Merge git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux

Merge mainline to pick up c7513c2a2714 ("crypto/arm64: aes-ce-gcm - add missing kernel_neon_begin/end pair").
author: Herbert Xu <herbert@gondor.apana.org.au> 2018-08-03 17:55:12 +0800
committer: Herbert Xu <herbert@gondor.apana.org.au> 2018-08-03 17:55:12 +0800
commit: c5f5aeef9b55b362ad5a0e04e4b41cd63b208842 (patch)
tree: 0ee2bb561e879db0a990d998359f6516dff3393b /tools
parent: crypto: rmd320 - use swap macro in rmd320_transform (diff)
parent: crypto/arm64: aes-ce-gcm - add missing kernel_neon_begin/end pair (diff)
download: linux-dev-c5f5aeef9b55b362ad5a0e04e4b41cd63b208842.tar.xz
linux-dev-c5f5aeef9b55b362ad5a0e04e4b41cd63b208842.zip
88 files changed, 1634 insertions, 385 deletions
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index caae4843cb70..16e006f708ca 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -91,6 +91,7 @@ struct kvm_regs {
 #define KVM_VGIC_V3_ADDR_TYPE_DIST	2
 #define KVM_VGIC_V3_ADDR_TYPE_REDIST	3
 #define KVM_VGIC_ITS_ADDR_TYPE		4
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION	5
 
 #define KVM_VGIC_V3_DIST_SIZE		SZ_64K
 #define KVM_VGIC_V3_REDIST_SIZE		(2 * SZ_64K)
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 04b3256f8e6d..4e76630dd655 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -91,6 +91,7 @@ struct kvm_regs {
 #define KVM_VGIC_V3_ADDR_TYPE_DIST	2
 #define KVM_VGIC_V3_ADDR_TYPE_REDIST	3
 #define KVM_VGIC_ITS_ADDR_TYPE		4
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION	5
 
 #define KVM_VGIC_V3_DIST_SIZE		SZ_64K
 #define KVM_VGIC_V3_REDIST_SIZE		(2 * SZ_64K)
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 833ed9a16adf..1b32b56a03d3 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -633,6 +633,7 @@ struct kvm_ppc_cpu_char {
 #define KVM_REG_PPC_PSSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
 
 #define KVM_REG_PPC_DEC_EXPIRY	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
+#define KVM_REG_PPC_ONLINE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf)
 
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
diff --git a/tools/arch/powerpc/include/uapi/asm/unistd.h b/tools/arch/powerpc/include/uapi/asm/unistd.h
index 389c36fd8299..ac5ba55066dd 100644
--- a/tools/arch/powerpc/include/uapi/asm/unistd.h
+++ b/tools/arch/powerpc/include/uapi/asm/unistd.h
@@ -398,5 +398,6 @@
 #define __NR_pkey_alloc		384
 #define __NR_pkey_free		385
 #define __NR_pkey_mprotect	386
+#define __NR_rseq		387
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index fb00a2fca990..5701f5cecd31 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -282,7 +282,9 @@
 #define X86_FEATURE_AMD_IBPB		(13*32+12) /* "" Indirect Branch Prediction Barrier */
 #define X86_FEATURE_AMD_IBRS		(13*32+14) /* "" Indirect Branch Restricted Speculation */
 #define X86_FEATURE_AMD_STIBP		(13*32+15) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_SSBD		(13*32+24) /* "" Speculative Store Bypass Disable */
 #define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
+#define X86_FEATURE_AMD_SSB_NO		(13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
 #define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 32f9e397a6c0..3f140eff039f 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -217,6 +217,14 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
 	int err;
 	int fd;
 
+	if (argc < 3) {
+		p_err("too few arguments, id ID and FILE path is required");
+		return -1;
+	} else if (argc > 3) {
+		p_err("too many arguments");
+		return -1;
+	}
+
 	if (!is_prefix(*argv, "id")) {
 		p_err("expected 'id' got %s", *argv);
 		return -1;
@@ -230,9 +238,6 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
 	}
 	NEXT_ARG();
 
-	if (argc != 1)
-		usage();
-
 	fd = get_fd_by_id(id);
 	if (fd < 0) {
 		p_err("can't get prog by id (%u): %s", id, strerror(errno));
diff --git a/tools/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c
index ac6b1a12c9b7..b76b77dcfd1f 100644
--- a/tools/bpf/bpftool/perf.c
+++ b/tools/bpf/bpftool/perf.c
@@ -29,9 +29,10 @@ static bool has_perf_query_support(void)
 	if (perf_query_supported)
 		goto out;
 
-	fd = open(bin_name, O_RDONLY);
+	fd = open("/", O_RDONLY);
 	if (fd < 0) {
-		p_err("perf_query_support: %s", strerror(errno));
+		p_err("perf_query_support: cannot open directory \"/\" (%s)",
+		      strerror(errno));
 		goto out;
 	}
 
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index a4f435203fef..959aa53ab678 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -90,7 +90,9 @@ static void print_boot_time(__u64 nsecs, char *buf, unsigned int size)
 	}
 
 	wallclock_secs = (real_time_ts.tv_sec - boot_time_ts.tv_sec) +
-		nsecs / 1000000000;
+		(real_time_ts.tv_nsec - boot_time_ts.tv_nsec + nsecs) /
+		1000000000;
+
 
 	if (!localtime_r(&wallclock_secs, &load_tm)) {
 		snprintf(buf, size, "%llu", nsecs / 1000000000);
@@ -692,15 +694,19 @@ static int do_load(int argc, char **argv)
 		return -1;
 	}
 
-	if (do_pin_fd(prog_fd, argv[1])) {
-		p_err("failed to pin program");
-		return -1;
-	}
+	if (do_pin_fd(prog_fd, argv[1]))
+		goto err_close_obj;
 
 	if (json_output)
 		jsonw_null(json_wtr);
 
+	bpf_object__close(obj);
+
 	return 0;
+
+err_close_obj:
+	bpf_object__close(obj);
+	return -1;
 }
 
 static int do_help(int argc, char **argv)
diff --git a/tools/build/Build.include b/tools/build/Build.include
index a4bbb984941d..950c1504ca37 100644
--- a/tools/build/Build.include
+++ b/tools/build/Build.include
@@ -63,8 +63,8 @@ dep-cmd = $(if $(wildcard $(fixdep)),
            $(fixdep) $(depfile) $@ '$(make-cmd)' > $(dot-target).tmp;           \
            rm -f $(depfile);                                                    \
            mv -f $(dot-target).tmp $(dot-target).cmd,                           \
-           printf '\# cannot find fixdep (%s)\n' $(fixdep) > $(dot-target).cmd; \
-           printf '\# using basic dep data\n\n' >> $(dot-target).cmd;           \
+           printf '$(pound) cannot find fixdep (%s)\n' $(fixdep) > $(dot-target).cmd; \
+           printf '$(pound) using basic dep data\n\n' >> $(dot-target).cmd;           \
            cat $(depfile) >> $(dot-target).cmd;                                 \
            printf '\n%s\n' 'cmd_$@ := $(make-cmd)' >> $(dot-target).cmd)
 
@@ -98,4 +98,4 @@ cxx_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CXXFLAGS) -D"BUILD_STR(s)=\#s" $(CXX
 ###
 ## HOSTCC C flags
 
-host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CHOSTFLAGS) -D"BUILD_STR(s)=\#s" $(CHOSTFLAGS_$(basetarget).o) $(CHOSTFLAGS_$(obj))
+host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(HOSTCFLAGS) -D"BUILD_STR(s)=\#s" $(HOSTCFLAGS_$(basetarget).o) $(HOSTCFLAGS_$(obj))
diff --git a/tools/build/Makefile b/tools/build/Makefile
index 5eb4b5ad79cb..5edf65e684ab 100644
--- a/tools/build/Makefile
+++ b/tools/build/Makefile
@@ -43,7 +43,7 @@ $(OUTPUT)fixdep-in.o: FORCE
 	$(Q)$(MAKE) $(build)=fixdep
 
 $(OUTPUT)fixdep: $(OUTPUT)fixdep-in.o
-	$(QUIET_LINK)$(HOSTCC) $(LDFLAGS) -o $@ $<
+	$(QUIET_LINK)$(HOSTCC) $(HOSTLDFLAGS) -o $@ $<
 
 FORCE:
 
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 6fdff5945c8a..9c660e1688ab 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -680,6 +680,13 @@ struct drm_get_cap {
  */
 #define DRM_CLIENT_CAP_ATOMIC	3
 
+/**
+ * DRM_CLIENT_CAP_ASPECT_RATIO
+ *
+ * If set to 1, the DRM core will provide aspect ratio information in modes.
+ */
+#define DRM_CLIENT_CAP_ASPECT_RATIO    4
+
 /** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
 struct drm_set_client_cap {
 	__u64 capability;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e0b06784f227..59b19b6a40d7 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2630,7 +2630,7 @@ struct bpf_fib_lookup {
 	union {
 		/* inputs to lookup */
 		__u8	tos;		/* AF_INET  */
-		__be32	flowlabel;	/* AF_INET6 */
+		__be32	flowinfo;	/* AF_INET6, flow_label + priority */
 
 		/* output: metric of fib result (IPv4/IPv6 only) */
 		__u32	rt_metric;
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 68699f654118..cf01b6824244 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -333,6 +333,7 @@ enum {
 	IFLA_BRPORT_BCAST_FLOOD,
 	IFLA_BRPORT_GROUP_FWD_MASK,
 	IFLA_BRPORT_NEIGH_SUPPRESS,
+	IFLA_BRPORT_ISOLATED,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -516,6 +517,7 @@ enum {
 	IFLA_VXLAN_COLLECT_METADATA,
 	IFLA_VXLAN_LABEL,
 	IFLA_VXLAN_GPE,
+	IFLA_VXLAN_TTL_INHERIT,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 39e364c70caf..b6270a3b38e9 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -948,6 +948,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_BPB 152
 #define KVM_CAP_GET_MSR_FEATURES 153
 #define KVM_CAP_HYPERV_EVENTFD 154
+#define KVM_CAP_HYPERV_TLBFLUSH 155
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 38047c6aa575..f4a25bd1871f 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -164,6 +164,7 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func,
 		"lbug_with_loc",
 		"fortify_panic",
 		"usercopy_abort",
+		"machine_real_restart",
 	};
 
 	if (func->bind == STB_WEAK)
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 4e60e105583e..7ec85d567598 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -302,19 +302,34 @@ static int read_symbols(struct elf *elf)
 				continue;
 			sym->pfunc = sym->cfunc = sym;
 			coldstr = strstr(sym->name, ".cold.");
-			if (coldstr) {
-				coldstr[0] = '\0';
-				pfunc = find_symbol_by_name(elf, sym->name);
-				coldstr[0] = '.';
-
-				if (!pfunc) {
-					WARN("%s(): can't find parent function",
-					     sym->name);
-					goto err;
-				}
-
-				sym->pfunc = pfunc;
-				pfunc->cfunc = sym;
+			if (!coldstr)
+				continue;
+
+			coldstr[0] = '\0';
+			pfunc = find_symbol_by_name(elf, sym->name);
+			coldstr[0] = '.';
+
+			if (!pfunc) {
+				WARN("%s(): can't find parent function",
+				     sym->name);
+				goto err;
+			}
+
+			sym->pfunc = pfunc;
+			pfunc->cfunc = sym;
+
+			/*
+			 * Unfortunately, -fnoreorder-functions puts the child
+			 * inside the parent.  Remove the overlap so we can
+			 * have sane assumptions.
+			 *
+			 * Note that pfunc->len now no longer matches
+			 * pfunc->sym.st_size.
+			 */
+			if (sym->sec == pfunc->sec &&
+			    sym->offset >= pfunc->offset &&
+			    sym->offset + sym->len == pfunc->offset + pfunc->len) {
+				pfunc->len -= sym->len;
 			}
 		}
 	}
@@ -504,10 +519,12 @@ struct section *elf_create_section(struct elf *elf, const char *name,
 	sec->sh.sh_flags = SHF_ALLOC;
 
 
-	/* Add section name to .shstrtab */
+	/* Add section name to .shstrtab (or .strtab for Clang) */
 	shstrtab = find_section_by_name(elf, ".shstrtab");
+	if (!shstrtab)
+		shstrtab = find_section_by_name(elf, ".strtab");
 	if (!shstrtab) {
-		WARN("can't find .shstrtab section");
+		WARN("can't find .shstrtab or .strtab section");
 		return NULL;
 	}
 
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 5dfe102fb5b5..b10a90b6a718 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -178,6 +178,9 @@ Print count deltas for fixed number of times.
 This option should be used together with "-I" option.
 	example: 'perf stat -I 1000 --interval-count 2 -e cycles -a'
 
+--interval-clear::
+Clear the screen before next interval.
+
 --timeout msecs::
 Stop the 'perf stat' session and print count deltas after N milliseconds (minimum: 10 ms).
 This option is not supported with the "-I" option.
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index b5ac356ba323..f5a3b402589e 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -207,8 +207,7 @@ ifdef PYTHON_CONFIG
   PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
   PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
   PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
-  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
-  PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
+  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null)
   FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
 endif
 
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index 3598b8b75d27..ef5d59a5742e 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -243,7 +243,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
 	u64 ip;
 	u64 skip_slot = -1;
 
-	if (chain->nr < 3)
+	if (!chain || chain->nr < 3)
 		return skip_slot;
 
 	ip = chain->ips[2];
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 4dfe42666d0c..f0b1709a5ffb 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -341,6 +341,8 @@
 330	common	pkey_alloc		__x64_sys_pkey_alloc
 331	common	pkey_free		__x64_sys_pkey_free
 332	common	statx			__x64_sys_statx
+333	common	io_pgetevents		__x64_sys_io_pgetevents
+334	common	rseq			__x64_sys_rseq
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index 4b2caf6d48e7..fead6b3b4206 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -226,7 +226,7 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op)
 		else if (rm[2].rm_so != rm[2].rm_eo)
 			prefix[0] = '+';
 		else
-			strncpy(prefix, "+0", 2);
+			scnprintf(prefix, sizeof(prefix), "+0");
 	}
 
 	/* Rename register */
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 63eb49082774..44195514b19e 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -1098,7 +1098,7 @@ static void *worker_thread(void *__tdata)
 	u8 *global_data;
 	u8 *process_data;
 	u8 *thread_data;
-	u64 bytes_done;
+	u64 bytes_done, secs;
 	long work_done;
 	u32 l;
 	struct rusage rusage;
@@ -1254,7 +1254,8 @@ static void *worker_thread(void *__tdata)
 	timersub(&stop, &start0, &diff);
 	td->runtime_ns = diff.tv_sec * NSEC_PER_SEC;
 	td->runtime_ns += diff.tv_usec * NSEC_PER_USEC;
-	td->speed_gbs = bytes_done / (td->runtime_ns / NSEC_PER_SEC) / 1e9;
+	secs = td->runtime_ns / NSEC_PER_SEC;
+	td->speed_gbs = secs ? bytes_done / secs / 1e9 : 0;
 
 	getrusage(RUSAGE_THREAD, &rusage);
 	td->system_time_ns = rusage.ru_stime.tv_sec * NSEC_PER_SEC;
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 5eb22cc56363..8180319285af 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -283,6 +283,15 @@ out_put:
 	return ret;
 }
 
+static int process_feature_event(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session)
+{
+	if (event->feat.feat_id < HEADER_LAST_FEATURE)
+		return perf_event__process_feature(tool, event, session);
+	return 0;
+}
+
 static int hist_entry__tty_annotate(struct hist_entry *he,
 				    struct perf_evsel *evsel,
 				    struct perf_annotate *ann)
@@ -471,7 +480,7 @@ int cmd_annotate(int argc, const char **argv)
 			.attr	= perf_event__process_attr,
 			.build_id = perf_event__process_build_id,
 			.tracing_data   = perf_event__process_tracing_data,
-			.feature	= perf_event__process_feature,
+			.feature	= process_feature_event,
 			.ordered_events = true,
 			.ordering_requires_timestamps = true,
 		},
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 307b3594525f..6a8738f7ead3 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -56,16 +56,16 @@ struct c2c_hist_entry {
 
 	struct compute_stats	 cstats;
 
+	unsigned long		 paddr;
+	unsigned long		 paddr_cnt;
+	bool			 paddr_zero;
+	char			*nodestr;
+
 	/*
 	 * must be at the end,
 	 * because of its callchain dynamic entry
 	 */
 	struct hist_entry	he;
-
-	unsigned long		 paddr;
-	unsigned long		 paddr_cnt;
-	bool			 paddr_zero;
-	char			*nodestr;
 };
 
 static char const *coalesce_default = "pid,iaddr";
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index cdb5b6949832..c04dc7b53797 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -217,7 +217,8 @@ static int process_feature_event(struct perf_tool *tool,
 	}
 
 	/*
-	 * All features are received, we can force the
+	 * (feat_id = HEADER_LAST_FEATURE) is the end marker which
+	 * means all features are received, now we can force the
 	 * group if needed.
 	 */
 	setup_forced_leader(rep, session->evlist);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index b3bf35512d21..568ddfac3213 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -180,6 +180,18 @@ static struct {
 				  PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE
 	},
 
+	[PERF_TYPE_HW_CACHE] = {
+		.user_set = false,
+
+		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+			      PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD,
+
+		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
+	},
+
 	[PERF_TYPE_RAW] = {
 		.user_set = false,
 
@@ -1822,6 +1834,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	struct perf_evlist *evlist;
 	struct perf_evsel *evsel, *pos;
 	int err;
+	static struct perf_evsel_script *es;
 
 	err = perf_event__process_attr(tool, event, pevlist);
 	if (err)
@@ -1830,6 +1843,19 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	evlist = *pevlist;
 	evsel = perf_evlist__last(*pevlist);
 
+	if (!evsel->priv) {
+		if (scr->per_event_dump) {
+			evsel->priv = perf_evsel_script__new(evsel,
+						scr->session->data);
+		} else {
+			es = zalloc(sizeof(*es));
+			if (!es)
+				return -ENOMEM;
+			es->fp = stdout;
+			evsel->priv = es;
+		}
+	}
+
 	if (evsel->attr.type >= PERF_TYPE_MAX &&
 	    evsel->attr.type != PERF_TYPE_SYNTH)
 		return 0;
@@ -3018,6 +3044,15 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
 	return set_maps(script);
 }
 
+static int process_feature_event(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session)
+{
+	if (event->feat.feat_id < HEADER_LAST_FEATURE)
+		return perf_event__process_feature(tool, event, session);
+	return 0;
+}
+
 #ifdef HAVE_AUXTRACE_SUPPORT
 static int perf_script__process_auxtrace_info(struct perf_tool *tool,
 					      union perf_event *event,
@@ -3062,7 +3097,7 @@ int cmd_script(int argc, const char **argv)
 			.attr		 = process_attr,
 			.event_update   = perf_event__process_event_update,
 			.tracing_data	 = perf_event__process_tracing_data,
-			.feature	 = perf_event__process_feature,
+			.feature	 = process_feature_event,
 			.build_id	 = perf_event__process_build_id,
 			.id_index	 = perf_event__process_id_index,
 			.auxtrace_info	 = perf_script__process_auxtrace_info,
@@ -3113,8 +3148,9 @@ int cmd_script(int argc, const char **argv)
 		     "+field to add and -field to remove."
 		     "Valid types: hw,sw,trace,raw,synth. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-		     "addr,symoff,period,iregs,uregs,brstack,brstacksym,flags,"
-		     "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr",
+		     "addr,symoff,srcline,period,iregs,uregs,brstack,"
+		     "brstacksym,flags,bpf-output,brstackinsn,brstackoff,"
+		     "callindent,insn,insnlen,synth,phys_addr,metric,misc",
 		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 096ccb25c11f..05be023c3f0e 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -65,6 +65,7 @@
 #include "util/tool.h"
 #include "util/string2.h"
 #include "util/metricgroup.h"
+#include "util/top.h"
 #include "asm/bug.h"
 
 #include <linux/time64.h>
@@ -144,6 +145,8 @@ static struct target target = {
 
 typedef int (*aggr_get_id_t)(struct cpu_map *m, int cpu);
 
+#define METRIC_ONLY_LEN 20
+
 static int			run_count			=  1;
 static bool			no_inherit			= false;
 static volatile pid_t		child_pid			= -1;
@@ -173,6 +176,7 @@ static struct cpu_map		*aggr_map;
 static aggr_get_id_t		aggr_get_id;
 static bool			append_file;
 static bool			interval_count;
+static bool			interval_clear;
 static const char		*output_name;
 static int			output_fd;
 static int			print_free_counters_hint;
@@ -180,6 +184,7 @@ static int			print_mixed_hw_group_error;
 static u64			*walltime_run;
 static bool			ru_display			= false;
 static struct rusage		ru_data;
+static unsigned int		metric_only_len			= METRIC_ONLY_LEN;
 
 struct perf_stat {
 	bool			 record;
@@ -967,8 +972,6 @@ static void print_metric_csv(void *ctx,
 	fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit);
 }
 
-#define METRIC_ONLY_LEN 20
-
 /* Filter out some columns that don't work well in metrics only mode */
 
 static bool valid_only_metric(const char *unit)
@@ -999,22 +1002,20 @@ static void print_metric_only(void *ctx, const char *color, const char *fmt,
 {
 	struct outstate *os = ctx;
 	FILE *out = os->fh;
-	int n;
-	char buf[1024];
-	unsigned mlen = METRIC_ONLY_LEN;
+	char buf[1024], str[1024];
+	unsigned mlen = metric_only_len;
 
 	if (!valid_only_metric(unit))
 		return;
 	unit = fixunit(buf, os->evsel, unit);
-	if (color)
-		n = color_fprintf(out, color, fmt, val);
-	else
-		n = fprintf(out, fmt, val);
-	if (n > METRIC_ONLY_LEN)
-		n = METRIC_ONLY_LEN;
 	if (mlen < strlen(unit))
 		mlen = strlen(unit) + 1;
-	fprintf(out, "%*s", mlen - n, "");
+
+	if (color)
+		mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1;
+
+	color_snprintf(str, sizeof(str), color ?: "", fmt, val);
+	fprintf(out, "%*s ", mlen, str);
 }
 
 static void print_metric_only_csv(void *ctx, const char *color __maybe_unused,
@@ -1054,7 +1055,7 @@ static void print_metric_header(void *ctx, const char *color __maybe_unused,
 	if (csv_output)
 		fprintf(os->fh, "%s%s", unit, csv_sep);
 	else
-		fprintf(os->fh, "%-*s ", METRIC_ONLY_LEN, unit);
+		fprintf(os->fh, "%*s ", metric_only_len, unit);
 }
 
 static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
@@ -1704,9 +1705,12 @@ static void print_interval(char *prefix, struct timespec *ts)
 	FILE *output = stat_config.output;
 	static int num_print_interval;
 
+	if (interval_clear)
+		puts(CONSOLE_CLEAR);
+
 	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
 
-	if (num_print_interval == 0 && !csv_output) {
+	if ((num_print_interval == 0 && !csv_output) || interval_clear) {
 		switch (stat_config.aggr_mode) {
 		case AGGR_SOCKET:
 			fprintf(output, "#           time socket cpus");
@@ -1719,7 +1723,7 @@ static void print_interval(char *prefix, struct timespec *ts)
 				fprintf(output, "             counts %*s events\n", unit_width, "unit");
 			break;
 		case AGGR_NONE:
-			fprintf(output, "#           time CPU");
+			fprintf(output, "#           time CPU    ");
 			if (!metric_only)
 				fprintf(output, "                counts %*s events\n", unit_width, "unit");
 			break;
@@ -1738,7 +1742,7 @@ static void print_interval(char *prefix, struct timespec *ts)
 		}
 	}
 
-	if (num_print_interval == 0 && metric_only)
+	if ((num_print_interval == 0 || interval_clear) && metric_only)
 		print_metric_headers(" ", true);
 	if (++num_print_interval == 25)
 		num_print_interval = 0;
@@ -2057,6 +2061,8 @@ static const struct option stat_options[] = {
 		    "(overhead is possible for values <= 100ms)"),
 	OPT_INTEGER(0, "interval-count", &stat_config.times,
 		    "print counts for fixed number of times"),
+	OPT_BOOLEAN(0, "interval-clear", &interval_clear,
+		    "clear screen in between new interval"),
 	OPT_UINTEGER(0, "timeout", &stat_config.timeout,
 		    "stop workload and print counts after a timeout period in ms (>= 10ms)"),
 	OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode,
@@ -2436,14 +2442,13 @@ static int add_default_attributes(void)
 	(PERF_COUNT_HW_CACHE_OP_PREFETCH	<<  8) |
 	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
 };
+	struct parse_events_error errinfo;
 
 	/* Set attrs if no event is selected and !null_run: */
 	if (null_run)
 		return 0;
 
 	if (transaction_run) {
-		struct parse_events_error errinfo;
-
 		if (pmu_have_event("cpu", "cycles-ct") &&
 		    pmu_have_event("cpu", "el-start"))
 			err = parse_events(evsel_list, transaction_attrs,
@@ -2454,6 +2459,7 @@ static int add_default_attributes(void)
 					   &errinfo);
 		if (err) {
 			fprintf(stderr, "Cannot set up transaction events\n");
+			parse_events_print_error(&errinfo, transaction_attrs);
 			return -1;
 		}
 		return 0;
@@ -2479,10 +2485,11 @@ static int add_default_attributes(void)
 		    pmu_have_event("msr", "smi")) {
 			if (!force_metric_only)
 				metric_only = true;
-			err = parse_events(evsel_list, smi_cost_attrs, NULL);
+			err = parse_events(evsel_list, smi_cost_attrs, &errinfo);
 		} else {
 			fprintf(stderr, "To measure SMI cost, it needs "
 				"msr/aperf/, msr/smi/ and cpu/cycles/ support\n");
+			parse_events_print_error(&errinfo, smi_cost_attrs);
 			return -1;
 		}
 		if (err) {
@@ -2517,12 +2524,13 @@ static int add_default_attributes(void)
 		if (topdown_attrs[0] && str) {
 			if (warn)
 				arch_topdown_group_warn();
-			err = parse_events(evsel_list, str, NULL);
+			err = parse_events(evsel_list, str, &errinfo);
 			if (err) {
 				fprintf(stderr,
 					"Cannot set up top down events %s: %d\n",
 					str, err);
 				free(str);
+				parse_events_print_error(&errinfo, str);
 				return -1;
 			}
 		} else {
diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c
index 0c6d1002b524..ac1bcdc17dae 100644
--- a/tools/perf/jvmti/jvmti_agent.c
+++ b/tools/perf/jvmti/jvmti_agent.c
@@ -35,6 +35,7 @@
 #include <sys/mman.h>
 #include <syscall.h> /* for gettid() */
 #include <err.h>
+#include <linux/kernel.h>
 
 #include "jvmti_agent.h"
 #include "../util/jitdump.h"
@@ -249,7 +250,7 @@ void *jvmti_open(void)
 	/*
 	 * jitdump file name
 	 */
-	snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
+	scnprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
 
 	fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666);
 	if (fd == -1)
diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build
index 17783913d330..215ba30b8534 100644
--- a/tools/perf/pmu-events/Build
+++ b/tools/perf/pmu-events/Build
@@ -1,7 +1,7 @@
 hostprogs := jevents
 
 jevents-y	+= json.o jsmn.o jevents.o
-CHOSTFLAGS_jevents.o	= -I$(srctree)/tools/include
+HOSTCFLAGS_jevents.o	= -I$(srctree)/tools/include
 pmu-events-y	+= pmu-events.o
 JDIR		=  pmu-events/arch/$(SRCARCH)
 JSON		=  $(shell [ -d $(JDIR) ] &&				\
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
index 38dfb720fb6f..54ace2f6bc36 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
@@ -31,10 +31,8 @@ def flag_str(event_name, field_name, value):
     string = ""
 
     if flag_fields[event_name][field_name]:
-	print_delim = 0
-        keys = flag_fields[event_name][field_name]['values'].keys()
-        keys.sort()
-        for idx in keys:
+        print_delim = 0
+        for idx in sorted(flag_fields[event_name][field_name]['values']):
             if not value and not idx:
                 string += flag_fields[event_name][field_name]['values'][idx]
                 break
@@ -51,14 +49,12 @@ def symbol_str(event_name, field_name, value):
     string = ""
 
     if symbolic_fields[event_name][field_name]:
-        keys = symbolic_fields[event_name][field_name]['values'].keys()
-        keys.sort()
-        for idx in keys:
+        for idx in sorted(symbolic_fields[event_name][field_name]['values']):
             if not value and not idx:
-		string = symbolic_fields[event_name][field_name]['values'][idx]
+                string = symbolic_fields[event_name][field_name]['values'][idx]
                 break
-	    if (value == idx):
-		string = symbolic_fields[event_name][field_name]['values'][idx]
+            if (value == idx):
+                string = symbolic_fields[event_name][field_name]['values'][idx]
                 break
 
     return string
@@ -74,19 +70,17 @@ def trace_flag_str(value):
     string = ""
     print_delim = 0
 
-    keys = trace_flags.keys()
-
-    for idx in keys:
-	if not value and not idx:
-	    string += "NONE"
-	    break
-
-	if idx and (value & idx) == idx:
-	    if print_delim:
-		string += " | ";
-	    string += trace_flags[idx]
-	    print_delim = 1
-	    value &= ~idx
+    for idx in trace_flags:
+        if not value and not idx:
+            string += "NONE"
+            break
+
+        if idx and (value & idx) == idx:
+            if print_delim:
+                string += " | ";
+            string += trace_flags[idx]
+            print_delim = 1
+            value &= ~idx
 
     return string
 
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
index 81a56cd2b3c1..21a7a1298094 100755
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
@@ -8,6 +8,7 @@
 # PerfEvent is the base class for all perf event sample, PebsEvent
 # is a HW base Intel x86 PEBS event, and user could add more SW/HW
 # event classes based on requirements.
+from __future__ import print_function
 
 import struct
 
@@ -44,7 +45,8 @@ class PerfEvent(object):
                 PerfEvent.event_num += 1
 
         def show(self):
-                print "PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" % (self.name, self.symbol, self.comm, self.dso)
+                print("PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" %
+                      (self.name, self.symbol, self.comm, self.dso))
 
 #
 # Basic Intel PEBS (Precise Event-based Sampling) event, whose raw buffer
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
index fdd92f699055..cac7b2542ee8 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
@@ -11,7 +11,7 @@
 try:
 	import wx
 except ImportError:
-	raise ImportError, "You need to install the wxpython lib for this script"
+	raise ImportError("You need to install the wxpython lib for this script")
 
 
 class RootFrame(wx.Frame):
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
index f6c84966e4f8..7384dcb628c4 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
@@ -5,6 +5,7 @@
 # This software may be distributed under the terms of the GNU General
 # Public License ("GPL") version 2 as published by the Free Software
 # Foundation.
+from __future__ import print_function
 
 import errno, os
 
@@ -33,7 +34,7 @@ def nsecs_str(nsecs):
     return str
 
 def add_stats(dict, key, value):
-	if not dict.has_key(key):
+	if key not in dict:
 		dict[key] = (value, value, value, 1)
 	else:
 		min, max, avg, count = dict[key]
@@ -72,10 +73,10 @@ try:
 except:
 	if not audit_package_warned:
 		audit_package_warned = True
-		print "Install the audit-libs-python package to get syscall names.\n" \
-                    "For example:\n  # apt-get install python-audit (Ubuntu)" \
-                    "\n  # yum install audit-libs-python (Fedora)" \
-                    "\n  etc.\n"
+		print("Install the audit-libs-python package to get syscall names.\n"
+                    "For example:\n  # apt-get install python-audit (Ubuntu)"
+                    "\n  # yum install audit-libs-python (Fedora)"
+                    "\n  etc.\n")
 
 def syscall_name(id):
 	try:
diff --git a/tools/perf/scripts/python/sched-migration.py b/tools/perf/scripts/python/sched-migration.py
index de66cb3b72c9..3473e7f66081 100644
--- a/tools/perf/scripts/python/sched-migration.py
+++ b/tools/perf/scripts/python/sched-migration.py
@@ -9,13 +9,17 @@
 # This software is distributed under the terms of the GNU General
 # Public License ("GPL") version 2 as published by the Free Software
 # Foundation.
-
+from __future__ import print_function
 
 import os
 import sys
 
 from collections import defaultdict
-from UserList import UserList
+try:
+    from UserList import UserList
+except ImportError:
+    # Python 3: UserList moved to the collections package
+    from collections import UserList
 
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
 	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
@@ -300,7 +304,7 @@ class TimeSliceList(UserList):
 		if i == -1:
 			return
 
-		for i in xrange(i, len(self.data)):
+		for i in range(i, len(self.data)):
 			timeslice = self.data[i]
 			if timeslice.start > end:
 				return
@@ -336,8 +340,8 @@ class SchedEventProxy:
 		on_cpu_task = self.current_tsk[headers.cpu]
 
 		if on_cpu_task != -1 and on_cpu_task != prev_pid:
-			print "Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \
-				(headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid)
+			print("Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \
+				headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid)
 
 		threads[prev_pid] = prev_comm
 		threads[next_pid] = next_comm
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 2bde505e2e7e..dd850a26d579 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -422,7 +422,7 @@ static const char *shell_test__description(char *description, size_t size,
 
 #define for_each_shell_test(dir, base, ent)	\
 	while ((ent = readdir(dir)) != NULL)	\
-		if (!is_directory(base, ent))
+		if (!is_directory(base, ent) && ent->d_name[0] != '.')
 
 static const char *shell_tests__dir(char *path, size_t size)
 {
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 7d4077068454..61211918bfba 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1309,6 +1309,11 @@ static int test__checkevent_config_cache(struct perf_evlist *evlist)
 	return 0;
 }
 
+static bool test__intel_pt_valid(void)
+{
+	return !!perf_pmu__find("intel_pt");
+}
+
 static int test__intel_pt(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel = perf_evlist__first(evlist);
@@ -1375,6 +1380,7 @@ struct evlist_test {
 	const char *name;
 	__u32 type;
 	const int id;
+	bool (*valid)(void);
 	int (*check)(struct perf_evlist *evlist);
 };
 
@@ -1648,6 +1654,7 @@ static struct evlist_test test__events[] = {
 	},
 	{
 		.name  = "intel_pt//u",
+		.valid = test__intel_pt_valid,
 		.check = test__intel_pt,
 		.id    = 52,
 	},
@@ -1686,17 +1693,24 @@ static struct terms_test test__terms[] = {
 
 static int test_event(struct evlist_test *e)
 {
+	struct parse_events_error err = { .idx = 0, };
 	struct perf_evlist *evlist;
 	int ret;
 
+	if (e->valid && !e->valid()) {
+		pr_debug("... SKIP");
+		return 0;
+	}
+
 	evlist = perf_evlist__new();
 	if (evlist == NULL)
 		return -ENOMEM;
 
-	ret = parse_events(evlist, e->name, NULL);
+	ret = parse_events(evlist, e->name, &err);
 	if (ret) {
-		pr_debug("failed to parse event '%s', err %d\n",
-			 e->name, ret);
+		pr_debug("failed to parse event '%s', err %d, str '%s'\n",
+			 e->name, ret, err.str);
+		parse_events_print_error(&err, e->name);
 	} else {
 		ret = e->check(evlist);
 	}
@@ -1714,10 +1728,11 @@ static int test_events(struct evlist_test *events, unsigned cnt)
 	for (i = 0; i < cnt; i++) {
 		struct evlist_test *e = &events[i];
 
-		pr_debug("running test %d '%s'\n", e->id, e->name);
+		pr_debug("running test %d '%s'", e->id, e->name);
 		ret1 = test_event(e);
 		if (ret1)
 			ret2 = ret1;
+		pr_debug("\n");
 	}
 
 	return ret2;
@@ -1799,7 +1814,7 @@ static int test_pmu_events(void)
 	}
 
 	while (!ret && (ent = readdir(dir))) {
-		struct evlist_test e;
+		struct evlist_test e = { .id = 0, };
 		char name[2 * NAME_MAX + 1 + 12 + 3];
 
 		/* Names containing . are special and cannot be used directly */
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index 263057039693..94e513e62b34 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -14,35 +14,40 @@ libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1
 nm -Dg $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 
 trace_libc_inet_pton_backtrace() {
-	idx=0
-	expected[0]="ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)"
-	expected[1]=".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
+
+	expected=`mktemp -u /tmp/expected.XXX`
+
+	echo "ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)" > $expected
+	echo ".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
 	case "$(uname -m)" in
 	s390x)
 		eventattr='call-graph=dwarf,max-stack=4'
-		expected[2]="gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
-		expected[3]="(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
-		expected[4]="main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
+		echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
+		echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
+		echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
 	*)
 		eventattr='max-stack=3'
-		expected[2]="getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$"
-		expected[3]=".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
+		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
 	esac
 
-	file=`mktemp -u /tmp/perf.data.XXX`
+	perf_data=`mktemp -u /tmp/perf.data.XXX`
+	perf_script=`mktemp -u /tmp/perf.script.XXX`
+	perf record -e probe_libc:inet_pton/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1
+	perf script -i $perf_data > $perf_script
 
-	perf record -e probe_libc:inet_pton/$eventattr/ -o $file ping -6 -c 1 ::1 > /dev/null 2>&1
-	perf script -i $file | while read line ; do
+	exec 3<$perf_script
+	exec 4<$expected
+	while read line <&3 && read -r pattern <&4; do
+		[ -z "$pattern" ] && break
 		echo $line
-		echo "$line" | egrep -q "${expected[$idx]}"
+		echo "$line" | egrep -q "$pattern"
 		if [ $? -ne 0 ] ; then
-			printf "FAIL: expected backtrace entry %d \"%s\" got \"%s\"\n" $idx "${expected[$idx]}" "$line"
+			printf "FAIL: expected backtrace entry \"%s\" got \"%s\"\n" "$pattern" "$line"
 			exit 1
 		fi
-		let idx+=1
-		[ -z "${expected[$idx]}" ] && break
 	done
 
 	# If any statements are executed from this point onwards,
@@ -58,6 +63,6 @@ skip_if_no_perf_probe && \
 perf probe -q $libc inet_pton && \
 trace_libc_inet_pton_backtrace
 err=$?
-rm -f ${file}
+rm -f ${perf_data} ${perf_script} ${expected}
 perf probe -q -d probe_libc:inet_pton
 exit $err
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index 55ad9793d544..4ce276efe6b4 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -17,7 +17,7 @@ skip_if_no_perf_probe || exit 2
 file=$(mktemp /tmp/temporary_file.XXXXX)
 
 trace_open_vfs_getname() {
-	evts=$(echo $(perf list syscalls:sys_enter_open* |& egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
+	evts=$(echo $(perf list syscalls:sys_enter_open* 2>&1 | egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
 	perf trace -e $evts touch $file 2>&1 | \
 	egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
 }
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 40e30a26b23c..9497d02f69e6 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -45,6 +45,7 @@ static int session_write_header(char *path)
 
 	perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY);
 	perf_header__set_feat(&session->header, HEADER_NRCPUS);
+	perf_header__set_feat(&session->header, HEADER_ARCH);
 
 	session->header.data_size += DATA_SIZE;
 
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index b085f1b3e34d..4ab663ec3e5e 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -382,7 +382,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 			gtk_tree_store_set(store, &iter, col_idx++, s, -1);
 		}
 
-		if (hists__has_callchains(hists) &&
+		if (hist_entry__has_callchains(h) &&
 		    symbol_conf.use_callchain && hists__has(hists, sym)) {
 			if (callchain_param.mode == CHAIN_GRAPH_REL)
 				total = symbol_conf.cumulate_callchain ?
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
index bf31ceab33bd..89512504551b 100644
--- a/tools/perf/util/c++/clang.cpp
+++ b/tools/perf/util/c++/clang.cpp
@@ -146,8 +146,15 @@ getBPFObjectFromModule(llvm::Module *Module)
 	raw_svector_ostream ostream(*Buffer);
 
 	legacy::PassManager PM;
-	if (TargetMachine->addPassesToEmitFile(PM, ostream,
-					       TargetMachine::CGFT_ObjectFile)) {
+	bool NotAdded;
+#if CLANG_VERSION_MAJOR < 7
+	NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream,
+						      TargetMachine::CGFT_ObjectFile);
+#else
+	NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream, nullptr,
+						      TargetMachine::CGFT_ObjectFile);
+#endif
+	if (NotAdded) {
 		llvm::errs() << "TargetMachine can't emit a file of this type\n";
 		return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr);;
 	}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 540cd2dcd3e7..653ff65aa2c3 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2129,6 +2129,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 	int cpu_nr = ff->ph->env.nr_cpus_avail;
 	u64 size = 0;
 	struct perf_header *ph = ff->ph;
+	bool do_core_id_test = true;
 
 	ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu));
 	if (!ph->env.cpu)
@@ -2183,6 +2184,13 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 		return 0;
 	}
 
+	/* On s390 the socket_id number is not related to the numbers of cpus.
+	 * The socket_id number might be higher than the numbers of cpus.
+	 * This depends on the configuration.
+	 */
+	if (ph->env.arch && !strncmp(ph->env.arch, "s390", 4))
+		do_core_id_test = false;
+
 	for (i = 0; i < (u32)cpu_nr; i++) {
 		if (do_read_u32(ff, &nr))
 			goto free_cpu;
@@ -2192,7 +2200,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 		if (do_read_u32(ff, &nr))
 			goto free_cpu;
 
-		if (nr != (u32)-1 && nr > (u32)cpu_nr) {
+		if (do_core_id_test && nr != (u32)-1 && nr > (u32)cpu_nr) {
 			pr_debug("socket_id number is too big."
 				 "You may need to upgrade the perf tool.\n");
 			goto free_cpu;
@@ -3456,7 +3464,7 @@ int perf_event__process_feature(struct perf_tool *tool,
 		pr_warning("invalid record type %d in pipe-mode\n", type);
 		return 0;
 	}
-	if (feat == HEADER_RESERVED || feat > HEADER_LAST_FEATURE) {
+	if (feat == HEADER_RESERVED || feat >= HEADER_LAST_FEATURE) {
 		pr_warning("invalid record type %d in pipe-mode\n", type);
 		return -1;
 	}
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 52e8fda93a47..828cb9794c76 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -370,9 +370,11 @@ void hists__delete_entries(struct hists *hists)
 
 static int hist_entry__init(struct hist_entry *he,
 			    struct hist_entry *template,
-			    bool sample_self)
+			    bool sample_self,
+			    size_t callchain_size)
 {
 	*he = *template;
+	he->callchain_size = callchain_size;
 
 	if (symbol_conf.cumulate_callchain) {
 		he->stat_acc = malloc(sizeof(he->stat));
@@ -473,7 +475,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
 
 	he = ops->new(callchain_size);
 	if (he) {
-		err = hist_entry__init(he, template, sample_self);
+		err = hist_entry__init(he, template, sample_self, callchain_size);
 		if (err) {
 			ops->free(he);
 			he = NULL;
@@ -619,9 +621,11 @@ __hists__add_entry(struct hists *hists,
 		.raw_data = sample->raw_data,
 		.raw_size = sample->raw_size,
 		.ops = ops,
-	};
+	}, *he = hists__findnew_entry(hists, &entry, al, sample_self);
 
-	return hists__findnew_entry(hists, &entry, al, sample_self);
+	if (!hists->has_callchains && he && he->callchain_size != 0)
+		hists->has_callchains = true;
+	return he;
 }
 
 struct hist_entry *hists__add_entry(struct hists *hists,
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 06607c434949..73049f7f0f60 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -85,6 +85,7 @@ struct hists {
 	struct events_stats	stats;
 	u64			event_stream;
 	u16			col_len[HISTC_NR_COLS];
+	bool			has_callchains;
 	int			socket_filter;
 	struct perf_hpp_list	*hpp_list;
 	struct list_head	hpp_formats;
@@ -222,8 +223,7 @@ static inline struct hists *evsel__hists(struct perf_evsel *evsel)
 
 static __pure inline bool hists__has_callchains(struct hists *hists)
 {
-	const struct perf_evsel *evsel = hists_to_evsel(hists);
-	return evsel__has_callchain(evsel);
+	return hists->has_callchains;
 }
 
 int hists__init(void);
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index ba4c9dd18643..d426761a549d 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -366,7 +366,7 @@ static int intel_pt_get_cyc(unsigned int byte, const unsigned char *buf,
 		if (len < offs)
 			return INTEL_PT_NEED_MORE_BYTES;
 		byte = buf[offs++];
-		payload |= (byte >> 1) << shift;
+		payload |= ((uint64_t)byte >> 1) << shift;
 	}
 
 	packet->type = INTEL_PT_CYC;
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 976e658e38dc..5e94857dfca2 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -266,16 +266,16 @@ static const char *kinc_fetch_script =
 "#!/usr/bin/env sh\n"
 "if ! test -d \"$KBUILD_DIR\"\n"
 "then\n"
-"	exit -1\n"
+"	exit 1\n"
 "fi\n"
 "if ! test -f \"$KBUILD_DIR/include/generated/autoconf.h\"\n"
 "then\n"
-"	exit -1\n"
+"	exit 1\n"
 "fi\n"
 "TMPDIR=`mktemp -d`\n"
 "if test -z \"$TMPDIR\"\n"
 "then\n"
-"    exit -1\n"
+"    exit 1\n"
 "fi\n"
 "cat << EOF > $TMPDIR/Makefile\n"
 "obj-y := dummy.o\n"
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 155d2570274f..da8fe57691b8 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -227,11 +227,16 @@ event_def: event_pmu |
 event_pmu:
 PE_NAME opt_pmu_config
 {
+	struct parse_events_state *parse_state = _parse_state;
+	struct parse_events_error *error = parse_state->error;
 	struct list_head *list, *orig_terms, *terms;
 
 	if (parse_events_copy_term_list($2, &orig_terms))
 		YYABORT;
 
+	if (error)
+		error->idx = @1.first_column;
+
 	ALLOC_LIST(list);
 	if (parse_events_add_pmu(_parse_state, list, $1, $2, false, false)) {
 		struct perf_pmu *pmu = NULL;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index d2fb597c9a8c..3ba6a1742f91 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -234,6 +234,74 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
 	return 0;
 }
 
+static void perf_pmu_assign_str(char *name, const char *field, char **old_str,
+				char **new_str)
+{
+	if (!*old_str)
+		goto set_new;
+
+	if (*new_str) {	/* Have new string, check with old */
+		if (strcasecmp(*old_str, *new_str))
+			pr_debug("alias %s differs in field '%s'\n",
+				 name, field);
+		zfree(old_str);
+	} else		/* Nothing new --> keep old string */
+		return;
+set_new:
+	*old_str = *new_str;
+	*new_str = NULL;
+}
+
+static void perf_pmu_update_alias(struct perf_pmu_alias *old,
+				  struct perf_pmu_alias *newalias)
+{
+	perf_pmu_assign_str(old->name, "desc", &old->desc, &newalias->desc);
+	perf_pmu_assign_str(old->name, "long_desc", &old->long_desc,
+			    &newalias->long_desc);
+	perf_pmu_assign_str(old->name, "topic", &old->topic, &newalias->topic);
+	perf_pmu_assign_str(old->name, "metric_expr", &old->metric_expr,
+			    &newalias->metric_expr);
+	perf_pmu_assign_str(old->name, "metric_name", &old->metric_name,
+			    &newalias->metric_name);
+	perf_pmu_assign_str(old->name, "value", &old->str, &newalias->str);
+	old->scale = newalias->scale;
+	old->per_pkg = newalias->per_pkg;
+	old->snapshot = newalias->snapshot;
+	memcpy(old->unit, newalias->unit, sizeof(old->unit));
+}
+
+/* Delete an alias entry. */
+static void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
+{
+	zfree(&newalias->name);
+	zfree(&newalias->desc);
+	zfree(&newalias->long_desc);
+	zfree(&newalias->topic);
+	zfree(&newalias->str);
+	zfree(&newalias->metric_expr);
+	zfree(&newalias->metric_name);
+	parse_events_terms__purge(&newalias->terms);
+	free(newalias);
+}
+
+/* Merge an alias, search in alias list. If this name is already
+ * present merge both of them to combine all information.
+ */
+static bool perf_pmu_merge_alias(struct perf_pmu_alias *newalias,
+				 struct list_head *alist)
+{
+	struct perf_pmu_alias *a;
+
+	list_for_each_entry(a, alist, list) {
+		if (!strcasecmp(newalias->name, a->name)) {
+			perf_pmu_update_alias(a, newalias);
+			perf_pmu_free_alias(newalias);
+			return true;
+		}
+	}
+	return false;
+}
+
 static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 				 char *desc, char *val,
 				 char *long_desc, char *topic,
@@ -241,9 +309,11 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 				 char *metric_expr,
 				 char *metric_name)
 {
+	struct parse_events_term *term;
 	struct perf_pmu_alias *alias;
 	int ret;
 	int num;
+	char newval[256];
 
 	alias = malloc(sizeof(*alias));
 	if (!alias)
@@ -262,6 +332,27 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 		return ret;
 	}
 
+	/* Scan event and remove leading zeroes, spaces, newlines, some
+	 * platforms have terms specified as
+	 * event=0x0091 (read from files ../<PMU>/events/<FILE>
+	 * and terms specified as event=0x91 (read from JSON files).
+	 *
+	 * Rebuild string to make alias->str member comparable.
+	 */
+	memset(newval, 0, sizeof(newval));
+	ret = 0;
+	list_for_each_entry(term, &alias->terms, list) {
+		if (ret)
+			ret += scnprintf(newval + ret, sizeof(newval) - ret,
+					 ",");
+		if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
+			ret += scnprintf(newval + ret, sizeof(newval) - ret,
+					 "%s=%#x", term->config, term->val.num);
+		else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
+			ret += scnprintf(newval + ret, sizeof(newval) - ret,
+					 "%s=%s", term->config, term->val.str);
+	}
+
 	alias->name = strdup(name);
 	if (dir) {
 		/*
@@ -285,9 +376,10 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 		snprintf(alias->unit, sizeof(alias->unit), "%s", unit);
 	}
 	alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1;
-	alias->str = strdup(val);
+	alias->str = strdup(newval);
 
-	list_add_tail(&alias->list, list);
+	if (!perf_pmu_merge_alias(alias, list))
+		list_add_tail(&alias->list, list);
 
 	return 0;
 }
@@ -303,6 +395,9 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 
 	buf[ret] = 0;
 
+	/* Remove trailing newline from sysfs file */
+	rtrim(buf);
+
 	return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL,
 				     NULL, NULL, NULL);
 }
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 46e9e19ab1ac..bc32e57d17be 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -908,14 +908,11 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	if (_PyTuple_Resize(&t, n) == -1)
 		Py_FatalError("error resizing Python tuple");
 
-	if (!dict) {
+	if (!dict)
 		call_object(handler, t, handler_name);
-	} else {
+	else
 		call_object(handler, t, default_handler_name);
-		Py_DECREF(dict);
-	}
 
-	Py_XDECREF(all_entries_dict);
 	Py_DECREF(t);
 }
 
@@ -1235,7 +1232,6 @@ static void python_process_general_event(struct perf_sample *sample,
 
 	call_object(handler, t, handler_name);
 
-	Py_DECREF(dict);
 	Py_DECREF(t);
 }
 
@@ -1627,6 +1623,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 	fprintf(ofp, "# See the perf-script-python Documentation for the list "
 		"of available functions.\n\n");
 
+	fprintf(ofp, "from __future__ import print_function\n\n");
 	fprintf(ofp, "import os\n");
 	fprintf(ofp, "import sys\n\n");
 
@@ -1636,10 +1633,10 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 	fprintf(ofp, "from Core import *\n\n\n");
 
 	fprintf(ofp, "def trace_begin():\n");
-	fprintf(ofp, "\tprint \"in trace_begin\"\n\n");
+	fprintf(ofp, "\tprint(\"in trace_begin\")\n\n");
 
 	fprintf(ofp, "def trace_end():\n");
-	fprintf(ofp, "\tprint \"in trace_end\"\n\n");
+	fprintf(ofp, "\tprint(\"in trace_end\")\n\n");
 
 	while ((event = trace_find_next_event(pevent, event))) {
 		fprintf(ofp, "def %s__%s(", event->system, event->name);
@@ -1675,7 +1672,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 			"common_secs, common_nsecs,\n\t\t\t"
 			"common_pid, common_comm)\n\n");
 
-		fprintf(ofp, "\t\tprint \"");
+		fprintf(ofp, "\t\tprint(\"");
 
 		not_first = 0;
 		count = 0;
@@ -1736,31 +1733,31 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 				fprintf(ofp, "%s", f->name);
 		}
 
-		fprintf(ofp, ")\n\n");
+		fprintf(ofp, "))\n\n");
 
-		fprintf(ofp, "\t\tprint 'Sample: {'+"
-			"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n");
+		fprintf(ofp, "\t\tprint('Sample: {'+"
+			"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}')\n\n");
 
 		fprintf(ofp, "\t\tfor node in common_callchain:");
 		fprintf(ofp, "\n\t\t\tif 'sym' in node:");
-		fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])");
+		fprintf(ofp, "\n\t\t\t\tprint(\"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name']))");
 		fprintf(ofp, "\n\t\t\telse:");
-		fprintf(ofp, "\n\t\t\t\tprint \"\t[%%x]\" %% (node['ip'])\n\n");
-		fprintf(ofp, "\t\tprint \"\\n\"\n\n");
+		fprintf(ofp, "\n\t\t\t\tprint(\"\t[%%x]\" %% (node['ip']))\n\n");
+		fprintf(ofp, "\t\tprint()\n\n");
 
 	}
 
 	fprintf(ofp, "def trace_unhandled(event_name, context, "
 		"event_fields_dict, perf_sample_dict):\n");
 
-	fprintf(ofp, "\t\tprint get_dict_as_string(event_fields_dict)\n");
-	fprintf(ofp, "\t\tprint 'Sample: {'+"
-		"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n");
+	fprintf(ofp, "\t\tprint(get_dict_as_string(event_fields_dict))\n");
+	fprintf(ofp, "\t\tprint('Sample: {'+"
+		"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}')\n\n");
 
 	fprintf(ofp, "def print_header("
 		"event_name, cpu, secs, nsecs, pid, comm):\n"
-		"\tprint \"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t"
-		"(event_name, cpu, secs, nsecs, pid, comm),\n\n");
+		"\tprint(\"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t"
+		"(event_name, cpu, secs, nsecs, pid, comm), end=\"\")\n\n");
 
 	fprintf(ofp, "def get_dict_as_string(a_dict, delimiter=' '):\n"
 		"\treturn delimiter.join"
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 7cf2d5cc038e..8bf302cafcec 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -112,6 +112,8 @@ struct hist_entry {
 
 	char			level;
 	u8			filtered;
+
+	u16			callchain_size;
 	union {
 		/*
 		 * Since perf diff only supports the stdio output, TUI
@@ -153,7 +155,7 @@ struct hist_entry {
 
 static __pure inline bool hist_entry__has_callchains(struct hist_entry *he)
 {
-	return hists__has_callchains(he->hists);
+	return he->callchain_size != 0;
 }
 
 static inline bool hist_entry__has_pairs(struct hist_entry *he)
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index ca9ef7017624..d39e4ff7d0bf 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -56,7 +56,7 @@ name as necessary to disambiguate it from others is necessary.  Note that option
 .PP
 \fB--hide column\fP do not show the specified built-in columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--hide sysfs" to hide the sysfs statistics columns as a group.
 .PP
-\fB--enable column\fP show the specified built-in columns, which are otherwise disabled, by default.  Currently the only built-in counters disabled by default are "usec" and "Time_Of_Day_Seconds".
+\fB--enable column\fP show the specified built-in columns, which are otherwise disabled, by default.  Currently the only built-in counters disabled by default are "usec", "Time_Of_Day_Seconds", "APIC" and "X2APIC".
 The column name "all" can be used to enable all disabled-by-default built-in counters.
 .PP
 \fB--show column\fP show only the specified built-in columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--show sysfs" to show the sysfs statistics columns as a group.
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index d6cff3070ebd..4d14bbbf9b63 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -109,6 +109,7 @@ unsigned int has_hwp_activity_window;	/* IA32_HWP_REQUEST[bits 41:32] */
 unsigned int has_hwp_epp;		/* IA32_HWP_REQUEST[bits 31:24] */
 unsigned int has_hwp_pkg;		/* IA32_HWP_REQUEST_PKG */
 unsigned int has_misc_feature_control;
+unsigned int first_counter_read = 1;
 
 #define RAPL_PKG		(1 << 0)
 					/* 0x610 MSR_PKG_POWER_LIMIT */
@@ -170,6 +171,8 @@ struct thread_data {
 	unsigned long long  irq_count;
 	unsigned int smi_count;
 	unsigned int cpu_id;
+	unsigned int apic_id;
+	unsigned int x2apic_id;
 	unsigned int flags;
 #define CPU_IS_FIRST_THREAD_IN_CORE	0x2
 #define CPU_IS_FIRST_CORE_IN_PACKAGE	0x4
@@ -381,19 +384,23 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
 }
 
 /*
- * Each string in this array is compared in --show and --hide cmdline.
- * Thus, strings that are proper sub-sets must follow their more specific peers.
+ * This list matches the column headers, except
+ * 1. built-in only, the sysfs counters are not here -- we learn of those at run-time
+ * 2. Core and CPU are moved to the end, we can't have strings that contain them
+ *    matching on them for --show and --hide.
  */
 struct msr_counter bic[] = {
 	{ 0x0, "usec" },
 	{ 0x0, "Time_Of_Day_Seconds" },
 	{ 0x0, "Package" },
+	{ 0x0, "Node" },
 	{ 0x0, "Avg_MHz" },
+	{ 0x0, "Busy%" },
 	{ 0x0, "Bzy_MHz" },
 	{ 0x0, "TSC_MHz" },
 	{ 0x0, "IRQ" },
 	{ 0x0, "SMI", "", 32, 0, FORMAT_DELTA, NULL},
-	{ 0x0, "Busy%" },
+	{ 0x0, "sysfs" },
 	{ 0x0, "CPU%c1" },
 	{ 0x0, "CPU%c3" },
 	{ 0x0, "CPU%c6" },
@@ -424,73 +431,73 @@ struct msr_counter bic[] = {
 	{ 0x0, "Cor_J" },
 	{ 0x0, "GFX_J" },
 	{ 0x0, "RAM_J" },
-	{ 0x0, "Core" },
-	{ 0x0, "CPU" },
 	{ 0x0, "Mod%c6" },
-	{ 0x0, "sysfs" },
 	{ 0x0, "Totl%C0" },
 	{ 0x0, "Any%C0" },
 	{ 0x0, "GFX%C0" },
 	{ 0x0, "CPUGFX%" },
-	{ 0x0, "Node%" },
+	{ 0x0, "Core" },
+	{ 0x0, "CPU" },
+	{ 0x0, "APIC" },
+	{ 0x0, "X2APIC" },
 };
 
-
-
 #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
 #define	BIC_USEC	(1ULL << 0)
 #define	BIC_TOD		(1ULL << 1)
 #define	BIC_Package	(1ULL << 2)
-#define	BIC_Avg_MHz	(1ULL << 3)
-#define	BIC_Bzy_MHz	(1ULL << 4)
-#define	BIC_TSC_MHz	(1ULL << 5)
-#define	BIC_IRQ		(1ULL << 6)
-#define	BIC_SMI		(1ULL << 7)
-#define	BIC_Busy	(1ULL << 8)
-#define	BIC_CPU_c1	(1ULL << 9)
-#define	BIC_CPU_c3	(1ULL << 10)
-#define	BIC_CPU_c6	(1ULL << 11)
-#define	BIC_CPU_c7	(1ULL << 12)
-#define	BIC_ThreadC	(1ULL << 13)
-#define	BIC_CoreTmp	(1ULL << 14)
-#define	BIC_CoreCnt	(1ULL << 15)
-#define	BIC_PkgTmp	(1ULL << 16)
-#define	BIC_GFX_rc6	(1ULL << 17)
-#define	BIC_GFXMHz	(1ULL << 18)
-#define	BIC_Pkgpc2	(1ULL << 19)
-#define	BIC_Pkgpc3	(1ULL << 20)
-#define	BIC_Pkgpc6	(1ULL << 21)
-#define	BIC_Pkgpc7	(1ULL << 22)
-#define	BIC_Pkgpc8	(1ULL << 23)
-#define	BIC_Pkgpc9	(1ULL << 24)
-#define	BIC_Pkgpc10	(1ULL << 25)
-#define BIC_CPU_LPI	(1ULL << 26)
-#define BIC_SYS_LPI	(1ULL << 27)
-#define	BIC_PkgWatt	(1ULL << 26)
-#define	BIC_CorWatt	(1ULL << 27)
-#define	BIC_GFXWatt	(1ULL << 28)
-#define	BIC_PkgCnt	(1ULL << 29)
-#define	BIC_RAMWatt	(1ULL << 30)
-#define	BIC_PKG__	(1ULL << 31)
-#define	BIC_RAM__	(1ULL << 32)
-#define	BIC_Pkg_J	(1ULL << 33)
-#define	BIC_Cor_J	(1ULL << 34)
-#define	BIC_GFX_J	(1ULL << 35)
-#define	BIC_RAM_J	(1ULL << 36)
-#define	BIC_Core	(1ULL << 37)
-#define	BIC_CPU		(1ULL << 38)
-#define	BIC_Mod_c6	(1ULL << 39)
-#define	BIC_sysfs	(1ULL << 40)
-#define	BIC_Totl_c0	(1ULL << 41)
-#define	BIC_Any_c0	(1ULL << 42)
-#define	BIC_GFX_c0	(1ULL << 43)
-#define	BIC_CPUGFX	(1ULL << 44)
-#define	BIC_Node	(1ULL << 45)
-
-#define BIC_DISABLED_BY_DEFAULT	(BIC_USEC | BIC_TOD)
+#define	BIC_Node	(1ULL << 3)
+#define	BIC_Avg_MHz	(1ULL << 4)
+#define	BIC_Busy	(1ULL << 5)
+#define	BIC_Bzy_MHz	(1ULL << 6)
+#define	BIC_TSC_MHz	(1ULL << 7)
+#define	BIC_IRQ		(1ULL << 8)
+#define	BIC_SMI		(1ULL << 9)
+#define	BIC_sysfs	(1ULL << 10)
+#define	BIC_CPU_c1	(1ULL << 11)
+#define	BIC_CPU_c3	(1ULL << 12)
+#define	BIC_CPU_c6	(1ULL << 13)
+#define	BIC_CPU_c7	(1ULL << 14)
+#define	BIC_ThreadC	(1ULL << 15)
+#define	BIC_CoreTmp	(1ULL << 16)
+#define	BIC_CoreCnt	(1ULL << 17)
+#define	BIC_PkgTmp	(1ULL << 18)
+#define	BIC_GFX_rc6	(1ULL << 19)
+#define	BIC_GFXMHz	(1ULL << 20)
+#define	BIC_Pkgpc2	(1ULL << 21)
+#define	BIC_Pkgpc3	(1ULL << 22)
+#define	BIC_Pkgpc6	(1ULL << 23)
+#define	BIC_Pkgpc7	(1ULL << 24)
+#define	BIC_Pkgpc8	(1ULL << 25)
+#define	BIC_Pkgpc9	(1ULL << 26)
+#define	BIC_Pkgpc10	(1ULL << 27)
+#define BIC_CPU_LPI	(1ULL << 28)
+#define BIC_SYS_LPI	(1ULL << 29)
+#define	BIC_PkgWatt	(1ULL << 30)
+#define	BIC_CorWatt	(1ULL << 31)
+#define	BIC_GFXWatt	(1ULL << 32)
+#define	BIC_PkgCnt	(1ULL << 33)
+#define	BIC_RAMWatt	(1ULL << 34)
+#define	BIC_PKG__	(1ULL << 35)
+#define	BIC_RAM__	(1ULL << 36)
+#define	BIC_Pkg_J	(1ULL << 37)
+#define	BIC_Cor_J	(1ULL << 38)
+#define	BIC_GFX_J	(1ULL << 39)
+#define	BIC_RAM_J	(1ULL << 40)
+#define	BIC_Mod_c6	(1ULL << 41)
+#define	BIC_Totl_c0	(1ULL << 42)
+#define	BIC_Any_c0	(1ULL << 43)
+#define	BIC_GFX_c0	(1ULL << 44)
+#define	BIC_CPUGFX	(1ULL << 45)
+#define	BIC_Core	(1ULL << 46)
+#define	BIC_CPU		(1ULL << 47)
+#define	BIC_APIC	(1ULL << 48)
+#define	BIC_X2APIC	(1ULL << 49)
+
+#define BIC_DISABLED_BY_DEFAULT	(BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
 
 unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT);
-unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs;
+unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC_X2APIC;
 
 #define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME)
 #define ENABLE_BIC(COUNTER_NAME) (bic_enabled |= COUNTER_NAME)
@@ -517,17 +524,34 @@ void help(void)
 	"when COMMAND completes.\n"
 	"If no COMMAND is specified, turbostat wakes every 5-seconds\n"
 	"to print statistics, until interrupted.\n"
-	"--add		add a counter\n"
-	"		eg. --add msr0x10,u64,cpu,delta,MY_TSC\n"
-	"--cpu	cpu-set	limit output to summary plus cpu-set:\n"
-	"		{core | package | j,k,l..m,n-p }\n"
-	"--quiet	skip decoding system configuration header\n"
-	"--interval sec.subsec	Override default 5-second measurement interval\n"
-	"--help		print this help message\n"
-	"--list		list column headers only\n"
-	"--num_iterations num   number of the measurement iterations\n"
-	"--out file	create or truncate \"file\" for all output\n"
-	"--version	print version information\n"
+	"  -a, --add	add a counter\n"
+	"		  eg. --add msr0x10,u64,cpu,delta,MY_TSC\n"
+	"  -c, --cpu	cpu-set	limit output to summary plus cpu-set:\n"
+	"		  {core | package | j,k,l..m,n-p }\n"
+	"  -d, --debug	displays usec, Time_Of_Day_Seconds and more debugging\n"
+	"  -D, --Dump	displays the raw counter values\n"
+	"  -e, --enable	[all | column]\n"
+	"		shows all or the specified disabled column\n"
+	"  -H, --hide [column|column,column,...]\n"
+	"		hide the specified column(s)\n"
+	"  -i, --interval sec.subsec\n"
+	"		Override default 5-second measurement interval\n"
+	"  -J, --Joules	displays energy in Joules instead of Watts\n"
+	"  -l, --list	list column headers only\n"
+	"  -n, --num_iterations num\n"
+	"		number of the measurement iterations\n"
+	"  -o, --out file\n"
+	"		create or truncate \"file\" for all output\n"
+	"  -q, --quiet	skip decoding system configuration header\n"
+	"  -s, --show [column|column,column,...]\n"
+	"		show only the specified column(s)\n"
+	"  -S, --Summary\n"
+	"		limits output to 1-line system summary per interval\n"
+	"  -T, --TCC temperature\n"
+	"		sets the Thermal Control Circuit temperature in\n"
+	"		  degrees Celsius\n"
+	"  -h, --help	print this help message\n"
+	"  -v, --version	print version information\n"
 	"\n"
 	"For more help, run \"man turbostat\"\n");
 }
@@ -601,6 +625,10 @@ void print_header(char *delim)
 		outp += sprintf(outp, "%sCore", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_CPU))
 		outp += sprintf(outp, "%sCPU", (printed++ ? delim : ""));
+	if (DO_BIC(BIC_APIC))
+		outp += sprintf(outp, "%sAPIC", (printed++ ? delim : ""));
+	if (DO_BIC(BIC_X2APIC))
+		outp += sprintf(outp, "%sX2APIC", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Avg_MHz))
 		outp += sprintf(outp, "%sAvg_MHz", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Busy))
@@ -880,6 +908,10 @@ int format_counters(struct thread_data *t, struct core_data *c,
 			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_CPU))
 			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+		if (DO_BIC(BIC_APIC))
+			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+		if (DO_BIC(BIC_X2APIC))
+			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 	} else {
 		if (DO_BIC(BIC_Package)) {
 			if (p)
@@ -904,6 +936,10 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		}
 		if (DO_BIC(BIC_CPU))
 			outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->cpu_id);
+		if (DO_BIC(BIC_APIC))
+			outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->apic_id);
+		if (DO_BIC(BIC_X2APIC))
+			outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->x2apic_id);
 	}
 
 	if (DO_BIC(BIC_Avg_MHz))
@@ -1231,6 +1267,12 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 	int i;
 	struct msr_counter *mp;
 
+	/* we run cpuid just the 1st time, copy the results */
+	if (DO_BIC(BIC_APIC))
+		new->apic_id = old->apic_id;
+	if (DO_BIC(BIC_X2APIC))
+		new->x2apic_id = old->x2apic_id;
+
 	/*
 	 * the timestamps from start of measurement interval are in "old"
 	 * the timestamp from end of measurement interval are in "new"
@@ -1393,6 +1435,12 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 	int i;
 	struct msr_counter *mp;
 
+	/* copy un-changing apic_id's */
+	if (DO_BIC(BIC_APIC))
+		average.threads.apic_id = t->apic_id;
+	if (DO_BIC(BIC_X2APIC))
+		average.threads.x2apic_id = t->x2apic_id;
+
 	/* remember first tv_begin */
 	if (average.threads.tv_begin.tv_sec == 0)
 		average.threads.tv_begin = t->tv_begin;
@@ -1619,6 +1667,34 @@ int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp)
 	return 0;
 }
 
+void get_apic_id(struct thread_data *t)
+{
+	unsigned int eax, ebx, ecx, edx, max_level;
+
+	eax = ebx = ecx = edx = 0;
+
+	if (!genuine_intel)
+		return;
+
+	__cpuid(0, max_level, ebx, ecx, edx);
+
+	__cpuid(1, eax, ebx, ecx, edx);
+	t->apic_id = (ebx >> 24) & 0xf;
+
+	if (max_level < 0xb)
+		return;
+
+	if (!DO_BIC(BIC_X2APIC))
+		return;
+
+	ecx = 0;
+	__cpuid(0xb, eax, ebx, ecx, edx);
+	t->x2apic_id = edx;
+
+	if (debug && (t->apic_id != t->x2apic_id))
+		fprintf(stderr, "cpu%d: apic 0x%x x2apic 0x%x\n", t->cpu_id, t->apic_id, t->x2apic_id);
+}
+
 /*
  * get_counters(...)
  * migrate to cpu
@@ -1632,7 +1708,6 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	struct msr_counter *mp;
 	int i;
 
-
 	gettimeofday(&t->tv_begin, (struct timezone *)NULL);
 
 	if (cpu_migrate(cpu)) {
@@ -1640,6 +1715,8 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		return -1;
 	}
 
+	if (first_counter_read)
+		get_apic_id(t);
 retry:
 	t->tsc = rdtsc();	/* we are running on local CPU of interest */
 
@@ -2432,6 +2509,12 @@ void set_node_data(void)
 		if (pni[pkg].count > topo.nodes_per_pkg)
 			topo.nodes_per_pkg = pni[0].count;
 
+	/* Fake 1 node per pkg for machines that don't
+	 * expose nodes and thus avoid -nan results
+	 */
+	if (topo.nodes_per_pkg == 0)
+		topo.nodes_per_pkg = 1;
+
 	for (cpu = 0; cpu < topo.num_cpus; cpu++) {
 		pkg = cpus[cpu].physical_package_id;
 		node = cpus[cpu].physical_node_id;
@@ -2879,6 +2962,7 @@ void do_sleep(void)
 	}
 }
 
+
 void turbostat_loop()
 {
 	int retval;
@@ -2892,6 +2976,7 @@ restart:
 
 	snapshot_proc_sysfs_files();
 	retval = for_all_cpus(get_counters, EVEN_COUNTERS);
+	first_counter_read = 0;
 	if (retval < -1) {
 		exit(retval);
 	} else if (retval == -1) {
@@ -4392,7 +4477,7 @@ void process_cpuid()
 	if (!quiet) {
 		fprintf(outf, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n",
 			max_level, family, model, stepping, family, model, stepping);
-		fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s\n",
+		fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s %s\n",
 			ecx & (1 << 0) ? "SSE3" : "-",
 			ecx & (1 << 3) ? "MONITOR" : "-",
 			ecx & (1 << 6) ? "SMX" : "-",
@@ -4401,6 +4486,7 @@ void process_cpuid()
 			edx & (1 << 4) ? "TSC" : "-",
 			edx & (1 << 5) ? "MSR" : "-",
 			edx & (1 << 22) ? "ACPI-TM" : "-",
+			edx & (1 << 28) ? "HT" : "-",
 			edx & (1 << 29) ? "TM" : "-");
 	}
 
@@ -4652,7 +4738,6 @@ void process_cpuid()
 	return;
 }
 
-
 /*
  * in /dev/cpu/ return success for names that are numbers
  * ie. filter out ".", "..", "microcode".
@@ -4842,6 +4927,13 @@ void init_counter(struct thread_data *thread_base, struct core_data *core_base,
 	struct core_data *c;
 	struct pkg_data *p;
 
+
+	/* Workaround for systems where physical_node_id==-1
+	 * and logical_node_id==(-1 - topo.num_cpus)
+	 */
+	if (node_id < 0)
+		node_id = 0;
+
 	t = GET_THREAD(thread_base, thread_id, core_id, node_id, pkg_id);
 	c = GET_CORE(core_base, core_id, node_id, pkg_id);
 	p = GET_PKG(pkg_base, pkg_id);
@@ -4946,6 +5038,7 @@ int fork_it(char **argv)
 
 	snapshot_proc_sysfs_files();
 	status = for_all_cpus(get_counters, EVEN_COUNTERS);
+	first_counter_read = 0;
 	if (status)
 		exit(status);
 	/* clear affinity side-effect of get_counters() */
@@ -5009,7 +5102,7 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-	fprintf(outf, "turbostat version 18.06.01"
+	fprintf(outf, "turbostat version 18.06.20"
 		" - Len Brown <lenb@kernel.org>\n");
 }
 
@@ -5381,7 +5474,7 @@ void cmdline(int argc, char **argv)
 			break;
 		case 'e':
 			/* --enable specified counter */
-			bic_enabled |= bic_lookup(optarg, SHOW_LIST);
+			bic_enabled = bic_enabled | bic_lookup(optarg, SHOW_LIST);
 			break;
 		case 'd':
 			debug++;
@@ -5465,7 +5558,6 @@ void cmdline(int argc, char **argv)
 int main(int argc, char **argv)
 {
 	outf = stderr;
-
 	cmdline(argc, argv);
 
 	if (!quiet)
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index a8fb63edcf89..e2926f72a821 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -1991,8 +1991,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	pcap->header.type = ACPI_NFIT_TYPE_CAPABILITIES;
 	pcap->header.length = sizeof(*pcap);
 	pcap->highest_capability = 1;
-	pcap->capabilities = ACPI_NFIT_CAPABILITY_CACHE_FLUSH |
-		ACPI_NFIT_CAPABILITY_MEM_FLUSH;
+	pcap->capabilities = ACPI_NFIT_CAPABILITY_MEM_FLUSH;
 	offset += pcap->header.length;
 
 	if (t->setup_hotplug) {
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 7a6214e9ae58..a362e3d7abc6 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -105,7 +105,7 @@ $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline
 
 BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
 BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
-BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --version 2>&1 | grep LLVM)
+BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm')
 
 ifneq ($(BTF_LLC_PROBE),)
 ifneq ($(BTF_PAHOLE_PROBE),)
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 1eefe211a4a8..b4994a94968b 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -6,4 +6,15 @@ CONFIG_TEST_BPF=m
 CONFIG_CGROUP_BPF=y
 CONFIG_NETDEVSIM=m
 CONFIG_NET_CLS_ACT=y
+CONFIG_NET_SCHED=y
 CONFIG_NET_SCH_INGRESS=y
+CONFIG_NET_IPIP=y
+CONFIG_IPV6=y
+CONFIG_NET_IPGRE_DEMUX=y
+CONFIG_NET_IPGRE=y
+CONFIG_IPV6_GRE=y
+CONFIG_CRYPTO_USER_API_HASH=m
+CONFIG_CRYPTO_HMAC=m
+CONFIG_CRYPTO_SHA256=m
+CONFIG_VXLAN=y
+CONFIG_GENEVE=y
diff --git a/tools/testing/selftests/bpf/test_kmod.sh b/tools/testing/selftests/bpf/test_kmod.sh
index 35669ccd4d23..9df0d2ac45f8 100755
--- a/tools/testing/selftests/bpf/test_kmod.sh
+++ b/tools/testing/selftests/bpf/test_kmod.sh
@@ -1,6 +1,15 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ "$(id -u)" != "0" ]; then
+	echo $msg please run this as root >&2
+	exit $ksft_skip
+fi
+
 SRC_TREE=../../../../
 
 test_run()
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2.sh b/tools/testing/selftests/bpf/test_lirc_mode2.sh
index ce2e15e4f976..677686198df3 100755
--- a/tools/testing/selftests/bpf/test_lirc_mode2.sh
+++ b/tools/testing/selftests/bpf/test_lirc_mode2.sh
@@ -1,6 +1,15 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ $UID != 0 ]; then
+	echo $msg please run this as root >&2
+	exit $ksft_skip
+fi
+
 GREEN='\033[0;92m'
 RED='\033[0;31m'
 NC='\033[0m' # No Color
diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh
index 1c77994b5e71..270fa8f49573 100755
--- a/tools/testing/selftests/bpf/test_lwt_seg6local.sh
+++ b/tools/testing/selftests/bpf/test_lwt_seg6local.sh
@@ -21,6 +21,15 @@
 # An UDP datagram is sent from fb00::1 to fb00::6. The test succeeds if this
 # datagram can be read on NS6 when binding to fb00::6.
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ $UID != 0 ]; then
+	echo $msg please run this as root >&2
+	exit $ksft_skip
+fi
+
 TMP_FILE="/tmp/selftest_lwt_seg6local.txt"
 
 cleanup()
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index e78aad0a68bb..be800d0e7a84 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -163,6 +163,10 @@ def bpftool(args, JSON=True, ns="", fail=True):
 
 def bpftool_prog_list(expected=None, ns=""):
     _, progs = bpftool("prog show", JSON=True, ns=ns, fail=True)
+    # Remove the base progs
+    for p in base_progs:
+        if p in progs:
+            progs.remove(p)
     if expected is not None:
         if len(progs) != expected:
             fail(True, "%d BPF programs loaded, expected %d" %
@@ -171,6 +175,10 @@ def bpftool_prog_list(expected=None, ns=""):
 
 def bpftool_map_list(expected=None, ns=""):
     _, maps = bpftool("map show", JSON=True, ns=ns, fail=True)
+    # Remove the base maps
+    for m in base_maps:
+        if m in maps:
+            maps.remove(m)
     if expected is not None:
         if len(maps) != expected:
             fail(True, "%d BPF maps loaded, expected %d" %
@@ -585,8 +593,8 @@ skip(os.getuid() != 0, "test must be run as root")
 # Check tools
 ret, progs = bpftool("prog", fail=False)
 skip(ret != 0, "bpftool not installed")
-# Check no BPF programs are loaded
-skip(len(progs) != 0, "BPF programs already loaded on the system")
+base_progs = progs
+_, base_maps = bpftool("map")
 
 # Check netdevsim
 ret, out = cmd("modprobe netdevsim", fail=False)
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 05c8cb71724a..9e78df207919 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -1413,18 +1413,12 @@ out:
 
 int main(int argc, char **argv)
 {
-	struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
 	int iov_count = 1, length = 1024, rate = 1;
 	struct sockmap_options options = {0};
 	int opt, longindex, err, cg_fd = 0;
 	char *bpf_file = BPF_SOCKMAP_FILENAME;
 	int test = PING_PONG;
 
-	if (setrlimit(RLIMIT_MEMLOCK, &r)) {
-		perror("setrlimit(RLIMIT_MEMLOCK)");
-		return 1;
-	}
-
 	if (argc < 2)
 		return test_suite();
 
diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh
index aeb2901f21f4..546aee3e9fb4 100755
--- a/tools/testing/selftests/bpf/test_tunnel.sh
+++ b/tools/testing/selftests/bpf/test_tunnel.sh
@@ -608,28 +608,26 @@ setup_xfrm_tunnel()
 test_xfrm_tunnel()
 {
 	config_device
-        #tcpdump -nei veth1 ip &
-	output=$(mktemp)
-	cat /sys/kernel/debug/tracing/trace_pipe | tee $output &
-        setup_xfrm_tunnel
+	> /sys/kernel/debug/tracing/trace
+	setup_xfrm_tunnel
 	tc qdisc add dev veth1 clsact
 	tc filter add dev veth1 proto ip ingress bpf da obj test_tunnel_kern.o \
 		sec xfrm_get_state
 	ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
 	sleep 1
-	grep "reqid 1" $output
+	grep "reqid 1" /sys/kernel/debug/tracing/trace
 	check_err $?
-	grep "spi 0x1" $output
+	grep "spi 0x1" /sys/kernel/debug/tracing/trace
 	check_err $?
-	grep "remote ip 0xac100164" $output
+	grep "remote ip 0xac100164" /sys/kernel/debug/tracing/trace
 	check_err $?
 	cleanup
 
 	if [ $ret -ne 0 ]; then
-                echo -e ${RED}"FAIL: xfrm tunnel"${NC}
-                return 1
-        fi
-        echo -e ${GREEN}"PASS: xfrm tunnel"${NC}
+		echo -e ${RED}"FAIL: xfrm tunnel"${NC}
+		return 1
+	fi
+	echo -e ${GREEN}"PASS: xfrm tunnel"${NC}
 }
 
 attach_bpf()
@@ -657,6 +655,10 @@ cleanup()
 	ip link del ip6geneve11 2> /dev/null
 	ip link del erspan11 2> /dev/null
 	ip link del ip6erspan11 2> /dev/null
+	ip xfrm policy delete dir out src 10.1.1.200/32 dst 10.1.1.100/32 2> /dev/null
+	ip xfrm policy delete dir in src 10.1.1.100/32 dst 10.1.1.200/32 2> /dev/null
+	ip xfrm state delete src 172.16.1.100 dst 172.16.1.200 proto esp spi 0x1 2> /dev/null
+	ip xfrm state delete src 172.16.1.200 dst 172.16.1.100 proto esp spi 0x2 2> /dev/null
 }
 
 cleanup_exit()
@@ -668,7 +670,7 @@ cleanup_exit()
 
 check()
 {
-	ip link help $1 2>&1 | grep -q "^Usage:"
+	ip link help 2>&1 | grep -q "\s$1\s"
 	if [ $? -ne 0 ];then
 		echo "SKIP $1: iproute2 not support"
 	cleanup
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 2ecd27b670d7..41106d9d5cc7 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -4975,6 +4975,24 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_LWT_XMIT,
 	},
 	{
+		"make headroom for LWT_XMIT",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_2, 34),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_EMIT_CALL(BPF_FUNC_skb_change_head),
+			/* split for s390 to succeed */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_MOV64_IMM(BPF_REG_2, 42),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_EMIT_CALL(BPF_FUNC_skb_change_head),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_LWT_XMIT,
+	},
+	{
 		"invalid access of tc_classid for LWT_IN",
 		.insns = {
 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
@@ -11987,6 +12005,46 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
 	{
+		"xadd/w check whether src/dst got mangled, 1",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+			BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+			BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+			BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_0, 3),
+			BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_10, 2),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 42),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.retval = 3,
+	},
+	{
+		"xadd/w check whether src/dst got mangled, 2",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+			BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -8),
+			BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -8),
+			BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -8),
+			BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_0, 3),
+			BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_10, 2),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -8),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 42),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.retval = 3,
+	},
+	{
 		"bpf_get_stack return R0 within range",
 		.insns = {
 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
@@ -12554,8 +12612,11 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	}
 
 	if (fd_prog >= 0) {
+		__u8 tmp[TEST_DATA_LEN << 2];
+		__u32 size_tmp = sizeof(tmp);
+
 		err = bpf_prog_test_run(fd_prog, 1, test->data,
-					sizeof(test->data), NULL, NULL,
+					sizeof(test->data), tmp, &size_tmp,
 					&retval, NULL);
 		if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
 			printf("Unexpected bpf_prog_test_run error\n");
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc b/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc
new file mode 100644
index 000000000000..3b1f45e13a2e
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc
@@ -0,0 +1,28 @@
+#!/bin/sh
+# description: Snapshot and tracing setting
+# flags: instance
+
+[ ! -f snapshot ] && exit_unsupported
+
+echo "Set tracing off"
+echo 0 > tracing_on
+
+echo "Allocate and take a snapshot"
+echo 1 > snapshot
+
+# Since trace buffer is empty, snapshot is also empty, but allocated
+grep -q "Snapshot is allocated" snapshot
+
+echo "Ensure keep tracing off"
+test `cat tracing_on` -eq 0
+
+echo "Set tracing on"
+echo 1 > tracing_on
+
+echo "Take a snapshot again"
+echo 1 > snapshot
+
+echo "Ensure keep tracing on"
+test `cat tracing_on` -eq 1
+
+exit 0
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 128e548aa377..1a0ac3a29ec5 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -12,3 +12,4 @@ tcp_mmap
 udpgso
 udpgso_bench_rx
 udpgso_bench_tx
+tcp_inq
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 7ba089b33e8b..cd3a2f1545b5 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -12,3 +12,5 @@ CONFIG_NET_IPVTI=y
 CONFIG_INET6_XFRM_MODE_TUNNEL=y
 CONFIG_IPV6_VTI=y
 CONFIG_DUMMY=y
+CONFIG_BRIDGE=y
+CONFIG_VLAN_8021Q=y
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 78245d60d8bc..0f45633bd634 100644..100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -740,13 +740,6 @@ ipv6_rt_add()
 	run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
 	log_test $? 2 "Attempt to add duplicate route - reject route"
 
-	# iproute2 prepend only sets NLM_F_CREATE
-	# - adds a new route; does NOT convert existing route to ECMP
-	add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
-	run_cmd "$IP -6 ro prepend 2001:db8:104::/64 via 2001:db8:103::2"
-	check_route6 "2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024 2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024"
-	log_test $? 0 "Add new route for existing prefix (w/o NLM_F_EXCL)"
-
 	# route append with same prefix adds a new route
 	# - iproute2 sets NLM_F_CREATE | NLM_F_APPEND
 	add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
@@ -754,27 +747,6 @@ ipv6_rt_add()
 	check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
 	log_test $? 0 "Append nexthop to existing route - gw"
 
-	add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
-	run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3"
-	check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop dev veth3 weight 1"
-	log_test $? 0 "Append nexthop to existing route - dev only"
-
-	# multipath route can not have a nexthop that is a reject route
-	add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
-	run_cmd "$IP -6 ro append unreachable 2001:db8:104::/64"
-	log_test $? 2 "Append nexthop to existing route - reject route"
-
-	# reject route can not be converted to multipath route
-	run_cmd "$IP -6 ro flush 2001:db8:104::/64"
-	run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
-	run_cmd "$IP -6 ro append 2001:db8:104::/64 via 2001:db8:103::2"
-	log_test $? 2 "Append nexthop to existing reject route - gw"
-
-	run_cmd "$IP -6 ro flush 2001:db8:104::/64"
-	run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
-	run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3"
-	log_test $? 2 "Append nexthop to existing reject route - dev only"
-
 	# insert mpath directly
 	add_route6 "2001:db8:104::/64" "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
 	check_route6  "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
@@ -819,13 +791,6 @@ ipv6_rt_replace_single()
 	check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::3 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
 	log_test $? 0 "Single path with multipath"
 
-	# single path with reject
-	#
-	add_initial_route6 "nexthop via 2001:db8:101::2"
-	run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64"
-	check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024"
-	log_test $? 0 "Single path with reject route"
-
 	# single path with single path using MULTIPATH attribute
 	#
 	add_initial_route6 "via 2001:db8:101::2"
@@ -873,12 +838,6 @@ ipv6_rt_replace_mpath()
 	check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024"
 	log_test $? 0 "Multipath with single path via multipath attribute"
 
-	# multipath with reject
-	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
-	run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64"
-	check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024"
-	log_test $? 0 "Multipath with reject route"
-
 	# route replace fails - invalid nexthop 1
 	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
 	run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3"
diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh
index 792fa4d0285e..850767befa47 100755
--- a/tools/testing/selftests/net/udpgso_bench.sh
+++ b/tools/testing/selftests/net/udpgso_bench.sh
@@ -35,9 +35,6 @@ run_udp() {
 
 	echo "udp gso"
 	run_in_netns ${args} -S
-
-	echo "udp gso zerocopy"
-	run_in_netns ${args} -S -z
 }
 
 run_tcp() {
diff --git a/tools/testing/selftests/pstore/pstore_post_reboot_tests b/tools/testing/selftests/pstore/pstore_post_reboot_tests
index 6ccb154cb4aa..22f8df1ad7d4 100755
--- a/tools/testing/selftests/pstore/pstore_post_reboot_tests
+++ b/tools/testing/selftests/pstore/pstore_post_reboot_tests
@@ -7,13 +7,16 @@
 #
 # Released under the terms of the GPL v2.
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 . ./common_tests
 
 if [ -e $REBOOT_FLAG  ]; then
     rm $REBOOT_FLAG
 else
     prlog "pstore_crash_test has not been executed yet. we skip further tests."
-    exit 0
+    exit $ksft_skip
 fi
 
 prlog -n "Mounting pstore filesystem ... "
diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index 6a9f602a8718..615252331813 100644
--- a/tools/testing/selftests/rseq/param_test.c
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -137,6 +137,30 @@ unsigned int yield_mod_cnt, nr_abort;
 	"subic. %%" INJECT_ASM_REG ", %%" INJECT_ASM_REG ", 1\n\t" \
 	"bne 222b\n\t" \
 	"333:\n\t"
+
+#elif defined(__mips__)
+
+#define RSEQ_INJECT_INPUT \
+	, [loop_cnt_1]"m"(loop_cnt[1]) \
+	, [loop_cnt_2]"m"(loop_cnt[2]) \
+	, [loop_cnt_3]"m"(loop_cnt[3]) \
+	, [loop_cnt_4]"m"(loop_cnt[4]) \
+	, [loop_cnt_5]"m"(loop_cnt[5]) \
+	, [loop_cnt_6]"m"(loop_cnt[6])
+
+#define INJECT_ASM_REG	"$5"
+
+#define RSEQ_INJECT_CLOBBER \
+	, INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+	"lw " INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \
+	"beqz " INJECT_ASM_REG ", 333f\n\t" \
+	"222:\n\t" \
+	"addiu " INJECT_ASM_REG ", -1\n\t" \
+	"bnez " INJECT_ASM_REG ", 222b\n\t" \
+	"333:\n\t"
+
 #else
 #error unsupported target
 #endif
diff --git a/tools/testing/selftests/rseq/rseq-arm.h b/tools/testing/selftests/rseq/rseq-arm.h
index 3b055f9aeaab..3cea19877227 100644
--- a/tools/testing/selftests/rseq/rseq-arm.h
+++ b/tools/testing/selftests/rseq/rseq-arm.h
@@ -57,6 +57,7 @@ do {									\
 #define __RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown,		\
 				abort_label, version, flags,		\
 				start_ip, post_commit_offset, abort_ip)	\
+		".balign 32\n\t"					\
 		__rseq_str(table_label) ":\n\t"				\
 		".word " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
 		".word " __rseq_str(start_ip) ", 0x0, " __rseq_str(post_commit_offset) ", 0x0, " __rseq_str(abort_ip) ", 0x0\n\t" \
diff --git a/tools/testing/selftests/rseq/rseq-mips.h b/tools/testing/selftests/rseq/rseq-mips.h
new file mode 100644
index 000000000000..7f48ecf46994
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-mips.h
@@ -0,0 +1,725 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Author: Paul Burton <paul.burton@mips.com>
+ * (C) Copyright 2018 MIPS Tech LLC
+ *
+ * Based on rseq-arm.h:
+ * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#define RSEQ_SIG	0x53053053
+
+#define rseq_smp_mb()	__asm__ __volatile__ ("sync" ::: "memory")
+#define rseq_smp_rmb()	rseq_smp_mb()
+#define rseq_smp_wmb()	rseq_smp_mb()
+
+#define rseq_smp_load_acquire(p)					\
+__extension__ ({							\
+	__typeof(*p) ____p1 = RSEQ_READ_ONCE(*p);			\
+	rseq_smp_mb();							\
+	____p1;								\
+})
+
+#define rseq_smp_acquire__after_ctrl_dep()	rseq_smp_rmb()
+
+#define rseq_smp_store_release(p, v)					\
+do {									\
+	rseq_smp_mb();							\
+	RSEQ_WRITE_ONCE(*p, v);						\
+} while (0)
+
+#ifdef RSEQ_SKIP_FASTPATH
+#include "rseq-skip.h"
+#else /* !RSEQ_SKIP_FASTPATH */
+
+#if _MIPS_SZLONG == 64
+# define LONG			".dword"
+# define LONG_LA		"dla"
+# define LONG_L			"ld"
+# define LONG_S			"sd"
+# define LONG_ADDI		"daddiu"
+# define U32_U64_PAD(x)		x
+#elif _MIPS_SZLONG == 32
+# define LONG			".word"
+# define LONG_LA		"la"
+# define LONG_L			"lw"
+# define LONG_S			"sw"
+# define LONG_ADDI		"addiu"
+# ifdef __BIG_ENDIAN
+#  define U32_U64_PAD(x)	"0x0, " x
+# else
+#  define U32_U64_PAD(x)	x ", 0x0"
+# endif
+#else
+# error unsupported _MIPS_SZLONG
+#endif
+
+#define __RSEQ_ASM_DEFINE_TABLE(version, flags,	start_ip, \
+				post_commit_offset, abort_ip) \
+		".pushsection __rseq_table, \"aw\"\n\t" \
+		".balign 32\n\t" \
+		".word " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+		LONG " " U32_U64_PAD(__rseq_str(start_ip)) "\n\t" \
+		LONG " " U32_U64_PAD(__rseq_str(post_commit_offset)) "\n\t" \
+		LONG " " U32_U64_PAD(__rseq_str(abort_ip)) "\n\t" \
+		".popsection\n\t"
+
+#define RSEQ_ASM_DEFINE_TABLE(start_ip, post_commit_ip, abort_ip) \
+	__RSEQ_ASM_DEFINE_TABLE(0x0, 0x0, start_ip, \
+				(post_commit_ip - start_ip), abort_ip)
+
+#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs) \
+		RSEQ_INJECT_ASM(1) \
+		LONG_LA " $4, " __rseq_str(cs_label) "\n\t" \
+		LONG_S  " $4, %[" __rseq_str(rseq_cs) "]\n\t" \
+		__rseq_str(label) ":\n\t"
+
+#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label) \
+		RSEQ_INJECT_ASM(2) \
+		"lw  $4, %[" __rseq_str(current_cpu_id) "]\n\t" \
+		"bne $4, %[" __rseq_str(cpu_id) "], " __rseq_str(label) "\n\t"
+
+#define __RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, \
+				abort_label, version, flags, \
+				start_ip, post_commit_offset, abort_ip) \
+		".balign 32\n\t" \
+		__rseq_str(table_label) ":\n\t" \
+		".word " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+		LONG " " U32_U64_PAD(__rseq_str(start_ip)) "\n\t" \
+		LONG " " U32_U64_PAD(__rseq_str(post_commit_offset)) "\n\t" \
+		LONG " " U32_U64_PAD(__rseq_str(abort_ip)) "\n\t" \
+		".word " __rseq_str(RSEQ_SIG) "\n\t" \
+		__rseq_str(label) ":\n\t" \
+		teardown \
+		"b %l[" __rseq_str(abort_label) "]\n\t"
+
+#define RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, abort_label, \
+			      start_ip, post_commit_ip, abort_ip) \
+	__RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, \
+				abort_label, 0x0, 0x0, start_ip, \
+				(post_commit_ip - start_ip), abort_ip)
+
+#define RSEQ_ASM_DEFINE_CMPFAIL(label, teardown, cmpfail_label) \
+		__rseq_str(label) ":\n\t" \
+		teardown \
+		"b %l[" __rseq_str(cmpfail_label) "]\n\t"
+
+#define rseq_workaround_gcc_asm_size_guess()	__asm__ __volatile__("")
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	rseq_workaround_gcc_asm_size_guess();
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], %l[error2]\n\t"
+#endif
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(5)
+		"b 5f\n\t"
+		RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+		"5:\n\t"
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "$4", "memory"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_workaround_gcc_asm_size_guess();
+	return 0;
+abort:
+	rseq_workaround_gcc_asm_size_guess();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_workaround_gcc_asm_size_guess();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+			       off_t voffp, intptr_t *load, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	rseq_workaround_gcc_asm_size_guess();
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_L " $4, %[v]\n\t"
+		"beq $4, %[expectnot], %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_L " $4, %[v]\n\t"
+		"beq $4, %[expectnot], %l[error2]\n\t"
+#endif
+		LONG_S " $4, %[load]\n\t"
+		LONG_ADDI " $4, %[voffp]\n\t"
+		LONG_L " $4, 0($4)\n\t"
+		/* final store */
+		LONG_S " $4, %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(5)
+		"b 5f\n\t"
+		RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+		"5:\n\t"
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expectnot]		"r" (expectnot),
+		  [voffp]		"Ir" (voffp),
+		  [load]		"m" (*load)
+		  RSEQ_INJECT_INPUT
+		: "$4", "memory"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_workaround_gcc_asm_size_guess();
+	return 0;
+abort:
+	rseq_workaround_gcc_asm_size_guess();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_workaround_gcc_asm_size_guess();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_addv(intptr_t *v, intptr_t count, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	rseq_workaround_gcc_asm_size_guess();
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+#endif
+		LONG_L " $4, %[v]\n\t"
+		LONG_ADDI " $4, %[count]\n\t"
+		/* final store */
+		LONG_S " $4, %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(4)
+		"b 5f\n\t"
+		RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+		"5:\n\t"
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [v]			"m" (*v),
+		  [count]		"Ir" (count)
+		  RSEQ_INJECT_INPUT
+		: "$4", "memory"
+		  RSEQ_INJECT_CLOBBER
+		: abort
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1
+#endif
+	);
+	rseq_workaround_gcc_asm_size_guess();
+	return 0;
+abort:
+	rseq_workaround_gcc_asm_size_guess();
+	RSEQ_INJECT_FAILED
+	return -1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
+				 intptr_t *v2, intptr_t newv2,
+				 intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	rseq_workaround_gcc_asm_size_guess();
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], %l[error2]\n\t"
+#endif
+		/* try store */
+		LONG_S " %[newv2], %[v2]\n\t"
+		RSEQ_INJECT_ASM(5)
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		"b 5f\n\t"
+		RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+		"5:\n\t"
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* try store input */
+		  [v2]			"m" (*v2),
+		  [newv2]		"r" (newv2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "$4", "memory"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_workaround_gcc_asm_size_guess();
+	return 0;
+abort:
+	rseq_workaround_gcc_asm_size_guess();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_workaround_gcc_asm_size_guess();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
+					 intptr_t *v2, intptr_t newv2,
+					 intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	rseq_workaround_gcc_asm_size_guess();
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], %l[error2]\n\t"
+#endif
+		/* try store */
+		LONG_S " %[newv2], %[v2]\n\t"
+		RSEQ_INJECT_ASM(5)
+		"sync\n\t"	/* full sync provides store-release */
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		"b 5f\n\t"
+		RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+		"5:\n\t"
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* try store input */
+		  [v2]			"m" (*v2),
+		  [newv2]		"r" (newv2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "$4", "memory"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_workaround_gcc_asm_size_guess();
+	return 0;
+abort:
+	rseq_workaround_gcc_asm_size_guess();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_workaround_gcc_asm_size_guess();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
+			      intptr_t *v2, intptr_t expect2,
+			      intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	rseq_workaround_gcc_asm_size_guess();
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+		LONG_L " $4, %[v2]\n\t"
+		"bne $4, %[expect2], %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(5)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], %l[error2]\n\t"
+		LONG_L " $4, %[v2]\n\t"
+		"bne $4, %[expect2], %l[error3]\n\t"
+#endif
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		"b 5f\n\t"
+		RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+		"5:\n\t"
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* cmp2 input */
+		  [v2]			"m" (*v2),
+		  [expect2]		"r" (expect2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "$4", "memory"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2, error3
+#endif
+	);
+	rseq_workaround_gcc_asm_size_guess();
+	return 0;
+abort:
+	rseq_workaround_gcc_asm_size_guess();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_workaround_gcc_asm_size_guess();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("1st expected value comparison failed");
+error3:
+	rseq_bug("2nd expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
+				 void *dst, void *src, size_t len,
+				 intptr_t newv, int cpu)
+{
+	uintptr_t rseq_scratch[3];
+
+	RSEQ_INJECT_C(9)
+
+	rseq_workaround_gcc_asm_size_guess();
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+		LONG_S " %[src], %[rseq_scratch0]\n\t"
+		LONG_S "  %[dst], %[rseq_scratch1]\n\t"
+		LONG_S " %[len], %[rseq_scratch2]\n\t"
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], 5f\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f)
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], 7f\n\t"
+#endif
+		/* try memcpy */
+		"beqz %[len], 333f\n\t" \
+		"222:\n\t" \
+		"lb   $4, 0(%[src])\n\t" \
+		"sb   $4, 0(%[dst])\n\t" \
+		LONG_ADDI " %[src], 1\n\t" \
+		LONG_ADDI " %[dst], 1\n\t" \
+		LONG_ADDI " %[len], -1\n\t" \
+		"bnez %[len], 222b\n\t" \
+		"333:\n\t" \
+		RSEQ_INJECT_ASM(5)
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		/* teardown */
+		LONG_L " %[len], %[rseq_scratch2]\n\t"
+		LONG_L " %[dst], %[rseq_scratch1]\n\t"
+		LONG_L " %[src], %[rseq_scratch0]\n\t"
+		"b 8f\n\t"
+		RSEQ_ASM_DEFINE_ABORT(3, 4,
+				      /* teardown */
+				      LONG_L " %[len], %[rseq_scratch2]\n\t"
+				      LONG_L " %[dst], %[rseq_scratch1]\n\t"
+				      LONG_L " %[src], %[rseq_scratch0]\n\t",
+				      abort, 1b, 2b, 4f)
+		RSEQ_ASM_DEFINE_CMPFAIL(5,
+					/* teardown */
+					LONG_L " %[len], %[rseq_scratch2]\n\t"
+					LONG_L " %[dst], %[rseq_scratch1]\n\t"
+					LONG_L " %[src], %[rseq_scratch0]\n\t",
+					cmpfail)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_CMPFAIL(6,
+					/* teardown */
+					LONG_L " %[len], %[rseq_scratch2]\n\t"
+					LONG_L " %[dst], %[rseq_scratch1]\n\t"
+					LONG_L " %[src], %[rseq_scratch0]\n\t",
+					error1)
+		RSEQ_ASM_DEFINE_CMPFAIL(7,
+					/* teardown */
+					LONG_L " %[len], %[rseq_scratch2]\n\t"
+					LONG_L " %[dst], %[rseq_scratch1]\n\t"
+					LONG_L " %[src], %[rseq_scratch0]\n\t",
+					error2)
+#endif
+		"8:\n\t"
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv),
+		  /* try memcpy input */
+		  [dst]			"r" (dst),
+		  [src]			"r" (src),
+		  [len]			"r" (len),
+		  [rseq_scratch0]	"m" (rseq_scratch[0]),
+		  [rseq_scratch1]	"m" (rseq_scratch[1]),
+		  [rseq_scratch2]	"m" (rseq_scratch[2])
+		  RSEQ_INJECT_INPUT
+		: "$4", "memory"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_workaround_gcc_asm_size_guess();
+	return 0;
+abort:
+	rseq_workaround_gcc_asm_size_guess();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_workaround_gcc_asm_size_guess();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_workaround_gcc_asm_size_guess();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_workaround_gcc_asm_size_guess();
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
+					 void *dst, void *src, size_t len,
+					 intptr_t newv, int cpu)
+{
+	uintptr_t rseq_scratch[3];
+
+	RSEQ_INJECT_C(9)
+
+	rseq_workaround_gcc_asm_size_guess();
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+		LONG_S " %[src], %[rseq_scratch0]\n\t"
+		LONG_S " %[dst], %[rseq_scratch1]\n\t"
+		LONG_S " %[len], %[rseq_scratch2]\n\t"
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], 5f\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f)
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], 7f\n\t"
+#endif
+		/* try memcpy */
+		"beqz %[len], 333f\n\t" \
+		"222:\n\t" \
+		"lb   $4, 0(%[src])\n\t" \
+		"sb   $4, 0(%[dst])\n\t" \
+		LONG_ADDI " %[src], 1\n\t" \
+		LONG_ADDI " %[dst], 1\n\t" \
+		LONG_ADDI " %[len], -1\n\t" \
+		"bnez %[len], 222b\n\t" \
+		"333:\n\t" \
+		RSEQ_INJECT_ASM(5)
+		"sync\n\t"	/* full sync provides store-release */
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		/* teardown */
+		LONG_L " %[len], %[rseq_scratch2]\n\t"
+		LONG_L " %[dst], %[rseq_scratch1]\n\t"
+		LONG_L " %[src], %[rseq_scratch0]\n\t"
+		"b 8f\n\t"
+		RSEQ_ASM_DEFINE_ABORT(3, 4,
+				      /* teardown */
+				      LONG_L " %[len], %[rseq_scratch2]\n\t"
+				      LONG_L " %[dst], %[rseq_scratch1]\n\t"
+				      LONG_L " %[src], %[rseq_scratch0]\n\t",
+				      abort, 1b, 2b, 4f)
+		RSEQ_ASM_DEFINE_CMPFAIL(5,
+					/* teardown */
+					LONG_L " %[len], %[rseq_scratch2]\n\t"
+					LONG_L " %[dst], %[rseq_scratch1]\n\t"
+					LONG_L " %[src], %[rseq_scratch0]\n\t",
+					cmpfail)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_CMPFAIL(6,
+					/* teardown */
+					LONG_L " %[len], %[rseq_scratch2]\n\t"
+					LONG_L " %[dst], %[rseq_scratch1]\n\t"
+					LONG_L " %[src], %[rseq_scratch0]\n\t",
+					error1)
+		RSEQ_ASM_DEFINE_CMPFAIL(7,
+					/* teardown */
+					LONG_L " %[len], %[rseq_scratch2]\n\t"
+					LONG_L " %[dst], %[rseq_scratch1]\n\t"
+					LONG_L " %[src], %[rseq_scratch0]\n\t",
+					error2)
+#endif
+		"8:\n\t"
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv),
+		  /* try memcpy input */
+		  [dst]			"r" (dst),
+		  [src]			"r" (src),
+		  [len]			"r" (len),
+		  [rseq_scratch0]	"m" (rseq_scratch[0]),
+		  [rseq_scratch1]	"m" (rseq_scratch[1]),
+		  [rseq_scratch2]	"m" (rseq_scratch[2])
+		  RSEQ_INJECT_INPUT
+		: "$4", "memory"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_workaround_gcc_asm_size_guess();
+	return 0;
+abort:
+	rseq_workaround_gcc_asm_size_guess();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_workaround_gcc_asm_size_guess();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_workaround_gcc_asm_size_guess();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_workaround_gcc_asm_size_guess();
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+#endif /* !RSEQ_SKIP_FASTPATH */
diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h
index 0a808575cbc4..86ce22417e0d 100644
--- a/tools/testing/selftests/rseq/rseq.h
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -73,6 +73,8 @@ extern __thread volatile struct rseq __rseq_abi;
 #include <rseq-arm.h>
 #elif defined(__PPC__)
 #include <rseq-ppc.h>
+#elif defined(__mips__)
+#include <rseq-mips.h>
 #else
 #error unsupported target
 #endif
@@ -131,17 +133,27 @@ static inline uint32_t rseq_current_cpu(void)
 	return cpu;
 }
 
+static inline void rseq_clear_rseq_cs(void)
+{
+#ifdef __LP64__
+	__rseq_abi.rseq_cs.ptr = 0;
+#else
+	__rseq_abi.rseq_cs.ptr.ptr32 = 0;
+#endif
+}
+
 /*
- * rseq_prepare_unload() should be invoked by each thread using rseq_finish*()
- * at least once between their last rseq_finish*() and library unload of the
- * library defining the rseq critical section (struct rseq_cs). This also
- * applies to use of rseq in code generated by JIT: rseq_prepare_unload()
- * should be invoked at least once by each thread using rseq_finish*() before
- * reclaim of the memory holding the struct rseq_cs.
+ * rseq_prepare_unload() should be invoked by each thread executing a rseq
+ * critical section at least once between their last critical section and
+ * library unload of the library defining the rseq critical section
+ * (struct rseq_cs). This also applies to use of rseq in code generated by
+ * JIT: rseq_prepare_unload() should be invoked at least once by each
+ * thread executing a rseq critical section before reclaim of the memory
+ * holding the struct rseq_cs.
  */
 static inline void rseq_prepare_unload(void)
 {
-	__rseq_abi.rseq_cs = 0;
+	rseq_clear_rseq_cs();
 }
 
 #endif  /* RSEQ_H_ */
diff --git a/tools/testing/selftests/rseq/run_param_test.sh b/tools/testing/selftests/rseq/run_param_test.sh
index 3acd6d75ff9f..3acd6d75ff9f 100644..100755
--- a/tools/testing/selftests/rseq/run_param_test.sh
+++ b/tools/testing/selftests/rseq/run_param_test.sh
diff --git a/tools/testing/selftests/sparc64/Makefile b/tools/testing/selftests/sparc64/Makefile
index 2082eeffd779..a19531dba4dc 100644
--- a/tools/testing/selftests/sparc64/Makefile
+++ b/tools/testing/selftests/sparc64/Makefile
@@ -1,7 +1,18 @@
+# SPDX-License-Identifier: GPL-2.0
+uname_M := $(shell uname -m 2>/dev/null || echo not)
+ARCH ?= $(shell echo $(uname_M) | sed -e s/x86_64/x86/)
+
+ifneq ($(ARCH),sparc64)
+nothing:
+.PHONY: all clean run_tests install
+.SILENT:
+else
+
 SUBDIRS := drivers
 
 TEST_PROGS := run.sh
 
+
 .PHONY: all clean
 
 include ../lib.mk
@@ -18,10 +29,6 @@ all:
 		fi \
 	done
 
-override define RUN_TESTS
-	@cd $(OUTPUT); ./run.sh
-endef
-
 override define INSTALL_RULE
 	mkdir -p $(INSTALL_PATH)
 	install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)
@@ -33,10 +40,6 @@ override define INSTALL_RULE
 	done;
 endef
 
-override define EMIT_TESTS
-	echo "./run.sh"
-endef
-
 override define CLEAN
 	@for DIR in $(SUBDIRS); do		\
 		BUILD_TARGET=$(OUTPUT)/$$DIR;	\
@@ -44,3 +47,4 @@ override define CLEAN
 		make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
 	done
 endef
+endif
diff --git a/tools/testing/selftests/sparc64/drivers/Makefile b/tools/testing/selftests/sparc64/drivers/Makefile
index 6264f40bbdbc..deb0df415565 100644
--- a/tools/testing/selftests/sparc64/drivers/Makefile
+++ b/tools/testing/selftests/sparc64/drivers/Makefile
@@ -1,4 +1,4 @@
-
+# SPDX-License-Identifier: GPL-2.0
 INCLUDEDIR := -I.
 CFLAGS := $(CFLAGS) $(INCLUDEDIR) -Wall -O2 -g
 
diff --git a/tools/testing/selftests/static_keys/test_static_keys.sh b/tools/testing/selftests/static_keys/test_static_keys.sh
index 24cff498b31a..fc9f8cde7d42 100755
--- a/tools/testing/selftests/static_keys/test_static_keys.sh
+++ b/tools/testing/selftests/static_keys/test_static_keys.sh
@@ -2,6 +2,19 @@
 # SPDX-License-Identifier: GPL-2.0
 # Runs static keys kernel module tests
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+if ! /sbin/modprobe -q -n test_static_key_base; then
+	echo "static_key: module test_static_key_base is not found [SKIP]"
+	exit $ksft_skip
+fi
+
+if ! /sbin/modprobe -q -n test_static_keys; then
+	echo "static_key: module test_static_keys is not found [SKIP]"
+	exit $ksft_skip
+fi
+
 if /sbin/modprobe -q test_static_key_base; then
 	if /sbin/modprobe -q test_static_keys; then
 		echo "static_key: ok"
diff --git a/tools/testing/selftests/sync/config b/tools/testing/selftests/sync/config
new file mode 100644
index 000000000000..1ab7e8130db2
--- /dev/null
+++ b/tools/testing/selftests/sync/config
@@ -0,0 +1,4 @@
+CONFIG_STAGING=y
+CONFIG_ANDROID=y
+CONFIG_SYNC=y
+CONFIG_SW_SYNC=y
diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh
index ec232c3cfcaa..584eb8ea780a 100755
--- a/tools/testing/selftests/sysctl/sysctl.sh
+++ b/tools/testing/selftests/sysctl/sysctl.sh
@@ -14,6 +14,9 @@
 
 # This performs a series tests against the proc sysctl interface.
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 TEST_NAME="sysctl"
 TEST_DRIVER="test_${TEST_NAME}"
 TEST_DIR=$(dirname $0)
@@ -41,7 +44,7 @@ test_modprobe()
                echo "$0: $DIR not present" >&2
                echo "You must have the following enabled in your kernel:" >&2
                cat $TEST_DIR/config >&2
-               exit 1
+               exit $ksft_skip
        fi
 }
 
@@ -98,28 +101,30 @@ test_reqs()
 	uid=$(id -u)
 	if [ $uid -ne 0 ]; then
 		echo $msg must be run as root >&2
-		exit 0
+		exit $ksft_skip
 	fi
 
 	if ! which perl 2> /dev/null > /dev/null; then
 		echo "$0: You need perl installed"
-		exit 1
+		exit $ksft_skip
 	fi
 	if ! which getconf 2> /dev/null > /dev/null; then
 		echo "$0: You need getconf installed"
-		exit 1
+		exit $ksft_skip
 	fi
 	if ! which diff 2> /dev/null > /dev/null; then
 		echo "$0: You need diff installed"
-		exit 1
+		exit $ksft_skip
 	fi
 }
 
 function load_req_mod()
 {
-	trap "test_modprobe" EXIT
-
 	if [ ! -d $DIR ]; then
+		if ! modprobe -q -n $TEST_DRIVER; then
+			echo "$0: module $TEST_DRIVER not found [SKIP]"
+			exit $ksft_skip
+		fi
 		modprobe $TEST_DRIVER
 		if [ $? -ne 0 ]; then
 			exit
@@ -765,6 +770,7 @@ function parse_args()
 test_reqs
 allow_user_defaults
 check_production_sysctl_writes_strict
+test_modprobe
 load_req_mod
 
 trap "test_finish" EXIT
diff --git a/tools/testing/selftests/user/test_user_copy.sh b/tools/testing/selftests/user/test_user_copy.sh
index d60506fc77f8..f9b31a57439b 100755
--- a/tools/testing/selftests/user/test_user_copy.sh
+++ b/tools/testing/selftests/user/test_user_copy.sh
@@ -2,6 +2,13 @@
 # SPDX-License-Identifier: GPL-2.0
 # Runs copy_to/from_user infrastructure using test_user_copy kernel module
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+if ! /sbin/modprobe -q -n test_user_copy; then
+	echo "user: module test_user_copy is not found [SKIP]"
+	exit $ksft_skip
+fi
 if /sbin/modprobe -q test_user_copy; then
 	/sbin/modprobe -q -r test_user_copy
 	echo "user_copy: ok"
diff --git a/tools/testing/selftests/vm/compaction_test.c b/tools/testing/selftests/vm/compaction_test.c
index 1097f04e4d80..bcec71250873 100644
--- a/tools/testing/selftests/vm/compaction_test.c
+++ b/tools/testing/selftests/vm/compaction_test.c
@@ -16,6 +16,8 @@
 #include <unistd.h>
 #include <string.h>
 
+#include "../kselftest.h"
+
 #define MAP_SIZE 1048576
 
 struct map_list {
@@ -169,7 +171,7 @@ int main(int argc, char **argv)
 		printf("Either the sysctl compact_unevictable_allowed is not\n"
 		       "set to 1 or couldn't read the proc file.\n"
 		       "Skipping the test\n");
-		return 0;
+		return KSFT_SKIP;
 	}
 
 	lim.rlim_cur = RLIM_INFINITY;
diff --git a/tools/testing/selftests/vm/mlock2-tests.c b/tools/testing/selftests/vm/mlock2-tests.c
index 4997b9222cfa..637b6d0ac0d0 100644
--- a/tools/testing/selftests/vm/mlock2-tests.c
+++ b/tools/testing/selftests/vm/mlock2-tests.c
@@ -9,6 +9,8 @@
 #include <stdbool.h>
 #include "mlock2.h"
 
+#include "../kselftest.h"
+
 struct vm_boundaries {
 	unsigned long start;
 	unsigned long end;
@@ -303,7 +305,7 @@ static int test_mlock_lock()
 	if (mlock2_(map, 2 * page_size, 0)) {
 		if (errno == ENOSYS) {
 			printf("Cannot call new mlock family, skipping test\n");
-			_exit(0);
+			_exit(KSFT_SKIP);
 		}
 		perror("mlock2(0)");
 		goto unmap;
@@ -412,7 +414,7 @@ static int test_mlock_onfault()
 	if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) {
 		if (errno == ENOSYS) {
 			printf("Cannot call new mlock family, skipping test\n");
-			_exit(0);
+			_exit(KSFT_SKIP);
 		}
 		perror("mlock2(MLOCK_ONFAULT)");
 		goto unmap;
@@ -425,7 +427,7 @@ static int test_mlock_onfault()
 	if (munlock(map, 2 * page_size)) {
 		if (errno == ENOSYS) {
 			printf("Cannot call new mlock family, skipping test\n");
-			_exit(0);
+			_exit(KSFT_SKIP);
 		}
 		perror("munlock()");
 		goto unmap;
@@ -457,7 +459,7 @@ static int test_lock_onfault_of_present()
 	if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) {
 		if (errno == ENOSYS) {
 			printf("Cannot call new mlock family, skipping test\n");
-			_exit(0);
+			_exit(KSFT_SKIP);
 		}
 		perror("mlock2(MLOCK_ONFAULT)");
 		goto unmap;
@@ -583,7 +585,7 @@ static int test_vma_management(bool call_mlock)
 	if (call_mlock && mlock2_(map, 3 * page_size, MLOCK_ONFAULT)) {
 		if (errno == ENOSYS) {
 			printf("Cannot call new mlock family, skipping test\n");
-			_exit(0);
+			_exit(KSFT_SKIP);
 		}
 		perror("mlock(ONFAULT)\n");
 		goto out;
diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests
index 22d564673830..88cbe5575f0c 100755
--- a/tools/testing/selftests/vm/run_vmtests
+++ b/tools/testing/selftests/vm/run_vmtests
@@ -2,6 +2,9 @@
 # SPDX-License-Identifier: GPL-2.0
 #please run as root
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 mnt=./huge
 exitcode=0
 
@@ -36,7 +39,7 @@ if [ -n "$freepgs" ] && [ -n "$hpgsize_KB" ]; then
 		echo $(( $lackpgs + $nr_hugepgs )) > /proc/sys/vm/nr_hugepages
 		if [ $? -ne 0 ]; then
 			echo "Please run this test as root"
-			exit 1
+			exit $ksft_skip
 		fi
 		while read name size unit; do
 			if [ "$name" = "HugePages_Free:" ]; then
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index de2f9ec8a87f..7b8171e3128a 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -69,6 +69,8 @@
 #include <setjmp.h>
 #include <stdbool.h>
 
+#include "../kselftest.h"
+
 #ifdef __NR_userfaultfd
 
 static unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size;
@@ -1322,7 +1324,7 @@ int main(int argc, char **argv)
 int main(void)
 {
 	printf("skip: Skipping userfaultfd test (missing __NR_userfaultfd)\n");
-	return 0;
+	return KSFT_SKIP;
 }
 
 #endif /* __NR_userfaultfd */
diff --git a/tools/testing/selftests/x86/sigreturn.c b/tools/testing/selftests/x86/sigreturn.c
index 246145b84a12..4d9dc3f2fd70 100644
--- a/tools/testing/selftests/x86/sigreturn.c
+++ b/tools/testing/selftests/x86/sigreturn.c
@@ -610,21 +610,41 @@ static int test_valid_sigreturn(int cs_bits, bool use_16bit_ss, int force_ss)
 	 */
 	for (int i = 0; i < NGREG; i++) {
 		greg_t req = requested_regs[i], res = resulting_regs[i];
+
 		if (i == REG_TRAPNO || i == REG_IP)
 			continue;	/* don't care */
-		if (i == REG_SP) {
-			printf("\tSP: %llx -> %llx\n", (unsigned long long)req,
-			       (unsigned long long)res);
 
+		if (i == REG_SP) {
 			/*
-			 * In many circumstances, the high 32 bits of rsp
-			 * are zeroed.  For example, we could be a real
-			 * 32-bit program, or we could hit any of a number
-			 * of poorly-documented IRET or segmented ESP
-			 * oddities.  If this happens, it's okay.
+			 * If we were using a 16-bit stack segment, then
+			 * the kernel is a bit stuck: IRET only restores
+			 * the low 16 bits of ESP/RSP if SS is 16-bit.
+			 * The kernel uses a hack to restore bits 31:16,
+			 * but that hack doesn't help with bits 63:32.
+			 * On Intel CPUs, bits 63:32 end up zeroed, and, on
+			 * AMD CPUs, they leak the high bits of the kernel
+			 * espfix64 stack pointer.  There's very little that
+			 * the kernel can do about it.
+			 *
+			 * Similarly, if we are returning to a 32-bit context,
+			 * the CPU will often lose the high 32 bits of RSP.
 			 */
-			if (res == (req & 0xFFFFFFFF))
-				continue;  /* OK; not expected to work */
+
+			if (res == req)
+				continue;
+
+			if (cs_bits != 64 && ((res ^ req) & 0xFFFFFFFF) == 0) {
+				printf("[NOTE]\tSP: %llx -> %llx\n",
+				       (unsigned long long)req,
+				       (unsigned long long)res);
+				continue;
+			}
+
+			printf("[FAIL]\tSP mismatch: requested 0x%llx; got 0x%llx\n",
+			       (unsigned long long)requested_regs[i],
+			       (unsigned long long)resulting_regs[i]);
+			nerrs++;
+			continue;
 		}
 
 		bool ignore_reg = false;
@@ -654,25 +674,18 @@ static int test_valid_sigreturn(int cs_bits, bool use_16bit_ss, int force_ss)
 #endif
 
 		/* Sanity check on the kernel */
-		if (i == REG_CX && requested_regs[i] != resulting_regs[i]) {
+		if (i == REG_CX && req != res) {
 			printf("[FAIL]\tCX (saved SP) mismatch: requested 0x%llx; got 0x%llx\n",
-			       (unsigned long long)requested_regs[i],
-			       (unsigned long long)resulting_regs[i]);
+			       (unsigned long long)req,
+			       (unsigned long long)res);
 			nerrs++;
 			continue;
 		}
 
-		if (requested_regs[i] != resulting_regs[i] && !ignore_reg) {
-			/*
-			 * SP is particularly interesting here.  The
-			 * usual cause of failures is that we hit the
-			 * nasty IRET case of returning to a 16-bit SS,
-			 * in which case bits 16:31 of the *kernel*
-			 * stack pointer persist in ESP.
-			 */
+		if (req != res && !ignore_reg) {
 			printf("[FAIL]\tReg %d mismatch: requested 0x%llx; got 0x%llx\n",
-			       i, (unsigned long long)requested_regs[i],
-			       (unsigned long long)resulting_regs[i]);
+			       i, (unsigned long long)req,
+			       (unsigned long long)res);
 			nerrs++;
 		}
 	}
diff --git a/tools/testing/selftests/zram/zram.sh b/tools/testing/selftests/zram/zram.sh
index 754de7da426a..232e958ec454 100755
--- a/tools/testing/selftests/zram/zram.sh
+++ b/tools/testing/selftests/zram/zram.sh
@@ -2,6 +2,9 @@
 # SPDX-License-Identifier: GPL-2.0
 TCID="zram.sh"
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 . ./zram_lib.sh
 
 run_zram () {
@@ -24,5 +27,5 @@ elif [ -b /dev/zram0 ]; then
 else
 	echo "$TCID : No zram.ko module or /dev/zram0 device file not found"
 	echo "$TCID : CONFIG_ZRAM is not set"
-	exit 1
+	exit $ksft_skip
 fi
diff --git a/tools/testing/selftests/zram/zram_lib.sh b/tools/testing/selftests/zram/zram_lib.sh
index f6a9c73e7a44..9e73a4fb9b0a 100755
--- a/tools/testing/selftests/zram/zram_lib.sh
+++ b/tools/testing/selftests/zram/zram_lib.sh
@@ -18,6 +18,9 @@ MODULE=0
 dev_makeswap=-1
 dev_mounted=-1
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 trap INT
 
 check_prereqs()
@@ -27,7 +30,7 @@ check_prereqs()
 
 	if [ $uid -ne 0 ]; then
 		echo $msg must be run as root >&2
-		exit 0
+		exit $ksft_skip
 	fi
 }
 
diff --git a/tools/usb/ffs-test.c b/tools/usb/ffs-test.c
index 95dd14648ba5..0f395dfb7774 100644
--- a/tools/usb/ffs-test.c
+++ b/tools/usb/ffs-test.c
@@ -44,12 +44,25 @@
 
 /******************** Little Endian Handling ********************************/
 
-#define cpu_to_le16(x)  htole16(x)
-#define cpu_to_le32(x)  htole32(x)
+/*
+ * cpu_to_le16/32 are used when initializing structures, a context where a
+ * function call is not allowed. To solve this, we code cpu_to_le16/32 in a way
+ * that allows them to be used when initializing structures.
+ */
+
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+#define cpu_to_le16(x)  (x)
+#define cpu_to_le32(x)  (x)
+#else
+#define cpu_to_le16(x)  ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8))
+#define cpu_to_le32(x)  \
+	((((x) & 0xff000000u) >> 24) | (((x) & 0x00ff0000u) >>  8) | \
+	(((x) & 0x0000ff00u) <<  8) | (((x) & 0x000000ffu) << 24))
+#endif
+
 #define le32_to_cpu(x)  le32toh(x)
 #define le16_to_cpu(x)  le16toh(x)
 
-
 /******************** Messages and Errors ***********************************/
 
 static const char argv0[] = "ffs-test";
diff --git a/tools/virtio/linux/scatterlist.h b/tools/virtio/linux/scatterlist.h
index 9a45f90e2d08..369ee308b668 100644
--- a/tools/virtio/linux/scatterlist.h
+++ b/tools/virtio/linux/scatterlist.h
@@ -36,7 +36,6 @@ static inline void sg_assign_page(struct scatterlist *sg, struct page *page)
 	 */
 	BUG_ON((unsigned long) page & 0x03);
 #ifdef CONFIG_DEBUG_SG
-	BUG_ON(sg->sg_magic != SG_MAGIC);
 	BUG_ON(sg_is_chain(sg));
 #endif
 	sg->page_link = page_link | (unsigned long) page;
@@ -67,7 +66,6 @@ static inline void sg_set_page(struct scatterlist *sg, struct page *page,
 static inline struct page *sg_page(struct scatterlist *sg)
 {
 #ifdef CONFIG_DEBUG_SG
-	BUG_ON(sg->sg_magic != SG_MAGIC);
 	BUG_ON(sg_is_chain(sg));
 #endif
 	return (struct page *)((sg)->page_link & ~0x3);
@@ -116,9 +114,6 @@ static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents,
  **/
 static inline void sg_mark_end(struct scatterlist *sg)
 {
-#ifdef CONFIG_DEBUG_SG
-	BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
 	/*
 	 * Set termination bit, clear potential chain bit
 	 */
@@ -136,17 +131,11 @@ static inline void sg_mark_end(struct scatterlist *sg)
  **/
 static inline void sg_unmark_end(struct scatterlist *sg)
 {
-#ifdef CONFIG_DEBUG_SG
-	BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
 	sg->page_link &= ~0x02;
 }
 
 static inline struct scatterlist *sg_next(struct scatterlist *sg)
 {
-#ifdef CONFIG_DEBUG_SG
-	BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
 	if (sg_is_last(sg))
 		return NULL;
 
@@ -160,13 +149,6 @@ static inline struct scatterlist *sg_next(struct scatterlist *sg)
 static inline void sg_init_table(struct scatterlist *sgl, unsigned int nents)
 {
 	memset(sgl, 0, sizeof(*sgl) * nents);
-#ifdef CONFIG_DEBUG_SG
-	{
-		unsigned int i;
-		for (i = 0; i < nents; i++)
-			sgl[i].sg_magic = SG_MAGIC;
-	}
-#endif
 	sg_mark_end(&sgl[nents - 1]);
 }
author	Herbert Xu <herbert@gondor.apana.org.au>	2018-08-03 17:55:12 +0800
committer	Herbert Xu <herbert@gondor.apana.org.au>	2018-08-03 17:55:12 +0800
commit	c5f5aeef9b55b362ad5a0e04e4b41cd63b208842 (patch)
tree	0ee2bb561e879db0a990d998359f6516dff3393b /tools
parent	crypto: rmd320 - use swap macro in rmd320_transform (diff)
parent	crypto/arm64: aes-ce-gcm - add missing kernel_neon_begin/end pair (diff)
download	linux-dev-c5f5aeef9b55b362ad5a0e04e4b41cd63b208842.tar.xz linux-dev-c5f5aeef9b55b362ad5a0e04e4b41cd63b208842.zip