel->sample_id == NULL &&
-		    perf_evsel__alloc_id(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0)
+		    perf_evsel__alloc_id(evsel, evsel->fd->max_x, evsel->fd->max_y) < 0)
 			return -ENOMEM;
 	}
 
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index bd0c2c828940..ca5b74603008 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -184,6 +184,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func,
 		"do_group_exit",
 		"stop_this_cpu",
 		"__invalid_creds",
+               "cpu_startup_entry",
 	};
 
 	if (!func)
@@ -559,12 +560,12 @@ static int add_dead_ends(struct objtool_file *file)
 		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",
+				WARN("can't find unreachable insn at %s+0x%lx",
 				     reloc->sym->sec->name, reloc->addend);
 				return -1;
 			}
 		} else {
-			WARN("can't find unreachable insn at %s+0x%x",
+			WARN("can't find unreachable insn at %s+0x%lx",
 			     reloc->sym->sec->name, reloc->addend);
 			return -1;
 		}
@@ -594,12 +595,12 @@ reachable:
 		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",
+				WARN("can't find reachable insn at %s+0x%lx",
 				     reloc->sym->sec->name, reloc->addend);
 				return -1;
 			}
 		} else {
-			WARN("can't find reachable insn at %s+0x%x",
+			WARN("can't find reachable insn at %s+0x%lx",
 			     reloc->sym->sec->name, reloc->addend);
 			return -1;
 		}
@@ -1271,12 +1272,19 @@ static bool is_first_func_insn(struct objtool_file *file, struct instruction *in
  */
 static int add_jump_destinations(struct objtool_file *file)
 {
-	struct instruction *insn;
+	struct instruction *insn, *jump_dest;
 	struct reloc *reloc;
 	struct section *dest_sec;
 	unsigned long dest_off;
 
 	for_each_insn(file, insn) {
+		if (insn->jump_dest) {
+			/*
+			 * handle_group_alt() may have previously set
+			 * 'jump_dest' for some alternatives.
+			 */
+			continue;
+		}
 		if (!is_static_jump(insn))
 			continue;
 
@@ -1291,7 +1299,10 @@ static int add_jump_destinations(struct objtool_file *file)
 			add_retpoline_call(file, insn);
 			continue;
 		} else if (insn->func) {
-			/* internal or external sibling call (with reloc) */
+			/*
+			 * External sibling call or internal sibling call with
+			 * STT_FUNC reloc.
+			 */
 			add_call_dest(file, insn, reloc->sym, true);
 			continue;
 		} else if (reloc->sym->sec->idx) {
@@ -1303,17 +1314,8 @@ static int add_jump_destinations(struct objtool_file *file)
 			continue;
 		}
 
-		insn->jump_dest = find_insn(file, dest_sec, dest_off);
-		if (!insn->jump_dest) {
-
-			/*
-			 * This is a special case where an alt instruction
-			 * jumps past the end of the section.  These are
-			 * handled later in handle_group_alt().
-			 */
-			if (!strcmp(insn->sec->name, ".altinstr_replacement"))
-				continue;
-
+		jump_dest = find_insn(file, dest_sec, dest_off);
+		if (!jump_dest) {
 			WARN_FUNC("can't find jump dest instruction at %s+0x%lx",
 				  insn->sec, insn->offset, dest_sec->name,
 				  dest_off);
@@ -1323,8 +1325,8 @@ static int add_jump_destinations(struct objtool_file *file)
 		/*
 		 * Cross-function jump.
 		 */
-		if (insn->func && insn->jump_dest->func &&
-		    insn->func != insn->jump_dest->func) {
+		if (insn->func && jump_dest->func &&
+		    insn->func != jump_dest->func) {
 
 			/*
 			 * For GCC 8+, create parent/child links for any cold
@@ -1342,16 +1344,22 @@ static int add_jump_destinations(struct objtool_file *file)
 			 * subfunction is through a jump table.
 			 */
 			if (!strstr(insn->func->name, ".cold") &&
-			    strstr(insn->jump_dest->func->name, ".cold")) {
-				insn->func->cfunc = insn->jump_dest->func;
-				insn->jump_dest->func->pfunc = insn->func;
+			    strstr(jump_dest->func->name, ".cold")) {
+				insn->func->cfunc = jump_dest->func;
+				jump_dest->func->pfunc = insn->func;
 
-			} else if (!same_function(insn, insn->jump_dest) &&
-				   is_first_func_insn(file, insn->jump_dest)) {
-				/* internal sibling call (without reloc) */
-				add_call_dest(file, insn, insn->jump_dest->func, true);
+			} else if (!same_function(insn, jump_dest) &&
+				   is_first_func_insn(file, jump_dest)) {
+				/*
+				 * Internal sibling call without reloc or with
+				 * STT_SECTION reloc.
+				 */
+				add_call_dest(file, insn, jump_dest->func, true);
+				continue;
 			}
 		}
+
+		insn->jump_dest = jump_dest;
 	}
 
 	return 0;
@@ -1540,13 +1548,13 @@ static int handle_group_alt(struct objtool_file *file,
 			continue;
 
 		dest_off = arch_jump_destination(insn);
-		if (dest_off == special_alt->new_off + special_alt->new_len)
+		if (dest_off == special_alt->new_off + special_alt->new_len) {
 			insn->jump_dest = next_insn_same_sec(file, last_orig_insn);
-
-		if (!insn->jump_dest) {
-			WARN_FUNC("can't find alternative jump destination",
-				  insn->sec, insn->offset);
-			return -1;
+			if (!insn->jump_dest) {
+				WARN_FUNC("can't find alternative jump destination",
+					  insn->sec, insn->offset);
+				return -1;
+			}
 		}
 	}
 
@@ -2245,14 +2253,14 @@ static int decode_sections(struct objtool_file *file)
 		return ret;
 
 	/*
-	 * Must be before add_special_section_alts() as that depends on
-	 * jump_dest being set.
+	 * Must be before add_jump_destinations(), which depends on 'func'
+	 * being set for alternatives, to enable proper sibling call detection.
 	 */
-	ret = add_jump_destinations(file);
+	ret = add_special_section_alts(file);
 	if (ret)
 		return ret;
 
-	ret = add_special_section_alts(file);
+	ret = add_jump_destinations(file);
 	if (ret)
 		return ret;
 
@@ -3210,9 +3218,8 @@ validate_ibt_reloc(struct objtool_file *file, struct reloc *reloc)
 static void warn_noendbr(const char *msg, struct section *sec, unsigned long offset,
 			 struct instruction *dest)
 {
-	WARN_FUNC("%srelocation to !ENDBR: %s+0x%lx", sec, offset, msg,
-		  dest->func ? dest->func->name : dest->sec->name,
-		  dest->func ? dest->offset - dest->func->offset : dest->offset);
+	WARN_FUNC("%srelocation to !ENDBR: %s", sec, offset, msg,
+		  offstr(dest->sec, dest->offset));
 }
 
 static void validate_ibt_dest(struct objtool_file *file, struct instruction *insn,
@@ -3303,7 +3310,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 	while (1) {
 		next_insn = next_insn_to_validate(file, insn);
 
-		if (file->c_file && func && insn->func && func != insn->func->pfunc) {
+		if (func && insn->func && func != insn->func->pfunc) {
 			WARN("%s() falls through to next function %s()",
 			     func->name, insn->func->name);
 			return 1;
@@ -3816,11 +3823,8 @@ static int validate_ibt(struct objtool_file *file)
 			struct instruction *dest;
 
 			dest = validate_ibt_reloc(file, reloc);
-			if (is_data && dest && !dest->noendbr) {
-				warn_noendbr("data ", reloc->sym->sec,
-					     reloc->sym->offset + reloc->addend,
-					     dest);
-			}
+			if (is_data && dest && !dest->noendbr)
+				warn_noendbr("data ", sec, reloc->offset, dest);
 		}
 	}
 
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index d7b99a737496..ebf2ba5755c1 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -546,7 +546,7 @@ static struct section *elf_create_reloc_section(struct elf *elf,
 						int reltype);
 
 int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset,
-		  unsigned int type, struct symbol *sym, int addend)
+		  unsigned int type, struct symbol *sym, long addend)
 {
 	struct reloc *reloc;
 
@@ -575,37 +575,180 @@ int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset,
 	return 0;
 }
 
-int elf_add_reloc_to_insn(struct elf *elf, struct section *sec,
-			  unsigned long offset, unsigned int type,
-			  struct section *insn_sec, unsigned long insn_off)
+/*
+ * Ensure that any reloc section containing references to @sym is marked
+ * changed such that it will get re-generated in elf_rebuild_reloc_sections()
+ * with the new symbol index.
+ */
+static void elf_dirty_reloc_sym(struct elf *elf, struct symbol *sym)
+{
+	struct section *sec;
+
+	list_for_each_entry(sec, &elf->sections, list) {
+		struct reloc *reloc;
+
+		if (sec->changed)
+			continue;
+
+		list_for_each_entry(reloc, &sec->reloc_list, list) {
+			if (reloc->sym == sym) {
+				sec->changed = true;
+				break;
+			}
+		}
+	}
+}
+
+/*
+ * Move the first global symbol, as per sh_info, into a new, higher symbol
+ * index. This fees up the shndx for a new local symbol.
+ */
+static int elf_move_global_symbol(struct elf *elf, struct section *symtab,
+				  struct section *symtab_shndx)
 {
+	Elf_Data *data, *shndx_data = NULL;
+	Elf32_Word first_non_local;
 	struct symbol *sym;
-	int addend;
+	Elf_Scn *s;
 
-	if (insn_sec->sym) {
-		sym = insn_sec->sym;
-		addend = insn_off;
+	first_non_local = symtab->sh.sh_info;
 
-	} else {
-		/*
-		 * The Clang assembler strips section symbols, so we have to
-		 * reference the function symbol instead:
-		 */
-		sym = find_symbol_containing(insn_sec, insn_off);
-		if (!sym) {
-			/*
-			 * Hack alert.  This happens when we need to reference
-			 * the NOP pad insn immediately after the function.
-			 */
-			sym = find_symbol_containing(insn_sec, insn_off - 1);
+	sym = find_symbol_by_index(elf, first_non_local);
+	if (!sym) {
+		WARN("no non-local symbols !?");
+		return first_non_local;
+	}
+
+	s = elf_getscn(elf->elf, symtab->idx);
+	if (!s) {
+		WARN_ELF("elf_getscn");
+		return -1;
+	}
+
+	data = elf_newdata(s);
+	if (!data) {
+		WARN_ELF("elf_newdata");
+		return -1;
+	}
+
+	data->d_buf = &sym->sym;
+	data->d_size = sizeof(sym->sym);
+	data->d_align = 1;
+	data->d_type = ELF_T_SYM;
+
+	sym->idx = symtab->sh.sh_size / sizeof(sym->sym);
+	elf_dirty_reloc_sym(elf, sym);
+
+	symtab->sh.sh_info += 1;
+	symtab->sh.sh_size += data->d_size;
+	symtab->changed = true;
+
+	if (symtab_shndx) {
+		s = elf_getscn(elf->elf, symtab_shndx->idx);
+		if (!s) {
+			WARN_ELF("elf_getscn");
+			return -1;
 		}
 
-		if (!sym) {
-			WARN("can't find symbol containing %s+0x%lx", insn_sec->name, insn_off);
+		shndx_data = elf_newdata(s);
+		if (!shndx_data) {
+			WARN_ELF("elf_newshndx_data");
 			return -1;
 		}
 
-		addend = insn_off - sym->offset;
+		shndx_data->d_buf = &sym->sec->idx;
+		shndx_data->d_size = sizeof(Elf32_Word);
+		shndx_data->d_align = 4;
+		shndx_data->d_type = ELF_T_WORD;
+
+		symtab_shndx->sh.sh_size += 4;
+		symtab_shndx->changed = true;
+	}
+
+	return first_non_local;
+}
+
+static struct symbol *
+elf_create_section_symbol(struct elf *elf, struct section *sec)
+{
+	struct section *symtab, *symtab_shndx;
+	Elf_Data *shndx_data = NULL;
+	struct symbol *sym;
+	Elf32_Word shndx;
+
+	symtab = find_section_by_name(elf, ".symtab");
+	if (symtab) {
+		symtab_shndx = find_section_by_name(elf, ".symtab_shndx");
+		if (symtab_shndx)
+			shndx_data = symtab_shndx->data;
+	} else {
+		WARN("no .symtab");
+		return NULL;
+	}
+
+	sym = malloc(sizeof(*sym));
+	if (!sym) {
+		perror("malloc");
+		return NULL;
+	}
+	memset(sym, 0, sizeof(*sym));
+
+	sym->idx = elf_move_global_symbol(elf, symtab, symtab_shndx);
+	if (sym->idx < 0) {
+		WARN("elf_move_global_symbol");
+		return NULL;
+	}
+
+	sym->name = sec->name;
+	sym->sec = sec;
+
+	// st_name 0
+	sym->sym.st_info = GELF_ST_INFO(STB_LOCAL, STT_SECTION);
+	// st_other 0
+	// st_value 0
+	// st_size 0
+	shndx = sec->idx;
+	if (shndx >= SHN_UNDEF && shndx < SHN_LORESERVE) {
+		sym->sym.st_shndx = shndx;
+		if (!shndx_data)
+			shndx = 0;
+	} else {
+		sym->sym.st_shndx = SHN_XINDEX;
+		if (!shndx_data) {
+			WARN("no .symtab_shndx");
+			return NULL;
+		}
+	}
+
+	if (!gelf_update_symshndx(symtab->data, shndx_data, sym->idx, &sym->sym, shndx)) {
+		WARN_ELF("gelf_update_symshndx");
+		return NULL;
+	}
+
+	elf_add_symbol(elf, sym);
+
+	return sym;
+}
+
+int elf_add_reloc_to_insn(struct elf *elf, struct section *sec,
+			  unsigned long offset, unsigned int type,
+			  struct section *insn_sec, unsigned long insn_off)
+{
+	struct symbol *sym = insn_sec->sym;
+	int addend = insn_off;
+
+	if (!sym) {
+		/*
+		 * Due to how weak functions work, we must use section based
+		 * relocations. Symbol based relocations would result in the
+		 * weak and non-weak function annotations being overlaid on the
+		 * non-weak function after linking.
+		 */
+		sym = elf_create_section_symbol(elf, insn_sec);
+		if (!sym)
+			return -1;
+
+		insn_sec->sym = sym;
 	}
 
 	return elf_add_reloc(elf, sec, offset, type, sym, addend);
diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h
index 22ba7e2b816e..9b36802ed86f 100644
--- a/tools/objtool/include/objtool/elf.h
+++ b/tools/objtool/include/objtool/elf.h
@@ -73,7 +73,7 @@ struct reloc {
 	struct symbol *sym;
 	unsigned long offset;
 	unsigned int type;
-	int addend;
+	long addend;
 	int idx;
 	bool jump_table_start;
 };
@@ -135,7 +135,7 @@ struct elf *elf_open_read(const char *name, int flags);
 struct section *elf_create_section(struct elf *elf, const char *name, unsigned int sh_flags, size_t entsize, int nr);
 
 int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset,
-		  unsigned int type, struct symbol *sym, int addend);
+		  unsigned int type, struct symbol *sym, long addend);
 int elf_add_reloc_to_insn(struct elf *elf, struct section *sec,
 			  unsigned long offset, unsigned int type,
 			  struct section *insn_sec, unsigned long insn_off);
diff --git a/tools/objtool/include/objtool/objtool.h b/tools/objtool/include/objtool/objtool.h
index 7a5c13a78f87..a6e72d916807 100644
--- a/tools/objtool/include/objtool/objtool.h
+++ b/tools/objtool/include/objtool/objtool.h
@@ -27,7 +27,7 @@ struct objtool_file {
 	struct list_head static_call_list;
 	struct list_head mcount_loc_list;
 	struct list_head endbr_list;
-	bool ignore_unreachables, c_file, hints, rodata;
+	bool ignore_unreachables, hints, rodata;
 
 	unsigned int nr_endbr;
 	unsigned int nr_endbr_int;
diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c
index b09946f4e1d6..843ff3c2f28e 100644
--- a/tools/objtool/objtool.c
+++ b/tools/objtool/objtool.c
@@ -129,7 +129,6 @@ struct objtool_file *objtool_open_read(const char *_objname)
 	INIT_LIST_HEAD(&file.static_call_list);
 	INIT_LIST_HEAD(&file.mcount_loc_list);
 	INIT_LIST_HEAD(&file.endbr_list);
-	file.c_file = !vmlinux && find_section_by_name(file.elf, ".comment");
 	file.ignore_unreachables = no_unreachable;
 	file.hints = false;
 
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index af4d63af8072..e8b577d33e53 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -148,6 +148,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	bool privileged = perf_event_paranoid_check(-1);
 	struct evsel *tracking_evsel;
 	int err;
+	u64 bit;
 
 	sper->evlist = evlist;
 
@@ -245,6 +246,15 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	 */
 	evsel__set_sample_bit(arm_spe_evsel, DATA_SRC);
 
+	/*
+	 * The PHYS_ADDR flag does not affect the driver behaviour, it is used to
+	 * inform that the resulting output's SPE samples contain physical addresses
+	 * where applicable.
+	 */
+	bit = perf_pmu__format_bits(&arm_spe_pmu->format, "pa_enable");
+	if (arm_spe_evsel->core.attr.config & bit)
+		evsel__set_sample_bit(arm_spe_evsel, PHYS_ADDR);
+
 	/* Add dummy event to keep tracking */
 	err = parse_events(evlist, "dummy:u", NULL);
 	if (err)
diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c
index d2ce31e28cd7..41c1596e5207 100644
--- a/tools/perf/arch/arm64/util/machine.c
+++ b/tools/perf/arch/arm64/util/machine.c
@@ -8,27 +8,6 @@
 #include "callchain.h"
 #include "record.h"
 
-/* On arm64, kernel text segment starts at high memory address,
- * for example 0xffff 0000 8xxx xxxx. Modules start at a low memory
- * address, like 0xffff 0000 00ax xxxx. When only small amount of
- * memory is used by modules, gap between end of module's text segment
- * and start of kernel text segment may reach 2G.
- * Therefore do not fill this gap and do not assign it to the kernel dso map.
- */
-
-#define SYMBOL_LIMIT (1 << 12) /* 4K */
-
-void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
-{
-	if ((strchr(p->name, '[') && strchr(c->name, '[') == NULL) ||
-			(strchr(p->name, '[') == NULL && strchr(c->name, '[')))
-		/* Limit range of last symbol in module and kernel */
-		p->end += SYMBOL_LIMIT;
-	else
-		p->end = c->start;
-	pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end);
-}
-
 void arch__add_leaf_frame_record_opts(struct record_opts *opts)
 {
 	opts->sample_user_regs |= sample_reg_masks[PERF_REG_ARM64_LR].mask;
diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
index 8a79c4126e5b..0115f3166568 100644
--- a/tools/perf/arch/powerpc/util/Build
+++ b/tools/perf/arch/powerpc/util/Build
@@ -1,5 +1,4 @@
 perf-y += header.o
-perf-y += machine.o
 perf-y += kvm-stat.o
 perf-y += perf_regs.o
 perf-y += mem-events.o
diff --git a/tools/perf/arch/powerpc/util/machine.c b/tools/perf/arch/powerpc/util/machine.c
deleted file mode 100644
index e652a1aa8132..000000000000
--- a/tools/perf/arch/powerpc/util/machine.c
+++ /dev/null
@@ -1,25 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <string.h>
-#include <internal/lib.h> // page_size
-#include "debug.h"
-#include "symbol.h"
-
-/* On powerpc kernel text segment start at memory addresses, 0xc000000000000000
- * whereas the modules are located at very high memory addresses,
- * for example 0xc00800000xxxxxxx. The gap between end of kernel text segment
- * and beginning of first module's text segment is very high.
- * Therefore do not fill this gap and do not assign it to the kernel dso map.
- */
-
-void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
-{
-	if (strchr(p->name, '[') == NULL && strchr(c->name, '['))
-		/* Limit the range of last kernel symbol */
-		p->end += page_size;
-	else
-		p->end = c->start;
-	pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end);
-}
diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c
index 7644a4f6d4a4..98bc3f39d5f3 100644
--- a/tools/perf/arch/s390/util/machine.c
+++ b/tools/perf/arch/s390/util/machine.c
@@ -35,19 +35,3 @@ int arch__fix_module_text_start(u64 *start, u64 *size, const char *name)
 
 	return 0;
 }
-
-/* On s390 kernel text segment start is located at very low memory addresses,
- * for example 0x10000. Modules are located at very high memory addresses,
- * for example 0x3ff xxxx xxxx. The gap between end of kernel text segment
- * and beginning of first module's text segment is very big.
- * Therefore do not fill this gap and do not assign it to the kernel dso map.
- */
-void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
-{
-	if (strchr(p->name, '[') == NULL && strchr(c->name, '['))
-		/* Last kernel symbol mapped to end of page */
-		p->end = roundup(p->end, page_size);
-	else
-		p->end = c->start;
-	pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end);
-}
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index f2640179ada9..44e1f8a44087 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -34,6 +34,7 @@
 #include <linux/numa.h>
 #include <linux/zalloc.h>
 
+#include "../util/header.h"
 #include <numa.h>
 #include <numaif.h>
 
@@ -54,7 +55,7 @@
 
 struct thread_data {
 	int			curr_cpu;
-	cpu_set_t		bind_cpumask;
+	cpu_set_t		*bind_cpumask;
 	int			bind_node;
 	u8			*process_data;
 	int			process_nr;
@@ -266,71 +267,115 @@ static bool node_has_cpus(int node)
 	return ret;
 }
 
-static cpu_set_t bind_to_cpu(int target_cpu)
+static cpu_set_t *bind_to_cpu(int target_cpu)
 {
-	cpu_set_t orig_mask, mask;
-	int ret;
+	int nrcpus = numa_num_possible_cpus();
+	cpu_set_t *orig_mask, *mask;
+	size_t size;
 
-	ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
-	BUG_ON(ret);
+	orig_mask = CPU_ALLOC(nrcpus);
+	BUG_ON(!orig_mask);
+	size = CPU_ALLOC_SIZE(nrcpus);
+	CPU_ZERO_S(size, orig_mask);
+
+	if (sched_getaffinity(0, size, orig_mask))
+		goto err_out;
+
+	mask = CPU_ALLOC(nrcpus);
+	if (!mask)
+		goto err_out;
 
-	CPU_ZERO(&mask);
+	CPU_ZERO_S(size, mask);
 
 	if (target_cpu == -1) {
 		int cpu;
 
 		for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
-			CPU_SET(cpu, &mask);
+			CPU_SET_S(cpu, size, mask);
 	} else {
-		BUG_ON(target_cpu < 0 || target_cpu >= g->p.nr_cpus);
-		CPU_SET(target_cpu, &mask);
+		if (target_cpu < 0 || target_cpu >= g->p.nr_cpus)
+			goto err;
+
+		CPU_SET_S(target_cpu, size, mask);
 	}
 
-	ret = sched_setaffinity(0, sizeof(mask), &mask);
-	BUG_ON(ret);
+	if (sched_setaffinity(0, size, mask))
+		goto err;
 
 	return orig_mask;
+
+err:
+	CPU_FREE(mask);
+err_out:
+	CPU_FREE(orig_mask);
+
+	/* BUG_ON due to failure in allocation of orig_mask/mask */
+	BUG_ON(-1);
 }
 
-static cpu_set_t bind_to_node(int target_node)
+static cpu_set_t *bind_to_node(int target_node)
 {
-	cpu_set_t orig_mask, mask;
+	int nrcpus = numa_num_possible_cpus();
+	size_t size;
+	cpu_set_t *orig_mask, *mask;
 	int cpu;
-	int ret;
 
-	ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
-	BUG_ON(ret);
+	orig_mask = CPU_ALLOC(nrcpus);
+	BUG_ON(!orig_mask);
+	size = CPU_ALLOC_SIZE(nrcpus);
+	CPU_ZERO_S(size, orig_mask);
 
-	CPU_ZERO(&mask);
+	if (sched_getaffinity(0, size, orig_mask))
+		goto err_out;
+
+	mask = CPU_ALLOC(nrcpus);
+	if (!mask)
+		goto err_out;
+
+	CPU_ZERO_S(size, mask);
 
 	if (target_node == NUMA_NO_NODE) {
 		for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
-			CPU_SET(cpu, &mask);
+			CPU_SET_S(cpu, size, mask);
 	} else {
 		struct bitmask *cpumask = numa_allocate_cpumask();
 
-		BUG_ON(!cpumask);
+		if (!cpumask)
+			goto err;
+
 		if (!numa_node_to_cpus(target_node, cpumask)) {
 			for (cpu = 0; cpu < (int)cpumask->size; cpu++) {
 				if (numa_bitmask_isbitset(cpumask, cpu))
-					CPU_SET(cpu, &mask);
+					CPU_SET_S(cpu, size, mask);
 			}
 		}
 		numa_free_cpumask(cpumask);
 	}
 
-	ret = sched_setaffinity(0, sizeof(mask), &mask);
-	BUG_ON(ret);
+	if (sched_setaffinity(0, size, mask))
+		goto err;
 
 	return orig_mask;
+
+err:
+	CPU_FREE(mask);
+err_out:
+	CPU_FREE(orig_mask);
+
+	/* BUG_ON due to failure in allocation of orig_mask/mask */
+	BUG_ON(-1);
 }
 
-static void bind_to_cpumask(cpu_set_t mask)
+static void bind_to_cpumask(cpu_set_t *mask)
 {
 	int ret;
+	size_t size = CPU_ALLOC_SIZE(numa_num_possible_cpus());
 
-	ret = sched_setaffinity(0, sizeof(mask), &mask);
-	BUG_ON(ret);
+	ret = sched_setaffinity(0, size, mask);
+	if (ret) {
+		CPU_FREE(mask);
+		BUG_ON(ret);
+	}
 }
 
 static void mempol_restore(void)
@@ -376,7 +421,7 @@ do {							\
 static u8 *alloc_data(ssize_t bytes0, int map_flags,
 		      int init_zero, int init_cpu0, int thp, int init_random)
 {
-	cpu_set_t orig_mask;
+	cpu_set_t *orig_mask = NULL;
 	ssize_t bytes;
 	u8 *buf;
 	int ret;
@@ -434,6 +479,7 @@ static u8 *alloc_data(ssize_t bytes0, int map_flags,
 	/* Restore affinity: */
 	if (init_cpu0) {
 		bind_to_cpumask(orig_mask);
+		CPU_FREE(orig_mask);
 		mempol_restore();
 	}
 
@@ -585,10 +631,16 @@ static int parse_setup_cpu_list(void)
 			return -1;
 		}
 
+		if (is_cpu_online(bind_cpu_0) != 1 || is_cpu_online(bind_cpu_1) != 1) {
+			printf("\nTest not applicable, bind_cpu_0 or bind_cpu_1 is offline\n");
+			return -1;
+		}
+
 		BUG_ON(bind_cpu_0 < 0 || bind_cpu_1 < 0);
 		BUG_ON(bind_cpu_0 > bind_cpu_1);
 
 		for (bind_cpu = bind_cpu_0; bind_cpu <= bind_cpu_1; bind_cpu += step) {
+			size_t size = CPU_ALLOC_SIZE(g->p.nr_cpus);
 			int i;
 
 			for (i = 0; i < mul; i++) {
@@ -608,10 +660,15 @@ static int parse_setup_cpu_list(void)
 					tprintf("%2d", bind_cpu);
 				}
 
-				CPU_ZERO(&td->bind_cpumask);
+				td->bind_cpumask = CPU_ALLOC(g->p.nr_cpus);
+				BUG_ON(!td->bind_cpumask);
+				CPU_ZERO_S(size, td->bind_cpumask);
 				for (cpu = bind_cpu; cpu < bind_cpu+bind_len; cpu++) {
-					BUG_ON(cpu < 0 || cpu >= g->p.nr_cpus);
-					CPU_SET(cpu, &td->bind_cpumask);
+					if (cpu < 0 || cpu >= g->p.nr_cpus) {
+						CPU_FREE(td->bind_cpumask);
+						BUG_ON(-1);
+					}
+					CPU_SET_S(cpu, size, td->bind_cpumask);
 				}
 				t++;
 			}
@@ -752,8 +809,6 @@ static int parse_nodes_opt(const struct option *opt __maybe_unused,
 	return parse_node_list(arg);
 }
 
-#define BIT(x) (1ul << x)
-
 static inline uint32_t lfsr_32(uint32_t lfsr)
 {
 	const uint32_t taps = BIT(1) | BIT(5) | BIT(6) | BIT(31);
@@ -1241,7 +1296,7 @@ static void *worker_thread(void *__tdata)
 		 * by migrating to CPU#0:
 		 */
 		if (first_task && g->p.perturb_secs && (int)(stop.tv_sec - last_perturbance) >= g->p.perturb_secs) {
-			cpu_set_t orig_mask;
+			cpu_set_t *orig_mask;
 			int target_cpu;
 			int this_cpu;
 
@@ -1265,6 +1320,7 @@ static void *worker_thread(void *__tdata)
 				printf(" (injecting perturbalance, moved to CPU#%d)\n", target_cpu);
 
 			bind_to_cpumask(orig_mask);
+			CPU_FREE(orig_mask);
 		}
 
 		if (details >= 3) {
@@ -1398,21 +1454,31 @@ static void init_thread_data(void)
 
 	for (t = 0; t < g->p.nr_tasks; t++) {
 		struct thread_data *td = g->threads + t;
+		size_t cpuset_size = CPU_ALLOC_SIZE(g->p.nr_cpus);
 		int cpu;
 
 		/* Allow all nodes by default: */
 		td->bind_node = NUMA_NO_NODE;
 
 		/* Allow all CPUs by default: */
-		CPU_ZERO(&td->bind_cpumask);
+		td->bind_cpumask = CPU_ALLOC(g->p.nr_cpus);
+		BUG_ON(!td->bind_cpumask);
+		CPU_ZERO_S(cpuset_size, td->bind_cpumask);
 		for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
-			CPU_SET(cpu, &td->bind_cpumask);
+			CPU_SET_S(cpu, cpuset_size, td->bind_cpumask);
 	}
 }
 
 static void deinit_thread_data(void)
 {
 	ssize_t size = sizeof(*g->threads)*g->p.nr_tasks;
+	int t;
+
+	/* Free the bind_cpumask allocated for thread_data */
+	for (t = 0; t < g->p.nr_tasks; t++) {
+		struct thread_data *td = g->threads + t;
+		CPU_FREE(td->bind_cpumask);
+	}
 
 	free_data(g->threads, size);
 }
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index ba74fab02e62..069825c48d40 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -989,8 +989,11 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru
 	struct mmap *overwrite_mmap = evlist->overwrite_mmap;
 	struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
 
-	thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits,
-					      thread_data->mask->maps.nbits);
+	if (cpu_map__is_dummy(cpus))
+		thread_data->nr_mmaps = nr_mmaps;
+	else
+		thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits,
+						      thread_data->mask->maps.nbits);
 	if (mmap) {
 		thread_data->maps = zalloc(thread_data->nr_mmaps * sizeof(struct mmap *));
 		if (!thread_data->maps)
@@ -1007,16 +1010,17 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru
 		 thread_data->nr_mmaps, thread_data->maps, thread_data->overwrite_maps);
 
 	for (m = 0, tm = 0; m < nr_mmaps && tm < thread_data->nr_mmaps; m++) {
-		if (test_bit(cpus->map[m].cpu, thread_data->mask->maps.bits)) {
+		if (cpu_map__is_dummy(cpus) ||
+		    test_bit(cpus->map[m].cpu, thread_data->mask->maps.bits)) {
 			if (thread_data->maps) {
 				thread_data->maps[tm] = &mmap[m];
 				pr_debug2("thread_data[%p]: cpu%d: maps[%d] -> mmap[%d]\n",
-					  thread_data, cpus->map[m].cpu, tm, m);
+					  thread_data, perf_cpu_map__cpu(cpus, m).cpu, tm, m);
 			}
 			if (thread_data->overwrite_maps) {
 				thread_data->overwrite_maps[tm] = &overwrite_mmap[m];
 				pr_debug2("thread_data[%p]: cpu%d: ow_maps[%d] -> ow_mmap[%d]\n",
-					  thread_data, cpus->map[m].cpu, tm, m);
+					  thread_data, perf_cpu_map__cpu(cpus, m).cpu, tm, m);
 			}
 			tm++;
 		}
@@ -3329,6 +3333,9 @@ static void record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_c
 {
 	int c;
 
+	if (cpu_map__is_dummy(cpus))
+		return;
+
 	for (c = 0; c < cpus->nr; c++)
 		set_bit(cpus->map[c].cpu, mask->bits);
 }
@@ -3680,6 +3687,11 @@ static int record__init_thread_masks(struct record *rec)
 	if (!record__threads_enabled(rec))
 		return record__init_thread_default_masks(rec, cpus);
 
+	if (cpu_map__is_dummy(cpus)) {
+		pr_err("--per-thread option is mutually exclusive to parallel streaming mode.\n");
+		return -EINVAL;
+	}
+
 	switch (rec->opts.threads_spec) {
 	case THREAD_SPEC__CPU:
 		ret = record__init_thread_cpu_masks(rec, cpus);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 1ad75c7ba074..afe4a5539ecc 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -353,6 +353,7 @@ static int report__setup_sample_type(struct report *rep)
 	struct perf_session *session = rep->session;
 	u64 sample_type = evlist__combined_sample_type(session->evlist);
 	bool is_pipe = perf_data__is_pipe(session->data);
+	struct evsel *evsel;
 
 	if (session->itrace_synth_opts->callchain ||
 	    session->itrace_synth_opts->add_callchain ||
@@ -407,6 +408,19 @@ static int report__setup_sample_type(struct report *rep)
 	}
 
 	if (sort__mode == SORT_MODE__MEMORY) {
+		/*
+		 * FIXUP: prior to kernel 5.18, Arm SPE missed to set
+		 * PERF_SAMPLE_DATA_SRC bit in sample type.  For backward
+		 * compatibility, set the bit if it's an old perf data file.
+		 */
+		evlist__for_each_entry(session->evlist, evsel) {
+			if (strstr(evsel->name, "arm_spe") &&
+				!(sample_type & PERF_SAMPLE_DATA_SRC)) {
+				evsel->core.attr.sample_type |= PERF_SAMPLE_DATA_SRC;
+				sample_type |= PERF_SAMPLE_DATA_SRC;
+			}
+		}
+
 		if (!is_pipe && !(sample_type & PERF_SAMPLE_DATA_SRC)) {
 			ui__error("Selected --mem-mode but no mem data. "
 				  "Did you call perf record without -d?\n");
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index a2f117936188..cf5eab5431b4 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -461,7 +461,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
 		return -EINVAL;
 
 	if (PRINT_FIELD(DATA_SRC) &&
-	    evsel__check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC", PERF_OUTPUT_DATA_SRC))
+	    evsel__do_check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC", PERF_OUTPUT_DATA_SRC, allow_user_set))
 		return -EINVAL;
 
 	if (PRINT_FIELD(WEIGHT) &&
diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README
index 454505d343fa..eb3f7d4bb324 100644
--- a/tools/perf/tests/attr/README
+++ b/tools/perf/tests/attr/README
@@ -60,6 +60,7 @@ Following tests are defined (with perf commands):
   perf record -R kill                           (test-record-raw)
   perf record -c 2 -e arm_spe_0// -- kill       (test-record-spe-period)
   perf record -e arm_spe_0/period=3/ -- kill    (test-record-spe-period-term)
+  perf record -e arm_spe_0/pa_enable=1/ -- kill (test-record-spe-physical-address)
   perf stat -e cycles kill                      (test-stat-basic)
   perf stat kill                                (test-stat-default)
   perf stat -d kill                             (test-stat-detailed-1)
diff --git a/tools/perf/tests/attr/test-record-spe-physical-address b/tools/perf/tests/attr/test-record-spe-physical-address
new file mode 100644
index 000000000000..7ebcf5012ce3
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-spe-physical-address
@@ -0,0 +1,12 @@
+[config]
+command = record
+args    = --no-bpf-event -e arm_spe_0/pa_enable=1/ -- kill >/dev/null 2>&1
+ret     = 1
+arch    = aarch64
+
+[event-10:base-record-spe]
+# 622727 is the decimal of IP|TID|TIME|CPU|IDENTIFIER|DATA_SRC|PHYS_ADDR
+sample_type=622727
+
+# dummy event
+[event-1:base-record-spe]
\ No newline at end of file
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index cc6df49a65a1..4ad0dfbc8b21 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -123,6 +123,10 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su
 		evsel->core.attr.enable_on_exec = 0;
 	}
 
+	if (evlist__open(evlist) == -ENOENT) {
+		err = TEST_SKIP;
+		goto out_err;
+	}
 	CHECK__(evlist__open(evlist));
 
 	CHECK__(evlist__mmap(evlist, UINT_MAX));
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index d2b64e3f588b..1a80151baed9 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -1033,10 +1033,11 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
 	memset(&attr, 0, sizeof(struct perf_event_attr));
 	attr.size = sizeof(struct perf_event_attr);
 	attr.type = PERF_TYPE_HARDWARE;
-	attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
+	attr.sample_type = evsel->core.attr.sample_type &
+				(PERF_SAMPLE_MASK | PERF_SAMPLE_PHYS_ADDR);
 	attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
 			    PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC |
-			    PERF_SAMPLE_WEIGHT;
+			    PERF_SAMPLE_WEIGHT | PERF_SAMPLE_ADDR;
 	if (spe->timeless_decoding)
 		attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
 	else
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
index df7b18fb6b6e..1aad7d6d34aa 100644
--- a/tools/perf/util/c++/clang.cpp
+++ b/tools/perf/util/c++/clang.cpp
@@ -20,7 +20,11 @@
 #include "llvm/Option/Option.h"
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/ManagedStatic.h"
+#if CLANG_VERSION_MAJOR >= 14
+#include "llvm/MC/TargetRegistry.h"
+#else
 #include "llvm/Support/TargetRegistry.h"
+#endif
 #include "llvm/Support/TargetSelect.h"
 #include "llvm/Target/TargetMachine.h"
 #include "llvm/Target/TargetOptions.h"
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index d546ff724dbe..a27132e5a5ef 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -983,6 +983,57 @@ static int write_dir_format(struct feat_fd *ff,
 	return do_write(ff, &data->dir.version, sizeof(data->dir.version));
 }
 
+/*
+ * Check whether a CPU is online
+ *
+ * Returns:
+ *     1 -> if CPU is online
+ *     0 -> if CPU is offline
+ *    -1 -> error case
+ */
+int is_cpu_online(unsigned int cpu)
+{
+	char *str;
+	size_t strlen;
+	char buf[256];
+	int status = -1;
+	struct stat statbuf;
+
+	snprintf(buf, sizeof(buf),
+		"/sys/devices/system/cpu/cpu%d", cpu);
+	if (stat(buf, &statbuf) != 0)
+		return 0;
+
+	/*
+	 * Check if /sys/devices/system/cpu/cpux/online file
+	 * exists. Some cases cpu0 won't have online file since
+	 * it is not expected to be turned off generally.
+	 * In kernels without CONFIG_HOTPLUG_CPU, this
+	 * file won't exist
+	 */
+	snprintf(buf, sizeof(buf),
+		"/sys/devices/system/cpu/cpu%d/online", cpu);
+	if (stat(buf, &statbuf) != 0)
+		return 1;
+
+	/*
+	 * Read online file using sysfs__read_str.
+	 * If read or open fails, return -1.
+	 * If read succeeds, return value from file
+	 * which gets stored in "str"
+	 */
+	snprintf(buf, sizeof(buf),
+		"devices/system/cpu/cpu%d/online", cpu);
+
+	if (sysfs__read_str(buf, &str, &strlen) < 0)
+		return status;
+
+	status = atoi(str);
+
+	free(str);
+	return status;
+}
+
 #ifdef HAVE_LIBBPF_SUPPORT
 static int write_bpf_prog_info(struct feat_fd *ff,
 			       struct evlist *evlist __maybe_unused)
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index c9e3265832d9..0eb4bc29a5a4 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -158,6 +158,7 @@ int do_write(struct feat_fd *fd, const void *buf, size_t size);
 int write_padded(struct feat_fd *fd, const void *bf,
 		 size_t count, size_t count_aligned);
 
+int is_cpu_online(unsigned int cpu);
 /*
  * arch specific callback
  */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 24997925ae00..dd84fed698a3 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1523,7 +1523,9 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 	bool use_uncore_alias;
 	LIST_HEAD(config_terms);
 
-	if (verbose > 1) {
+	pmu = parse_state->fake_pmu ?: perf_pmu__find(name);
+
+	if (verbose > 1 && !(pmu && pmu->selectable)) {
 		fprintf(stderr, "Attempting to add event pmu '%s' with '",
 			name);
 		if (head_config) {
@@ -1536,7 +1538,6 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 		fprintf(stderr, "' that may result in non-fatal errors\n");
 	}
 
-	pmu = parse_state->fake_pmu ?: perf_pmu__find(name);
 	if (!pmu) {
 		char *err_str;
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 45a30040ec8d..f9a320694b85 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -2576,7 +2576,7 @@ int perf_session__process_events(struct perf_session *session)
 	if (perf_data__is_pipe(session->data))
 		return __perf_session__process_pipe_events(session);
 
-	if (perf_data__is_dir(session->data))
+	if (perf_data__is_dir(session->data) && session->data->dir.nr)
 		return __perf_session__process_dir_events(session);
 
 	return __perf_session__process_events(session);
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index ee6f03481215..817a2de264b4 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
+#include <linux/err.h>
 #include <inttypes.h>
 #include <math.h>
 #include <string.h>
@@ -311,7 +312,7 @@ static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals,
 
 	if (!mask) {
 		mask = hashmap__new(pkg_id_hash, pkg_id_equal, NULL);
-		if (!mask)
+		if (IS_ERR(mask))
 			return -ENOMEM;
 
 		counter->per_pkg_mask = mask;
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 31cd59a2b66e..ecd377938eea 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1290,7 +1290,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 	 * For misannotated, zeroed, ASM function sizes.
 	 */
 	if (nr > 0) {
-		symbols__fixup_end(&dso->symbols);
+		symbols__fixup_end(&dso->symbols, false);
 		symbols__fixup_duplicate(&dso->symbols);
 		if (kmap) {
 			/*
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index dea0fc495185..f72baf636724 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -101,11 +101,6 @@ static int prefix_underscores_count(const char *str)
 	return tail - str;
 }
 
-void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
-{
-	p->end = c->start;
-}
-
 const char * __weak arch__normalize_symbol_name(const char *name)
 {
 	return name;
@@ -217,7 +212,8 @@ again:
 	}
 }
 
-void symbols__fixup_end(struct rb_root_cached *symbols)
+/* Update zero-sized symbols using the address of the next symbol */
+void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms)
 {
 	struct rb_node *nd, *prevnd = rb_first_cached(symbols);
 	struct symbol *curr, *prev;
@@ -231,8 +227,29 @@ void symbols__fixup_end(struct rb_root_cached *symbols)
 		prev = curr;
 		curr = rb_entry(nd, struct symbol, rb_node);
 
-		if (prev->end == prev->start || prev->end != curr->start)
-			arch__symbols__fixup_end(prev, curr);
+		/*
+		 * On some architecture kernel text segment start is located at
+		 * some low memory address, while modules are located at high
+		 * memory addresses (or vice versa).  The gap between end of
+		 * kernel text segment and beginning of first module's text
+		 * segment is very big.  Therefore do not fill this gap and do
+		 * not assign it to the kernel dso map (kallsyms).
+		 *
+		 * In kallsyms, it determines module symbols using '[' character
+		 * like in:
+		 *   ffffffffc1937000 T hdmi_driver_init  [snd_hda_codec_hdmi]
+		 */
+		if (prev->end == prev->start) {
+			/* Last kernel/module symbol mapped to end of page */
+			if (is_kallsyms && (!strchr(prev->name, '[') !=
+					    !strchr(curr->name, '[')))
+				prev->end = roundup(prev->end + 4096, 4096);
+			else
+				prev->end = curr->start;
+
+			pr_debug4("%s sym:%s end:%#" PRIx64 "\n",
+				  __func__, prev->name, prev->end);
+		}
 	}
 
 	/* Last entry */
@@ -1467,7 +1484,7 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename,
 	if (kallsyms__delta(kmap, filename, &delta))
 		return -1;
 
-	symbols__fixup_end(&dso->symbols);
+	symbols__fixup_end(&dso->symbols, true);
 	symbols__fixup_duplicate(&dso->symbols);
 
 	if (dso->kernel == DSO_SPACE__KERNEL_GUEST)
@@ -1659,7 +1676,7 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile)
 #undef bfd_asymbol_section
 #endif
 
-	symbols__fixup_end(&dso->symbols);
+	symbols__fixup_end(&dso->symbols, false);
 	symbols__fixup_duplicate(&dso->symbols);
 	dso->adjust_symbols = 1;
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index fbf866d82dcc..0b893dcc8ea6 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -203,7 +203,7 @@ void __symbols__insert(struct rb_root_cached *symbols, struct symbol *sym,
 		       bool kernel);
 void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym);
 void symbols__fixup_duplicate(struct rb_root_cached *symbols);
-void symbols__fixup_end(struct rb_root_cached *symbols);
+void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms);
 void maps__fixup_end(struct maps *maps);
 
 typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data);
@@ -241,7 +241,6 @@ const char *arch__normalize_symbol_name(const char *name);
 #define SYMBOL_A 0
 #define SYMBOL_B 1
 
-void arch__symbols__fixup_end(struct symbol *p, struct symbol *c);
 int arch__compare_symbol_names(const char *namea, const char *nameb);
 int arch__compare_symbol_names_n(const char *namea, const char *nameb,
 				 unsigned int n);
diff --git a/tools/power/x86/intel-speed-select/Makefile b/tools/power/x86/intel-speed-select/Makefile
index 846f785e278d..7221f2f55e8b 100644
--- a/tools/power/x86/intel-speed-select/Makefile
+++ b/tools/power/x86/intel-speed-select/Makefile
@@ -42,7 +42,7 @@ ISST_IN := $(OUTPUT)intel-speed-select-in.o
 $(ISST_IN): prepare FORCE
 	$(Q)$(MAKE) $(build)=intel-speed-select
 $(OUTPUT)intel-speed-select: $(ISST_IN)
-	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
+	$(QUIET_LINK)$(CC) $(CFLAGS) $< $(LDFLAGS) -o $@
 
 clean:
 	rm -f $(ALL_PROGRAMS)
diff --git a/tools/testing/radix-tree/linux.c b/tools/testing/radix-tree/linux.c
index 81539f543954..d5c1bcba86fe 100644
--- a/tools/testing/radix-tree/linux.c
+++ b/tools/testing/radix-tree/linux.c
@@ -25,7 +25,8 @@ struct kmem_cache {
 	void (*ctor)(void *);
 };
 
-void *kmem_cache_alloc(struct kmem_cache *cachep, int gfp)
+void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru,
+		int gfp)
 {
 	void *p;
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh
index 429f7ee735cf..fd23c80eba31 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh
@@ -159,6 +159,17 @@ flooding_remotes_add()
 	local lsb
 	local i
 
+	# Prevent unwanted packets from entering the bridge and interfering
+	# with the test.
+	tc qdisc add dev br0 clsact
+	tc filter add dev br0 egress protocol all pref 1 handle 1 \
+		matchall skip_hw action drop
+	tc qdisc add dev $h1 clsact
+	tc filter add dev $h1 egress protocol all pref 1 handle 1 \
+		flower skip_hw dst_mac de:ad:be:ef:13:37 action pass
+	tc filter add dev $h1 egress protocol all pref 2 handle 2 \
+		matchall skip_hw action drop
+
 	for i in $(eval echo {1..$num_remotes}); do
 		lsb=$((i + 1))
 
@@ -195,6 +206,12 @@ flooding_filters_del()
 	done
 
 	tc qdisc del dev $rp2 clsact
+
+	tc filter del dev $h1 egress protocol all pref 2 handle 2 matchall
+	tc filter del dev $h1 egress protocol all pref 1 handle 1 flower
+	tc qdisc del dev $h1 clsact
+	tc filter del dev br0 egress protocol all pref 1 handle 1 matchall
+	tc qdisc del dev br0 clsact
 }
 
 flooding_check_packets()
diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh
index fedcb7b35af9..af5ea50ed5c0 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh
@@ -172,6 +172,17 @@ flooding_filters_add()
 	local lsb
 	local i
 
+	# Prevent unwanted packets from entering the bridge and interfering
+	# with the test.
+	tc qdisc add dev br0 clsact
+	tc filter add dev br0 egress protocol all pref 1 handle 1 \
+		matchall skip_hw action drop
+	tc qdisc add dev $h1 clsact
+	tc filter add dev $h1 egress protocol all pref 1 handle 1 \
+		flower skip_hw dst_mac de:ad:be:ef:13:37 action pass
+	tc filter add dev $h1 egress protocol all pref 2 handle 2 \
+		matchall skip_hw action drop
+
 	tc qdisc add dev $rp2 clsact
 
 	for i in $(eval echo {1..$num_remotes}); do
@@ -194,6 +205,12 @@ flooding_filters_del()
 	done
 
 	tc qdisc del dev $rp2 clsact
+
+	tc filter del dev $h1 egress protocol all pref 2 handle 2 matchall
+	tc filter del dev $h1 egress protocol all pref 1 handle 1 flower
+	tc qdisc del dev $h1 clsact
+	tc filter del dev br0 egress protocol all pref 1 handle 1 matchall
+	tc qdisc del dev br0 clsact
 }
 
 flooding_check_packets()
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index d1e8f5237469..0b0e4402bba6 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -3,6 +3,7 @@
 /aarch64/debug-exceptions
 /aarch64/get-reg-list
 /aarch64/psci_cpu_on_test
+/aarch64/vcpu_width_config
 /aarch64/vgic_init
 /aarch64/vgic_irq
 /s390x/memop
@@ -33,6 +34,7 @@
 /x86_64/state_test
 /x86_64/svm_vmcall_test
 /x86_64/svm_int_ctl_test
+/x86_64/tsc_scaling_sync
 /x86_64/sync_regs_test
 /x86_64/tsc_msrs_test
 /x86_64/userspace_io_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 21c2dbd21a81..681b173aa87c 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -106,6 +106,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/arch_timer
 TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions
 TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
 TEST_GEN_PROGS_aarch64 += aarch64/psci_cpu_on_test
+TEST_GEN_PROGS_aarch64 += aarch64/vcpu_width_config
 TEST_GEN_PROGS_aarch64 += aarch64/vgic_init
 TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq
 TEST_GEN_PROGS_aarch64 += demand_paging_test
diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c
index b08d30bf71c5..3b940a101bc0 100644
--- a/tools/testing/selftests/kvm/aarch64/arch_timer.c
+++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c
@@ -362,11 +362,12 @@ static void test_init_timer_irq(struct kvm_vm *vm)
 	pr_debug("ptimer_irq: %d; vtimer_irq: %d\n", ptimer_irq, vtimer_irq);
 }
 
+static int gic_fd;
+
 static struct kvm_vm *test_vm_create(void)
 {
 	struct kvm_vm *vm;
 	unsigned int i;
-	int ret;
 	int nr_vcpus = test_args.nr_vcpus;
 
 	vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL);
@@ -383,8 +384,8 @@ static struct kvm_vm *test_vm_create(void)
 
 	ucall_init(vm, NULL);
 	test_init_timer_irq(vm);
-	ret = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
-	if (ret < 0) {
+	gic_fd = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
+	if (gic_fd < 0) {
 		print_skip("Failed to create vgic-v3");
 		exit(KSFT_SKIP);
 	}
@@ -395,6 +396,12 @@ static struct kvm_vm *test_vm_create(void)
 	return vm;
 }
 
+static void test_vm_cleanup(struct kvm_vm *vm)
+{
+	close(gic_fd);
+	kvm_vm_free(vm);
+}
+
 static void test_print_help(char *name)
 {
 	pr_info("Usage: %s [-h] [-n nr_vcpus] [-i iterations] [-p timer_period_ms]\n",
@@ -478,7 +485,7 @@ int main(int argc, char *argv[])
 
 	vm = test_vm_create();
 	test_run(vm);
-	kvm_vm_free(vm);
+	test_vm_cleanup(vm);
 
 	return 0;
 }
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index f12147c43464..0b571f3fe64c 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -503,8 +503,13 @@ static void run_test(struct vcpu_config *c)
 		++missing_regs;
 
 	if (new_regs || missing_regs) {
+		n = 0;
+		for_each_reg_filtered(i)
+			++n;
+
 		printf("%s: Number blessed registers: %5lld\n", config_name(c), blessed_n);
-		printf("%s: Number registers:         %5lld\n", config_name(c), reg_list->n);
+		printf("%s: Number registers:         %5lld (includes %lld filtered registers)\n",
+		       config_name(c), reg_list->n, reg_list->n - n);
 	}
 
 	if (new_regs) {
@@ -683,9 +688,10 @@ static __u64 base_regs[] = {
 	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[4]),
 	KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpsr),
 	KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpcr),
-	KVM_REG_ARM_FW_REG(0),
-	KVM_REG_ARM_FW_REG(1),
-	KVM_REG_ARM_FW_REG(2),
+	KVM_REG_ARM_FW_REG(0),		/* KVM_REG_ARM_PSCI_VERSION */
+	KVM_REG_ARM_FW_REG(1),		/* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 */
+	KVM_REG_ARM_FW_REG(2),		/* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 */
+	KVM_REG_ARM_FW_REG(3),		/* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3 */
 	ARM64_SYS_REG(3, 3, 14, 3, 1),	/* CNTV_CTL_EL0 */
 	ARM64_SYS_REG(3, 3, 14, 3, 2),	/* CNTV_CVAL_EL0 */
 	ARM64_SYS_REG(3, 3, 14, 0, 2),
diff --git a/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c b/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c
new file mode 100644
index 000000000000..6e9402679229
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vcpu_width_config - Test KVM_ARM_VCPU_INIT() with KVM_ARM_VCPU_EL1_32BIT.
+ *
+ * Copyright (c) 2022 Google LLC.
+ *
+ * This is a test that ensures that non-mixed-width vCPUs (all 64bit vCPUs
+ * or all 32bit vcPUs) can be configured and mixed-width vCPUs cannot be
+ * configured.
+ */
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "test_util.h"
+
+
+/*
+ * Add a vCPU, run KVM_ARM_VCPU_INIT with @init1, and then
+ * add another vCPU, and run KVM_ARM_VCPU_INIT with @init2.
+ */
+static int add_init_2vcpus(struct kvm_vcpu_init *init1,
+			   struct kvm_vcpu_init *init2)
+{
+	struct kvm_vm *vm;
+	int ret;
+
+	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+
+	vm_vcpu_add(vm, 0);
+	ret = _vcpu_ioctl(vm, 0, KVM_ARM_VCPU_INIT, init1);
+	if (ret)
+		goto free_exit;
+
+	vm_vcpu_add(vm, 1);
+	ret = _vcpu_ioctl(vm, 1, KVM_ARM_VCPU_INIT, init2);
+
+free_exit:
+	kvm_vm_free(vm);
+	return ret;
+}
+
+/*
+ * Add two vCPUs, then run KVM_ARM_VCPU_INIT for one vCPU with @init1,
+ * and run KVM_ARM_VCPU_INIT for another vCPU with @init2.
+ */
+static int add_2vcpus_init_2vcpus(struct kvm_vcpu_init *init1,
+				  struct kvm_vcpu_init *init2)
+{
+	struct kvm_vm *vm;
+	int ret;
+
+	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+
+	vm_vcpu_add(vm, 0);
+	vm_vcpu_add(vm, 1);
+
+	ret = _vcpu_ioctl(vm, 0, KVM_ARM_VCPU_INIT, init1);
+	if (ret)
+		goto free_exit;
+
+	ret = _vcpu_ioctl(vm, 1, KVM_ARM_VCPU_INIT, init2);
+
+free_exit:
+	kvm_vm_free(vm);
+	return ret;
+}
+
+/*
+ * Tests that two 64bit vCPUs can be configured, two 32bit vCPUs can be
+ * configured, and two mixed-width vCPUs cannot be configured.
+ * Each of those three cases, configure vCPUs in two different orders.
+ * The one is running KVM_CREATE_VCPU for 2 vCPUs, and then running
+ * KVM_ARM_VCPU_INIT for them.
+ * The other is running KVM_CREATE_VCPU and KVM_ARM_VCPU_INIT for a vCPU,
+ * and then run those commands for another vCPU.
+ */
+int main(void)
+{
+	struct kvm_vcpu_init init1, init2;
+	struct kvm_vm *vm;
+	int ret;
+
+	if (!kvm_check_cap(KVM_CAP_ARM_EL1_32BIT)) {
+		print_skip("KVM_CAP_ARM_EL1_32BIT is not supported");
+		exit(KSFT_SKIP);
+	}
+
+	/* Get the preferred target type and copy that to init2 for later use */
+	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+	vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init1);
+	kvm_vm_free(vm);
+	init2 = init1;
+
+	/* Test with 64bit vCPUs */
+	ret = add_init_2vcpus(&init1, &init1);
+	TEST_ASSERT(ret == 0,
+		    "Configuring 64bit EL1 vCPUs failed unexpectedly");
+	ret = add_2vcpus_init_2vcpus(&init1, &init1);
+	TEST_ASSERT(ret == 0,
+		    "Configuring 64bit EL1 vCPUs failed unexpectedly");
+
+	/* Test with 32bit vCPUs */
+	init1.features[0] = (1 << KVM_ARM_VCPU_EL1_32BIT);
+	ret = add_init_2vcpus(&init1, &init1);
+	TEST_ASSERT(ret == 0,
+		    "Configuring 32bit EL1 vCPUs failed unexpectedly");
+	ret = add_2vcpus_init_2vcpus(&init1, &init1);
+	TEST_ASSERT(ret == 0,
+		    "Configuring 32bit EL1 vCPUs failed unexpectedly");
+
+	/* Test with mixed-width vCPUs  */
+	init1.features[0] = 0;
+	init2.features[0] = (1 << KVM_ARM_VCPU_EL1_32BIT);
+	ret = add_init_2vcpus(&init1, &init2);
+	TEST_ASSERT(ret != 0,
+		    "Configuring mixed-width vCPUs worked unexpectedly");
+	ret = add_2vcpus_init_2vcpus(&init1, &init2);
+	TEST_ASSERT(ret != 0,
+		    "Configuring mixed-width vCPUs worked unexpectedly");
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index c9d9e513ca04..7b47ae4f952e 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -18,11 +18,40 @@
 #include "test_util.h"
 #include "perf_test_util.h"
 #include "guest_modes.h"
+
 #ifdef __aarch64__
 #include "aarch64/vgic.h"
 
 #define GICD_BASE_GPA			0x8000000ULL
 #define GICR_BASE_GPA			0x80A0000ULL
+
+static int gic_fd;
+
+static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus)
+{
+	/*
+	 * The test can still run even if hardware does not support GICv3, as it
+	 * is only an optimization to reduce guest exits.
+	 */
+	gic_fd = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
+}
+
+static void arch_cleanup_vm(struct kvm_vm *vm)
+{
+	if (gic_fd > 0)
+		close(gic_fd);
+}
+
+#else /* __aarch64__ */
+
+static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus)
+{
+}
+
+static void arch_cleanup_vm(struct kvm_vm *vm)
+{
+}
+
 #endif
 
 /* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/
@@ -206,9 +235,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		vm_enable_cap(vm, &cap);
 	}
 
-#ifdef __aarch64__
-	vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
-#endif
+	arch_setup_vm(vm, nr_vcpus);
 
 	/* Start the iterations */
 	iteration = 0;
@@ -302,6 +329,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	}
 
 	free_bitmaps(bitmaps, p->slots);
+	arch_cleanup_vm(vm);
 	perf_test_destroy_vm(vm);
 }
 
diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h
index dc284c6bdbc3..eca5c622efd2 100644
--- a/tools/testing/selftests/kvm/include/riscv/processor.h
+++ b/tools/testing/selftests/kvm/include/riscv/processor.h
@@ -101,7 +101,9 @@ static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id,
 #define PGTBL_PTE_WRITE_SHIFT			2
 #define PGTBL_PTE_READ_MASK			0x0000000000000002ULL
 #define PGTBL_PTE_READ_SHIFT			1
-#define PGTBL_PTE_PERM_MASK			(PGTBL_PTE_EXECUTE_MASK | \
+#define PGTBL_PTE_PERM_MASK			(PGTBL_PTE_ACCESSED_MASK | \
+						 PGTBL_PTE_DIRTY_MASK | \
+						 PGTBL_PTE_EXECUTE_MASK | \
 						 PGTBL_PTE_WRITE_MASK | \
 						 PGTBL_PTE_READ_MASK)
 #define PGTBL_PTE_VALID_MASK			0x0000000000000001ULL
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 37db341d4cc5..d0d51adec76e 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -60,6 +60,23 @@
 /* CPUID.0x8000_0001.EDX */
 #define CPUID_GBPAGES		(1ul << 26)
 
+/* Page table bitfield declarations */
+#define PTE_PRESENT_MASK        BIT_ULL(0)
+#define PTE_WRITABLE_MASK       BIT_ULL(1)
+#define PTE_USER_MASK           BIT_ULL(2)
+#define PTE_ACCESSED_MASK       BIT_ULL(5)
+#define PTE_DIRTY_MASK          BIT_ULL(6)
+#define PTE_LARGE_MASK          BIT_ULL(7)
+#define PTE_GLOBAL_MASK         BIT_ULL(8)
+#define PTE_NX_MASK             BIT_ULL(63)
+
+#define PAGE_SHIFT		12
+#define PAGE_SIZE		(1ULL << PAGE_SHIFT)
+#define PAGE_MASK		(~(PAGE_SIZE-1))
+
+#define PHYSICAL_PAGE_MASK      GENMASK_ULL(51, 12)
+#define PTE_GET_PFN(pte)        (((pte) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT)
+
 /* General Registers in 64-Bit Mode */
 struct gpr64_regs {
 	u64 rax;
diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c
index ba1fdc3dcf4a..2c4a7563a4f8 100644
--- a/tools/testing/selftests/kvm/kvm_page_table_test.c
+++ b/tools/testing/selftests/kvm/kvm_page_table_test.c
@@ -278,7 +278,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg)
 	else
 		guest_test_phys_mem = p->phys_offset;
 #ifdef __s390x__
-	alignment = max(0x100000, alignment);
+	alignment = max(0x100000UL, alignment);
 #endif
 	guest_test_phys_mem = align_down(guest_test_phys_mem, alignment);
 
diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c
index d377f2603d98..3961487a4870 100644
--- a/tools/testing/selftests/kvm/lib/riscv/processor.c
+++ b/tools/testing/selftests/kvm/lib/riscv/processor.c
@@ -268,7 +268,7 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
 		core.regs.t3, core.regs.t4, core.regs.t5, core.regs.t6);
 }
 
-static void guest_hang(void)
+static void __aligned(16) guest_hang(void)
 {
 	while (1)
 		;
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 9f000dfb5594..33ea5e9955d9 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -19,38 +19,6 @@
 
 vm_vaddr_t exception_handlers;
 
-/* Virtual translation table structure declarations */
-struct pageUpperEntry {
-	uint64_t present:1;
-	uint64_t writable:1;
-	uint64_t user:1;
-	uint64_t write_through:1;
-	uint64_t cache_disable:1;
-	uint64_t accessed:1;
-	uint64_t ignored_06:1;
-	uint64_t page_size:1;
-	uint64_t ignored_11_08:4;
-	uint64_t pfn:40;
-	uint64_t ignored_62_52:11;
-	uint64_t execute_disable:1;
-};
-
-struct pageTableEntry {
-	uint64_t present:1;
-	uint64_t writable:1;
-	uint64_t user:1;
-	uint64_t write_through:1;
-	uint64_t cache_disable:1;
-	uint64_t accessed:1;
-	uint64_t dirty:1;
-	uint64_t reserved_07:1;
-	uint64_t global:1;
-	uint64_t ignored_11_09:3;
-	uint64_t pfn:40;
-	uint64_t ignored_62_52:11;
-	uint64_t execute_disable:1;
-};
-
 void regs_dump(FILE *stream, struct kvm_regs *regs,
 	       uint8_t indent)
 {
@@ -195,23 +163,21 @@ static void *virt_get_pte(struct kvm_vm *vm, uint64_t pt_pfn, uint64_t vaddr,
 	return &page_table[index];
 }
 
-static struct pageUpperEntry *virt_create_upper_pte(struct kvm_vm *vm,
-						    uint64_t pt_pfn,
-						    uint64_t vaddr,
-						    uint64_t paddr,
-						    int level,
-						    enum x86_page_size page_size)
+static uint64_t *virt_create_upper_pte(struct kvm_vm *vm,
+				       uint64_t pt_pfn,
+				       uint64_t vaddr,
+				       uint64_t paddr,
+				       int level,
+				       enum x86_page_size page_size)
 {
-	struct pageUpperEntry *pte = virt_get_pte(vm, pt_pfn, vaddr, level);
-
-	if (!pte->present) {
-		pte->writable = true;
-		pte->present = true;
-		pte->page_size = (level == page_size);
-		if (pte->page_size)
-			pte->pfn = paddr >> vm->page_shift;
+	uint64_t *pte = virt_get_pte(vm, pt_pfn, vaddr, level);
+
+	if (!(*pte & PTE_PRESENT_MASK)) {
+		*pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK;
+		if (level == page_size)
+			*pte |= PTE_LARGE_MASK | (paddr & PHYSICAL_PAGE_MASK);
 		else
-			pte->pfn = vm_alloc_page_table(vm) >> vm->page_shift;
+			*pte |= vm_alloc_page_table(vm) & PHYSICAL_PAGE_MASK;
 	} else {
 		/*
 		 * Entry already present.  Assert that the caller doesn't want
@@ -221,7 +187,7 @@ static struct pageUpperEntry *virt_create_upper_pte(struct kvm_vm *vm,
 		TEST_ASSERT(level != page_size,
 			    "Cannot create hugepage at level: %u, vaddr: 0x%lx\n",
 			    page_size, vaddr);
-		TEST_ASSERT(!pte->page_size,
+		TEST_ASSERT(!(*pte & PTE_LARGE_MASK),
 			    "Cannot create page table at level: %u, vaddr: 0x%lx\n",
 			    level, vaddr);
 	}
@@ -232,8 +198,8 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 		   enum x86_page_size page_size)
 {
 	const uint64_t pg_size = 1ull << ((page_size * 9) + 12);
-	struct pageUpperEntry *pml4e, *pdpe, *pde;
-	struct pageTableEntry *pte;
+	uint64_t *pml4e, *pdpe, *pde;
+	uint64_t *pte;
 
 	TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K,
 		    "Unknown or unsupported guest mode, mode: 0x%x", vm->mode);
@@ -257,24 +223,22 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 	 */
 	pml4e = virt_create_upper_pte(vm, vm->pgd >> vm->page_shift,
 				      vaddr, paddr, 3, page_size);
-	if (pml4e->page_size)
+	if (*pml4e & PTE_LARGE_MASK)
 		return;
 
-	pdpe = virt_create_upper_pte(vm, pml4e->pfn, vaddr, paddr, 2, page_size);
-	if (pdpe->page_size)
+	pdpe = virt_create_upper_pte(vm, PTE_GET_PFN(*pml4e), vaddr, paddr, 2, page_size);
+	if (*pdpe & PTE_LARGE_MASK)
 		return;
 
-	pde = virt_create_upper_pte(vm, pdpe->pfn, vaddr, paddr, 1, page_size);
-	if (pde->page_size)
+	pde = virt_create_upper_pte(vm, PTE_GET_PFN(*pdpe), vaddr, paddr, 1, page_size);
+	if (*pde & PTE_LARGE_MASK)
 		return;
 
 	/* Fill in page table entry. */
-	pte = virt_get_pte(vm, pde->pfn, vaddr, 0);
-	TEST_ASSERT(!pte->present,
+	pte = virt_get_pte(vm, PTE_GET_PFN(*pde), vaddr, 0);
+	TEST_ASSERT(!(*pte & PTE_PRESENT_MASK),
 		    "PTE already present for 4k page at vaddr: 0x%lx\n", vaddr);
-	pte->pfn = paddr >> vm->page_shift;
-	pte->writable = true;
-	pte->present = 1;
+	*pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK);
 }
 
 void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
@@ -282,22 +246,22 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
 	__virt_pg_map(vm, vaddr, paddr, X86_PAGE_SIZE_4K);
 }
 
-static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid,
+static uint64_t *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid,
 						       uint64_t vaddr)
 {
 	uint16_t index[4];
-	struct pageUpperEntry *pml4e, *pdpe, *pde;
-	struct pageTableEntry *pte;
+	uint64_t *pml4e, *pdpe, *pde;
+	uint64_t *pte;
 	struct kvm_cpuid_entry2 *entry;
 	struct kvm_sregs sregs;
 	int max_phy_addr;
-	/* Set the bottom 52 bits. */
-	uint64_t rsvd_mask = 0x000fffffffffffff;
+	uint64_t rsvd_mask = 0;
 
 	entry = kvm_get_supported_cpuid_index(0x80000008, 0);
 	max_phy_addr = entry->eax & 0x000000ff;
-	/* Clear the bottom bits of the reserved mask. */
-	rsvd_mask = (rsvd_mask >> max_phy_addr) << max_phy_addr;
+	/* Set the high bits in the reserved mask. */
+	if (max_phy_addr < 52)
+		rsvd_mask = GENMASK_ULL(51, max_phy_addr);
 
 	/*
 	 * SDM vol 3, fig 4-11 "Formats of CR3 and Paging-Structure Entries
@@ -307,7 +271,7 @@ static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vc
 	 */
 	vcpu_sregs_get(vm, vcpuid, &sregs);
 	if ((sregs.efer & EFER_NX) == 0) {
-		rsvd_mask |= (1ull << 63);
+		rsvd_mask |= PTE_NX_MASK;
 	}
 
 	TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
@@ -329,30 +293,29 @@ static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vc
 	index[3] = (vaddr >> 39) & 0x1ffu;
 
 	pml4e = addr_gpa2hva(vm, vm->pgd);
-	TEST_ASSERT(pml4e[index[3]].present,
+	TEST_ASSERT(pml4e[index[3]] & PTE_PRESENT_MASK,
 		"Expected pml4e to be present for gva: 0x%08lx", vaddr);
-	TEST_ASSERT((*(uint64_t*)(&pml4e[index[3]]) &
-		(rsvd_mask | (1ull << 7))) == 0,
+	TEST_ASSERT((pml4e[index[3]] & (rsvd_mask | PTE_LARGE_MASK)) == 0,
 		"Unexpected reserved bits set.");
 
-	pdpe = addr_gpa2hva(vm, pml4e[index[3]].pfn * vm->page_size);
-	TEST_ASSERT(pdpe[index[2]].present,
+	pdpe = addr_gpa2hva(vm, PTE_GET_PFN(pml4e[index[3]]) * vm->page_size);
+	TEST_ASSERT(pdpe[index[2]] & PTE_PRESENT_MASK,
 		"Expected pdpe to be present for gva: 0x%08lx", vaddr);
-	TEST_ASSERT(pdpe[index[2]].page_size == 0,
+	TEST_ASSERT(!(pdpe[index[2]] & PTE_LARGE_MASK),
 		"Expected pdpe to map a pde not a 1-GByte page.");
-	TEST_ASSERT((*(uint64_t*)(&pdpe[index[2]]) & rsvd_mask) == 0,
+	TEST_ASSERT((pdpe[index[2]] & rsvd_mask) == 0,
 		"Unexpected reserved bits set.");
 
-	pde = addr_gpa2hva(vm, pdpe[index[2]].pfn * vm->page_size);
-	TEST_ASSERT(pde[index[1]].present,
+	pde = addr_gpa2hva(vm, PTE_GET_PFN(pdpe[index[2]]) * vm->page_size);
+	TEST_ASSERT(pde[index[1]] & PTE_PRESENT_MASK,
 		"Expected pde to be present for gva: 0x%08lx", vaddr);
-	TEST_ASSERT(pde[index[1]].page_size == 0,
+	TEST_ASSERT(!(pde[index[1]] & PTE_LARGE_MASK),
 		"Expected pde to map a pte not a 2-MByte page.");
-	TEST_ASSERT((*(uint64_t*)(&pde[index[1]]) & rsvd_mask) == 0,
+	TEST_ASSERT((pde[index[1]] & rsvd_mask) == 0,
 		"Unexpected reserved bits set.");
 
-	pte = addr_gpa2hva(vm, pde[index[1]].pfn * vm->page_size);
-	TEST_ASSERT(pte[index[0]].present,
+	pte = addr_gpa2hva(vm, PTE_GET_PFN(pde[index[1]]) * vm->page_size);
+	TEST_ASSERT(pte[index[0]] & PTE_PRESENT_MASK,
 		"Expected pte to be present for gva: 0x%08lx", vaddr);
 
 	return &pte[index[0]];
@@ -360,7 +323,7 @@ static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vc
 
 uint64_t vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr)
 {
-	struct pageTableEntry *pte = _vm_get_page_table_entry(vm, vcpuid, vaddr);
+	uint64_t *pte = _vm_get_page_table_entry(vm, vcpuid, vaddr);
 
 	return *(uint64_t *)pte;
 }
@@ -368,18 +331,17 @@ uint64_t vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr)
 void vm_set_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr,
 			     uint64_t pte)
 {
-	struct pageTableEntry *new_pte = _vm_get_page_table_entry(vm, vcpuid,
-								  vaddr);
+	uint64_t *new_pte = _vm_get_page_table_entry(vm, vcpuid, vaddr);
 
 	*(uint64_t *)new_pte = pte;
 }
 
 void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 {
-	struct pageUpperEntry *pml4e, *pml4e_start;
-	struct pageUpperEntry *pdpe, *pdpe_start;
-	struct pageUpperEntry *pde, *pde_start;
-	struct pageTableEntry *pte, *pte_start;
+	uint64_t *pml4e, *pml4e_start;
+	uint64_t *pdpe, *pdpe_start;
+	uint64_t *pde, *pde_start;
+	uint64_t *pte, *pte_start;
 
 	if (!vm->pgd_created)
 		return;
@@ -389,58 +351,58 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 	fprintf(stream, "%*s      index hvaddr         gpaddr         "
 		"addr         w exec dirty\n",
 		indent, "");
-	pml4e_start = (struct pageUpperEntry *) addr_gpa2hva(vm, vm->pgd);
+	pml4e_start = (uint64_t *) addr_gpa2hva(vm, vm->pgd);
 	for (uint16_t n1 = 0; n1 <= 0x1ffu; n1++) {
 		pml4e = &pml4e_start[n1];
-		if (!pml4e->present)
+		if (!(*pml4e & PTE_PRESENT_MASK))
 			continue;
-		fprintf(stream, "%*spml4e 0x%-3zx %p 0x%-12lx 0x%-10lx %u "
+		fprintf(stream, "%*spml4e 0x%-3zx %p 0x%-12lx 0x%-10llx %u "
 			" %u\n",
 			indent, "",
 			pml4e - pml4e_start, pml4e,
-			addr_hva2gpa(vm, pml4e), (uint64_t) pml4e->pfn,
-			pml4e->writable, pml4e->execute_disable);
+			addr_hva2gpa(vm, pml4e), PTE_GET_PFN(*pml4e),
+			!!(*pml4e & PTE_WRITABLE_MASK), !!(*pml4e & PTE_NX_MASK));
 
-		pdpe_start = addr_gpa2hva(vm, pml4e->pfn * vm->page_size);
+		pdpe_start = addr_gpa2hva(vm, *pml4e & PHYSICAL_PAGE_MASK);
 		for (uint16_t n2 = 0; n2 <= 0x1ffu; n2++) {
 			pdpe = &pdpe_start[n2];
-			if (!pdpe->present)
+			if (!(*pdpe & PTE_PRESENT_MASK))
 				continue;
-			fprintf(stream, "%*spdpe  0x%-3zx %p 0x%-12lx 0x%-10lx "
+			fprintf(stream, "%*spdpe  0x%-3zx %p 0x%-12lx 0x%-10llx "
 				"%u  %u\n",
 				indent, "",
 				pdpe - pdpe_start, pdpe,
 				addr_hva2gpa(vm, pdpe),
-				(uint64_t) pdpe->pfn, pdpe->writable,
-				pdpe->execute_disable);
+				PTE_GET_PFN(*pdpe), !!(*pdpe & PTE_WRITABLE_MASK),
+				!!(*pdpe & PTE_NX_MASK));
 
-			pde_start = addr_gpa2hva(vm, pdpe->pfn * vm->page_size);
+			pde_start = addr_gpa2hva(vm, *pdpe & PHYSICAL_PAGE_MASK);
 			for (uint16_t n3 = 0; n3 <= 0x1ffu; n3++) {
 				pde = &pde_start[n3];
-				if (!pde->present)
+				if (!(*pde & PTE_PRESENT_MASK))
 					continue;
 				fprintf(stream, "%*spde   0x%-3zx %p "
-					"0x%-12lx 0x%-10lx %u  %u\n",
+					"0x%-12lx 0x%-10llx %u  %u\n",
 					indent, "", pde - pde_start, pde,
 					addr_hva2gpa(vm, pde),
-					(uint64_t) pde->pfn, pde->writable,
-					pde->execute_disable);
+					PTE_GET_PFN(*pde), !!(*pde & PTE_WRITABLE_MASK),
+					!!(*pde & PTE_NX_MASK));
 
-				pte_start = addr_gpa2hva(vm, pde->pfn * vm->page_size);
+				pte_start = addr_gpa2hva(vm, *pde & PHYSICAL_PAGE_MASK);
 				for (uint16_t n4 = 0; n4 <= 0x1ffu; n4++) {
 					pte = &pte_start[n4];
-					if (!pte->present)
+					if (!(*pte & PTE_PRESENT_MASK))
 						continue;
 					fprintf(stream, "%*spte   0x%-3zx %p "
-						"0x%-12lx 0x%-10lx %u  %u "
+						"0x%-12lx 0x%-10llx %u  %u "
 						"    %u    0x%-10lx\n",
 						indent, "",
 						pte - pte_start, pte,
 						addr_hva2gpa(vm, pte),
-						(uint64_t) pte->pfn,
-						pte->writable,
-						pte->execute_disable,
-						pte->dirty,
+						PTE_GET_PFN(*pte),
+						!!(*pte & PTE_WRITABLE_MASK),
+						!!(*pte & PTE_NX_MASK),
+						!!(*pte & PTE_DIRTY_MASK),
 						((uint64_t) n1 << 27)
 							| ((uint64_t) n2 << 18)
 							| ((uint64_t) n3 << 9)
@@ -558,8 +520,8 @@ static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector,
 vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 {
 	uint16_t index[4];
-	struct pageUpperEntry *pml4e, *pdpe, *pde;
-	struct pageTableEntry *pte;
+	uint64_t *pml4e, *pdpe, *pde;
+	uint64_t *pte;
 
 	TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
 		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
@@ -572,22 +534,22 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 	if (!vm->pgd_created)
 		goto unmapped_gva;
 	pml4e = addr_gpa2hva(vm, vm->pgd);
-	if (!pml4e[index[3]].present)
+	if (!(pml4e[index[3]] & PTE_PRESENT_MASK))
 		goto unmapped_gva;
 
-	pdpe = addr_gpa2hva(vm, pml4e[index[3]].pfn * vm->page_size);
-	if (!pdpe[index[2]].present)
+	pdpe = addr_gpa2hva(vm, PTE_GET_PFN(pml4e[index[3]]) * vm->page_size);
+	if (!(pdpe[index[2]] & PTE_PRESENT_MASK))
 		goto unmapped_gva;
 
-	pde = addr_gpa2hva(vm, pdpe[index[2]].pfn * vm->page_size);
-	if (!pde[index[1]].present)
+	pde = addr_gpa2hva(vm, PTE_GET_PFN(pdpe[index[2]]) * vm->page_size);
+	if (!(pde[index[1]] & PTE_PRESENT_MASK))
 		goto unmapped_gva;
 
-	pte = addr_gpa2hva(vm, pde[index[1]].pfn * vm->page_size);
-	if (!pte[index[0]].present)
+	pte = addr_gpa2hva(vm, PTE_GET_PFN(pde[index[1]]) * vm->page_size);
+	if (!(pte[index[0]] & PTE_PRESENT_MASK))
 		goto unmapped_gva;
 
-	return (pte[index[0]].pfn * vm->page_size) + (gva & 0xfffu);
+	return (PTE_GET_PFN(pte[index[0]]) * vm->page_size) + (gva & ~PAGE_MASK);
 
 unmapped_gva:
 	TEST_FAIL("No mapping for vm virtual address, gva: 0x%lx", gva);
diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c
index 52a3ef6629e8..76f65c22796f 100644
--- a/tools/testing/selftests/kvm/x86_64/amx_test.c
+++ b/tools/testing/selftests/kvm/x86_64/amx_test.c
@@ -29,7 +29,6 @@
 #define X86_FEATURE_XSAVE		(1 << 26)
 #define X86_FEATURE_OSXSAVE		(1 << 27)
 
-#define PAGE_SIZE			(1 << 12)
 #define NUM_TILES			8
 #define TILE_SIZE			1024
 #define XSAVE_SIZE			((NUM_TILES * TILE_SIZE) + PAGE_SIZE)
diff --git a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c
index f070ff0224fa..aeb3850f81bd 100644
--- a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c
+++ b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c
@@ -12,7 +12,6 @@
 #include "vmx.h"
 
 #define VCPU_ID	   1
-#define PAGE_SIZE  4096
 #define MAXPHYADDR 36
 
 #define MEM_REGION_GVA	0x0000123456789000
diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c
index a626d40fdb48..b4e0c860769e 100644
--- a/tools/testing/selftests/kvm/x86_64/smm_test.c
+++ b/tools/testing/selftests/kvm/x86_64/smm_test.c
@@ -21,8 +21,6 @@
 
 #define VCPU_ID	      1
 
-#define PAGE_SIZE  4096
-
 #define SMRAM_SIZE 65536
 #define SMRAM_MEMSLOT ((1 << 16) | 1)
 #define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE)
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
index e683d0ac3e45..19b35c607dc6 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
@@ -32,7 +32,6 @@
 #define MSR_IA32_TSC_ADJUST 0x3b
 #endif
 
-#define PAGE_SIZE	4096
 #define VCPU_ID		5
 
 #define TSC_ADJUST_VALUE (1ll << 32)
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 865e17146815..bcd370827859 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -23,7 +23,6 @@
 #define SHINFO_REGION_GVA	0xc0000000ULL
 #define SHINFO_REGION_GPA	0xc0000000ULL
 #define SHINFO_REGION_SLOT	10
-#define PAGE_SIZE		4096
 
 #define DUMMY_REGION_GPA	(SHINFO_REGION_GPA + (2 * PAGE_SIZE))
 #define DUMMY_REGION_SLOT	11
diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c
index adc94452b57c..b30fe9de1d4f 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c
@@ -15,7 +15,6 @@
 
 #define HCALL_REGION_GPA	0xc0000000ULL
 #define HCALL_REGION_SLOT	10
-#define PAGE_SIZE		4096
 
 static struct kvm_vm *vm;
 
diff --git a/tools/testing/selftests/mqueue/mq_perf_tests.c b/tools/testing/selftests/mqueue/mq_perf_tests.c
index b019e0b8221c..84fda3b49073 100644
--- a/tools/testing/selftests/mqueue/mq_perf_tests.c
+++ b/tools/testing/selftests/mqueue/mq_perf_tests.c
@@ -180,6 +180,9 @@ void shutdown(int exit_val, char *err_cause, int line_no)
 	if (in_shutdown++)
 		return;
 
+	/* Free the cpu_set allocated using CPU_ALLOC in main function */
+	CPU_FREE(cpu_set);
+
 	for (i = 0; i < num_cpus_to_pin; i++)
 		if (cpu_threads[i]) {
 			pthread_kill(cpu_threads[i], SIGUSR1);
@@ -551,6 +554,12 @@ int main(int argc, char *argv[])
 		perror("sysconf(_SC_NPROCESSORS_ONLN)");
 		exit(1);
 	}
+
+	if (getuid() != 0)
+		ksft_exit_skip("Not running as root, but almost all tests "
+			"require root in order to modify\nsystem settings.  "
+			"Exiting.\n");
+
 	cpus_online = min(MAX_CPUS, sysconf(_SC_NPROCESSORS_ONLN));
 	cpu_set = CPU_ALLOC(cpus_online);
 	if (cpu_set == NULL) {
@@ -589,7 +598,7 @@ int main(int argc, char *argv[])
 						cpu_set)) {
 					fprintf(stderr, "Any given CPU may "
 						"only be given once.\n");
-					exit(1);
+					goto err_code;
 				} else
 					CPU_SET_S(cpus_to_pin[cpu],
 						  cpu_set_size, cpu_set);
@@ -607,7 +616,7 @@ int main(int argc, char *argv[])
 				queue_path = malloc(strlen(option) + 2);
 				if (!queue_path) {
 					perror("malloc()");
-					exit(1);
+					goto err_code;
 				}
 				queue_path[0] = '/';
 				queue_path[1] = 0;
@@ -622,17 +631,12 @@ int main(int argc, char *argv[])
 		fprintf(stderr, "Must pass at least one CPU to continuous "
 			"mode.\n");
 		poptPrintUsage(popt_context, stderr, 0);
-		exit(1);
+		goto err_code;
 	} else if (!continuous_mode) {
 		num_cpus_to_pin = 1;
 		cpus_to_pin[0] = cpus_online - 1;
 	}
 
-	if (getuid() != 0)
-		ksft_exit_skip("Not running as root, but almost all tests "
-			"require root in order to modify\nsystem settings.  "
-			"Exiting.\n");
-
 	max_msgs = fopen(MAX_MSGS, "r+");
 	max_msgsize = fopen(MAX_MSGSIZE, "r+");
 	if (!max_msgs)
@@ -740,4 +744,9 @@ int main(int argc, char *argv[])
 			sleep(1);
 	}
 	shutdown(0, "", 0);
+
+err_code:
+	CPU_FREE(cpu_set);
+	exit(1);
+
 }
diff --git a/tools/testing/selftests/vm/mremap_test.c b/tools/testing/selftests/vm/mremap_test.c
index 7c0b0617b9f8..db0270127aeb 100644
--- a/tools/testing/selftests/vm/mremap_test.c
+++ b/tools/testing/selftests/vm/mremap_test.c
@@ -6,9 +6,11 @@
 
 #include <errno.h>
 #include <stdlib.h>
+#include <stdio.h>
 #include <string.h>
 #include <sys/mman.h>
 #include <time.h>
+#include <stdbool.h>
 
 #include "../kselftest.h"
 
@@ -64,6 +66,59 @@ enum {
 }
 
 /*
+ * Returns false if the requested remap region overlaps with an
+ * existing mapping (e.g text, stack) else returns true.
+ */
+static bool is_remap_region_valid(void *addr, unsigned long long size)
+{
+	void *remap_addr = NULL;
+	bool ret = true;
+
+	/* Use MAP_FIXED_NOREPLACE flag to ensure region is not mapped */
+	remap_addr = mmap(addr, size, PROT_READ | PROT_WRITE,
+					 MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED,
+					 -1, 0);
+
+	if (remap_addr == MAP_FAILED) {
+		if (errno == EEXIST)
+			ret = false;
+	} else {
+		munmap(remap_addr, size);
+	}
+
+	return ret;
+}
+
+/* Returns mmap_min_addr sysctl tunable from procfs */
+static unsigned long long get_mmap_min_addr(void)
+{
+	FILE *fp;
+	int n_matched;
+	static unsigned long long addr;
+
+	if (addr)
+		return addr;
+
+	fp = fopen("/proc/sys/vm/mmap_min_addr", "r");
+	if (fp == NULL) {
+		ksft_print_msg("Failed to open /proc/sys/vm/mmap_min_addr: %s\n",
+			strerror(errno));
+		exit(KSFT_SKIP);
+	}
+
+	n_matched = fscanf(fp, "%llu", &addr);
+	if (n_matched != 1) {
+		ksft_print_msg("Failed to read /proc/sys/vm/mmap_min_addr: %s\n",
+			strerror(errno));
+		fclose(fp);
+		exit(KSFT_SKIP);
+	}
+
+	fclose(fp);
+	return addr;
+}
+
+/*
  * Returns the start address of the mapping on success, else returns
  * NULL on failure.
  */
@@ -71,11 +126,18 @@ static void *get_source_mapping(struct config c)
 {
 	unsigned long long addr = 0ULL;
 	void *src_addr = NULL;
+	unsigned long long mmap_min_addr;
+
+	mmap_min_addr = get_mmap_min_addr();
+
 retry:
 	addr += c.src_alignment;
+	if (addr < mmap_min_addr)
+		goto retry;
+
 	src_addr = mmap((void *) addr, c.region_size, PROT_READ | PROT_WRITE,
-			MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED,
-			-1, 0);
+					MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED,
+					-1, 0);
 	if (src_addr == MAP_FAILED) {
 		if (errno == EPERM || errno == EEXIST)
 			goto retry;
@@ -90,8 +152,10 @@ retry:
 	 * alignment in the tests.
 	 */
 	if (((unsigned long long) src_addr & (c.src_alignment - 1)) ||
-			!((unsigned long long) src_addr & c.src_alignment))
+			!((unsigned long long) src_addr & c.src_alignment)) {
+		munmap(src_addr, c.region_size);
 		goto retry;
+	}
 
 	if (!src_addr)
 		goto error;
@@ -140,9 +204,20 @@ static long long remap_region(struct config c, unsigned int threshold_mb,
 	if (!((unsigned long long) addr & c.dest_alignment))
 		addr = (void *) ((unsigned long long) addr | c.dest_alignment);
 
+	/* Don't destroy existing mappings unless expected to overlap */
+	while (!is_remap_region_valid(addr, c.region_size) && !c.overlapping) {
+		/* Check for unsigned overflow */
+		if (addr + c.dest_alignment < addr) {
+			ksft_print_msg("Couldn't find a valid region to remap to\n");
+			ret = -1;
+			goto out;
+		}
+		addr += c.dest_alignment;
+	}
+
 	clock_gettime(CLOCK_MONOTONIC, &t_start);
 	dest_addr = mremap(src_addr, c.region_size, c.region_size,
-			MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr);
+					  MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr);
 	clock_gettime(CLOCK_MONOTONIC, &t_end);
 
 	if (dest_addr == MAP_FAILED) {
@@ -193,7 +268,7 @@ static void run_mremap_test_case(struct test test_case, int *failures,
 
 	if (remap_time < 0) {
 		if (test_case.expect_failure)
-			ksft_test_result_pass("%s\n\tExpected mremap failure\n",
+			ksft_test_result_xfail("%s\n\tExpected mremap failure\n",
 					      test_case.name);
 		else {
 			ksft_test_result_fail("%s\n", test_case.name);
diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh
index 3b265f140c25..352ba00cf26b 100755
--- a/tools/testing/selftests/vm/run_vmtests.sh
+++ b/tools/testing/selftests/vm/run_vmtests.sh
@@ -291,11 +291,16 @@ echo "-------------------"
 echo "running mremap_test"
 echo "-------------------"
 ./mremap_test
-if [ $? -ne 0 ]; then
+ret_val=$?
+
+if [ $ret_val -eq 0 ]; then
+	echo "[PASS]"
+elif [ $ret_val -eq $ksft_skip ]; then
+	 echo "[SKIP]"
+	 exitcode=$ksft_skip
+else
 	echo "[FAIL]"
 	exitcode=1
-else
-	echo "[PASS]"
 fi
 
 echo "-----------------"
diff --git a/tools/testing/selftests/wireguard/qemu/arch/i686.config b/tools/testing/selftests/wireguard/qemu/arch/i686.config
index a85025d7206e..a9b4fe795048 100644
--- a/tools/testing/selftests/wireguard/qemu/arch/i686.config
+++ b/tools/testing/selftests/wireguard/qemu/arch/i686.config
@@ -1,3 +1,4 @@
+CONFIG_ACPI=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_CMDLINE_BOOL=y
diff --git a/tools/testing/selftests/wireguard/qemu/arch/x86_64.config b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config
index 00a1ef4869d5..45dd53a0d760 100644
--- a/tools/testing/selftests/wireguard/qemu/arch/x86_64.config
+++ b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config
@@ -1,3 +1,4 @@
+CONFIG_ACPI=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_CMDLINE_BOOL=y