Merge 4.20-rc5 into staging-next

We need the staging fixes in here as well.

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

64 files changed, 1806 insertions, 180 deletions

diff --git a/tools/arch/arm64/include/asm/barrier.h b/tools/arch/arm64/include/asm/barrier.h
index 12835ea0e417..378c051fa177 100644
--- a/tools/arch/arm64/include/asm/barrier.h
+++ b/tools/arch/arm64/include/asm/barrier.h
@@ -14,74 +14,75 @@
 #define wmb()		asm volatile("dmb ishst" ::: "memory")
 #define rmb()		asm volatile("dmb ishld" ::: "memory")
 
-#define smp_store_release(p, v)					\
-do {								\
-	union { typeof(*p) __val; char __c[1]; } __u =		\
-		{ .__val = (__force typeof(*p)) (v) }; 		\
-								\
-	switch (sizeof(*p)) {					\
-	case 1:							\
-		asm volatile ("stlrb %w1, %0"			\
-				: "=Q" (*p)			\
-				: "r" (*(__u8 *)__u.__c)	\
-				: "memory");			\
-		break;						\
-	case 2:							\
-		asm volatile ("stlrh %w1, %0"			\
-				: "=Q" (*p)			\
-				: "r" (*(__u16 *)__u.__c)	\
-				: "memory");			\
-		break;						\
-	case 4:							\
-		asm volatile ("stlr %w1, %0"			\
-				: "=Q" (*p)			\
-				: "r" (*(__u32 *)__u.__c)	\
-				: "memory");			\
-		break;						\
-	case 8:							\
-		asm volatile ("stlr %1, %0"			\
-				: "=Q" (*p)			\
-				: "r" (*(__u64 *)__u.__c)	\
-				: "memory");			\
-		break;						\
-	default:						\
-		/* Only to shut up gcc ... */			\
-		mb();						\
-		break;						\
-	}							\
+#define smp_store_release(p, v)						\
+do {									\
+	union { typeof(*p) __val; char __c[1]; } __u =			\
+		{ .__val = (v) }; 					\
+									\
+	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile ("stlrb %w1, %0"				\
+				: "=Q" (*p)				\
+				: "r" (*(__u8_alias_t *)__u.__c)	\
+				: "memory");				\
+		break;							\
+	case 2:								\
+		asm volatile ("stlrh %w1, %0"				\
+				: "=Q" (*p)				\
+				: "r" (*(__u16_alias_t *)__u.__c)	\
+				: "memory");				\
+		break;							\
+	case 4:								\
+		asm volatile ("stlr %w1, %0"				\
+				: "=Q" (*p)				\
+				: "r" (*(__u32_alias_t *)__u.__c)	\
+				: "memory");				\
+		break;							\
+	case 8:								\
+		asm volatile ("stlr %1, %0"				\
+				: "=Q" (*p)				\
+				: "r" (*(__u64_alias_t *)__u.__c)	\
+				: "memory");				\
+		break;							\
+	default:							\
+		/* Only to shut up gcc ... */				\
+		mb();							\
+		break;							\
+	}								\
 } while (0)
 
-#define smp_load_acquire(p)					\
-({								\
-	union { typeof(*p) __val; char __c[1]; } __u;		\
-								\
-	switch (sizeof(*p)) {					\
-	case 1:							\
-		asm volatile ("ldarb %w0, %1"			\
-			: "=r" (*(__u8 *)__u.__c)		\
-			: "Q" (*p) : "memory");			\
-		break;						\
-	case 2:							\
-		asm volatile ("ldarh %w0, %1"			\
-			: "=r" (*(__u16 *)__u.__c)		\
-			: "Q" (*p) : "memory");			\
-		break;						\
-	case 4:							\
-		asm volatile ("ldar %w0, %1"			\
-			: "=r" (*(__u32 *)__u.__c)		\
-			: "Q" (*p) : "memory");			\
-		break;						\
-	case 8:							\
-		asm volatile ("ldar %0, %1"			\
-			: "=r" (*(__u64 *)__u.__c)		\
-			: "Q" (*p) : "memory");			\
-		break;						\
-	default:						\
-		/* Only to shut up gcc ... */			\
-		mb();						\
-		break;						\
-	}							\
-	__u.__val;						\
+#define smp_load_acquire(p)						\
+({									\
+	union { typeof(*p) __val; char __c[1]; } __u =			\
+		{ .__c = { 0 } };					\
+									\
+	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile ("ldarb %w0, %1"				\
+			: "=r" (*(__u8_alias_t *)__u.__c)		\
+			: "Q" (*p) : "memory");				\
+		break;							\
+	case 2:								\
+		asm volatile ("ldarh %w0, %1"				\
+			: "=r" (*(__u16_alias_t *)__u.__c)		\
+			: "Q" (*p) : "memory");				\
+		break;							\
+	case 4:								\
+		asm volatile ("ldar %w0, %1"				\
+			: "=r" (*(__u32_alias_t *)__u.__c)		\
+			: "Q" (*p) : "memory");				\
+		break;							\
+	case 8:								\
+		asm volatile ("ldar %0, %1"				\
+			: "=r" (*(__u64_alias_t *)__u.__c)		\
+			: "Q" (*p) : "memory");				\
+		break;							\
+	default:							\
+		/* Only to shut up gcc ... */				\
+		mb();							\
+		break;							\
+	}								\
+	__u.__val;							\
 })
 
 #endif /* _TOOLS_LINUX_ASM_AARCH64_BARRIER_H */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 89a048c2faec..28c4a502b419 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -331,6 +331,8 @@
 #define X86_FEATURE_LA57		(16*32+16) /* 5-level page tables */
 #define X86_FEATURE_RDPID		(16*32+22) /* RDPID instruction */
 #define X86_FEATURE_CLDEMOTE		(16*32+25) /* CLDEMOTE instruction */
+#define X86_FEATURE_MOVDIRI		(16*32+27) /* MOVDIRI instruction */
+#define X86_FEATURE_MOVDIR64B		(16*32+28) /* MOVDIR64B instruction */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
 #define X86_FEATURE_OVERFLOW_RECOV	(17*32+ 0) /* MCA overflow recovery support */
diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
index edbe81534c6d..d07ccf8a23f7 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
@@ -137,4 +137,10 @@ EXAMPLES
 
 SEE ALSO
 ========
-	**bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8)
+	**bpf**\ (2),
+	**bpf-helpers**\ (7),
+	**bpftool**\ (8),
+	**bpftool-prog**\ (8),
+	**bpftool-map**\ (8),
+	**bpftool-net**\ (8),
+	**bpftool-perf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
index f55a2daed59b..7bb787cfa971 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-map.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -171,4 +171,10 @@ The following three commands are equivalent:
 
 SEE ALSO
 ========
-	**bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-cgroup**\ (8)
+	**bpf**\ (2),
+	**bpf-helpers**\ (7),
+	**bpftool**\ (8),
+	**bpftool-prog**\ (8),
+	**bpftool-cgroup**\ (8),
+	**bpftool-net**\ (8),
+	**bpftool-perf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst
index 408ec30d8872..ed87c9b619ad 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-net.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst
@@ -136,4 +136,10 @@ EXAMPLES
 
 SEE ALSO
 ========
-	**bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8)
+	**bpf**\ (2),
+	**bpf-helpers**\ (7),
+	**bpftool**\ (8),
+	**bpftool-prog**\ (8),
+	**bpftool-map**\ (8),
+	**bpftool-cgroup**\ (8),
+	**bpftool-perf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst
index e3eb0eab7641..f4c5e5538bb8 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-perf.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst
@@ -78,4 +78,10 @@ EXAMPLES
 
 SEE ALSO
 ========
-	**bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8)
+	**bpf**\ (2),
+	**bpf-helpers**\ (7),
+	**bpftool**\ (8),
+	**bpftool-prog**\ (8),
+	**bpftool-map**\ (8),
+	**bpftool-cgroup**\ (8),
+	**bpftool-net**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index ac4e904b10fb..ecf618807125 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -124,7 +124,8 @@ OPTIONS
 		  Generate human-readable JSON output. Implies **-j**.
 
 	-f, --bpffs
-		  Show file names of pinned programs.
+		  When showing BPF programs, show file names of pinned
+		  programs.
 
 EXAMPLES
 ========
@@ -206,4 +207,10 @@ EXAMPLES
 
 SEE ALSO
 ========
-	**bpftool**\ (8), **bpftool-map**\ (8), **bpftool-cgroup**\ (8)
+	**bpf**\ (2),
+	**bpf-helpers**\ (7),
+	**bpftool**\ (8),
+	**bpftool-map**\ (8),
+	**bpftool-cgroup**\ (8),
+	**bpftool-net**\ (8),
+	**bpftool-perf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index 04cd4f92ab89..129b7a9c0f9b 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -63,5 +63,10 @@ OPTIONS
 
 SEE ALSO
 ========
-	**bpftool-map**\ (8), **bpftool-prog**\ (8), **bpftool-cgroup**\ (8)
-        **bpftool-perf**\ (8), **bpftool-net**\ (8)
+	**bpf**\ (2),
+	**bpf-helpers**\ (7),
+	**bpftool-prog**\ (8),
+	**bpftool-map**\ (8),
+	**bpftool-cgroup**\ (8),
+	**bpftool-net**\ (8),
+	**bpftool-perf**\ (8)
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 25af85304ebe..70fd48d79f61 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -130,16 +130,17 @@ static int mnt_bpffs(const char *target, char *buff, size_t bufflen)
 	return 0;
 }
 
-int open_obj_pinned(char *path)
+int open_obj_pinned(char *path, bool quiet)
 {
 	int fd;
 
 	fd = bpf_obj_get(path);
 	if (fd < 0) {
-		p_err("bpf obj get (%s): %s", path,
-		      errno == EACCES && !is_bpffs(dirname(path)) ?
-		    "directory not in bpf file system (bpffs)" :
-		    strerror(errno));
+		if (!quiet)
+			p_err("bpf obj get (%s): %s", path,
+			      errno == EACCES && !is_bpffs(dirname(path)) ?
+			    "directory not in bpf file system (bpffs)" :
+			    strerror(errno));
 		return -1;
 	}
 
@@ -151,7 +152,7 @@ int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type)
 	enum bpf_obj_type type;
 	int fd;
 
-	fd = open_obj_pinned(path);
+	fd = open_obj_pinned(path, false);
 	if (fd < 0)
 		return -1;
 
@@ -304,7 +305,7 @@ char *get_fdinfo(int fd, const char *key)
 		return NULL;
 	}
 
-	while ((n = getline(&line, &line_n, fdi))) {
+	while ((n = getline(&line, &line_n, fdi)) > 0) {
 		char *value;
 		int len;
 
@@ -384,7 +385,7 @@ int build_pinned_obj_table(struct pinned_obj_table *tab,
 		while ((ftse = fts_read(fts))) {
 			if (!(ftse->fts_info & FTS_F))
 				continue;
-			fd = open_obj_pinned(ftse->fts_path);
+			fd = open_obj_pinned(ftse->fts_path, true);
 			if (fd < 0)
 				continue;
 
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 28322ace2856..a8bf1e2d9818 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -127,7 +127,7 @@ int cmd_select(const struct cmd *cmds, int argc, char **argv,
 int get_fd_type(int fd);
 const char *get_fd_type_name(enum bpf_obj_type type);
 char *get_fdinfo(int fd, const char *key);
-int open_obj_pinned(char *path);
+int open_obj_pinned(char *path, bool quiet);
 int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type);
 int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32));
 int do_pin_fd(int fd, const char *name);
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 5302ee282409..ccee180dfb76 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -357,10 +357,9 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd)
 	if (!hash_empty(prog_table.table)) {
 		struct pinned_obj *obj;
 
-		printf("\n");
 		hash_for_each_possible(prog_table.table, obj, hash, info->id) {
 			if (obj->id == info->id)
-				printf("\tpinned %s\n", obj->path);
+				printf("\n\tpinned %s", obj->path);
 		}
 	}
 
@@ -845,6 +844,7 @@ static int do_load(int argc, char **argv)
 			}
 			NEXT_ARG();
 		} else if (is_prefix(*argv, "map")) {
+			void *new_map_replace;
 			char *endptr, *name;
 			int fd;
 
@@ -878,12 +878,15 @@ static int do_load(int argc, char **argv)
 			if (fd < 0)
 				goto err_free_reuse_maps;
 
-			map_replace = reallocarray(map_replace, old_map_fds + 1,
-						   sizeof(*map_replace));
-			if (!map_replace) {
+			new_map_replace = reallocarray(map_replace,
+						       old_map_fds + 1,
+						       sizeof(*map_replace));
+			if (!new_map_replace) {
 				p_err("mem alloc failed");
 				goto err_free_reuse_maps;
 			}
+			map_replace = new_map_replace;
+
 			map_replace[old_map_fds].idx = idx;
 			map_replace[old_map_fds].name = name;
 			map_replace[old_map_fds].fd = fd;
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index f216b2f5c3d7..d74bb9414d7c 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -33,6 +33,7 @@ FEATURE_TESTS_BASIC :=                  \
         dwarf_getlocations              \
         fortify-source                  \
         sync-compare-and-swap           \
+        get_current_dir_name            \
         glibc                           \
         gtk2                            \
         gtk2-infobar                    \
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 0516259be70f..304b984f11b9 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -7,6 +7,7 @@ FILES=                                          \
          test-dwarf_getlocations.bin            \
          test-fortify-source.bin                \
          test-sync-compare-and-swap.bin         \
+         test-get_current_dir_name.bin          \
          test-glibc.bin                         \
          test-gtk2.bin                          \
          test-gtk2-infobar.bin                  \
@@ -101,6 +102,9 @@ $(OUTPUT)test-bionic.bin:
 $(OUTPUT)test-libelf.bin:
 	$(BUILD) -lelf
 
+$(OUTPUT)test-get_current_dir_name.bin:
+	$(BUILD)
+
 $(OUTPUT)test-glibc.bin:
 	$(BUILD)
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 8dc20a61341f..56722bfe6bdd 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -34,6 +34,10 @@
 # include "test-libelf-mmap.c"
 #undef main
 
+#define main main_test_get_current_dir_name
+# include "test-get_current_dir_name.c"
+#undef main
+
 #define main main_test_glibc
 # include "test-glibc.c"
 #undef main
@@ -174,6 +178,7 @@ int main(int argc, char *argv[])
 	main_test_hello();
 	main_test_libelf();
 	main_test_libelf_mmap();
+	main_test_get_current_dir_name();
 	main_test_glibc();
 	main_test_dwarf();
 	main_test_dwarf_getlocations();
diff --git a/tools/build/feature/test-get_current_dir_name.c b/tools/build/feature/test-get_current_dir_name.c
new file mode 100644
index 000000000000..573000f93212
--- /dev/null
+++ b/tools/build/feature/test-get_current_dir_name.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <unistd.h>
+#include <stdlib.h>
+
+int main(void)
+{
+	free(get_current_dir_name());
+	return 0;
+}
diff --git a/tools/include/uapi/asm-generic/ioctls.h b/tools/include/uapi/asm-generic/ioctls.h
index 040651735662..cdc9f4ca8c27 100644
--- a/tools/include/uapi/asm-generic/ioctls.h
+++ b/tools/include/uapi/asm-generic/ioctls.h
@@ -79,6 +79,8 @@
 #define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
 #define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
 #define TIOCGPTPEER	_IO('T', 0x41) /* Safely open the slave */
+#define TIOCGISO7816	_IOR('T', 0x42, struct serial_iso7816)
+#define TIOCSISO7816	_IOWR('T', 0x43, struct serial_iso7816)
 
 #define FIONCLEX	0x5450
 #define FIOCLEX		0x5451
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 7f5634ce8e88..a4446f452040 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -529,6 +529,28 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_CS_TIMESTAMP_FREQUENCY 51
 
+/*
+ * Once upon a time we supposed that writes through the GGTT would be
+ * immediately in physical memory (once flushed out of the CPU path). However,
+ * on a few different processors and chipsets, this is not necessarily the case
+ * as the writes appear to be buffered internally. Thus a read of the backing
+ * storage (physical memory) via a different path (with different physical tags
+ * to the indirect write via the GGTT) will see stale values from before
+ * the GGTT write. Inside the kernel, we can for the most part keep track of
+ * the different read/write domains in use (e.g. set-domain), but the assumption
+ * of coherency is baked into the ABI, hence reporting its true state in this
+ * parameter.
+ *
+ * Reports true when writes via mmap_gtt are immediately visible following an
+ * lfence to flush the WCB.
+ *
+ * Reports false when writes via mmap_gtt are indeterminately delayed in an in
+ * internal buffer and are _not_ immediately visible to third parties accessing
+ * directly via mmap_cpu/mmap_wc. Use of mmap_gtt as part of an IPC
+ * communications channel when reporting false is strongly disadvised.
+ */
+#define I915_PARAM_MMAP_GTT_COHERENT	52
+
 typedef struct drm_i915_getparam {
 	__s32 param;
 	/*
diff --git a/tools/include/uapi/linux/pkt_cls.h b/tools/include/uapi/linux/pkt_cls.h
new file mode 100644
index 000000000000..401d0c1e612d
--- /dev/null
+++ b/tools/include/uapi/linux/pkt_cls.h
@@ -0,0 +1,612 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_PKT_CLS_H
+#define __LINUX_PKT_CLS_H
+
+#include <linux/types.h>
+#include <linux/pkt_sched.h>
+
+#define TC_COOKIE_MAX_SIZE 16
+
+/* Action attributes */
+enum {
+	TCA_ACT_UNSPEC,
+	TCA_ACT_KIND,
+	TCA_ACT_OPTIONS,
+	TCA_ACT_INDEX,
+	TCA_ACT_STATS,
+	TCA_ACT_PAD,
+	TCA_ACT_COOKIE,
+	__TCA_ACT_MAX
+};
+
+#define TCA_ACT_MAX __TCA_ACT_MAX
+#define TCA_OLD_COMPAT (TCA_ACT_MAX+1)
+#define TCA_ACT_MAX_PRIO 32
+#define TCA_ACT_BIND	1
+#define TCA_ACT_NOBIND	0
+#define TCA_ACT_UNBIND	1
+#define TCA_ACT_NOUNBIND	0
+#define TCA_ACT_REPLACE		1
+#define TCA_ACT_NOREPLACE	0
+
+#define TC_ACT_UNSPEC	(-1)
+#define TC_ACT_OK		0
+#define TC_ACT_RECLASSIFY	1
+#define TC_ACT_SHOT		2
+#define TC_ACT_PIPE		3
+#define TC_ACT_STOLEN		4
+#define TC_ACT_QUEUED		5
+#define TC_ACT_REPEAT		6
+#define TC_ACT_REDIRECT		7
+#define TC_ACT_TRAP		8 /* For hw path, this means "trap to cpu"
+				   * and don't further process the frame
+				   * in hardware. For sw path, this is
+				   * equivalent of TC_ACT_STOLEN - drop
+				   * the skb and act like everything
+				   * is alright.
+				   */
+#define TC_ACT_VALUE_MAX	TC_ACT_TRAP
+
+/* There is a special kind of actions called "extended actions",
+ * which need a value parameter. These have a local opcode located in
+ * the highest nibble, starting from 1. The rest of the bits
+ * are used to carry the value. These two parts together make
+ * a combined opcode.
+ */
+#define __TC_ACT_EXT_SHIFT 28
+#define __TC_ACT_EXT(local) ((local) << __TC_ACT_EXT_SHIFT)
+#define TC_ACT_EXT_VAL_MASK ((1 << __TC_ACT_EXT_SHIFT) - 1)
+#define TC_ACT_EXT_OPCODE(combined) ((combined) & (~TC_ACT_EXT_VAL_MASK))
+#define TC_ACT_EXT_CMP(combined, opcode) (TC_ACT_EXT_OPCODE(combined) == opcode)
+
+#define TC_ACT_JUMP __TC_ACT_EXT(1)
+#define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2)
+#define TC_ACT_EXT_OPCODE_MAX	TC_ACT_GOTO_CHAIN
+
+/* Action type identifiers*/
+enum {
+	TCA_ID_UNSPEC=0,
+	TCA_ID_POLICE=1,
+	/* other actions go here */
+	__TCA_ID_MAX=255
+};
+
+#define TCA_ID_MAX __TCA_ID_MAX
+
+struct tc_police {
+	__u32			index;
+	int			action;
+#define TC_POLICE_UNSPEC	TC_ACT_UNSPEC
+#define TC_POLICE_OK		TC_ACT_OK
+#define TC_POLICE_RECLASSIFY	TC_ACT_RECLASSIFY
+#define TC_POLICE_SHOT		TC_ACT_SHOT
+#define TC_POLICE_PIPE		TC_ACT_PIPE
+
+	__u32			limit;
+	__u32			burst;
+	__u32			mtu;
+	struct tc_ratespec	rate;
+	struct tc_ratespec	peakrate;
+	int			refcnt;
+	int			bindcnt;
+	__u32			capab;
+};
+
+struct tcf_t {
+	__u64   install;
+	__u64   lastuse;
+	__u64   expires;
+	__u64   firstuse;
+};
+
+struct tc_cnt {
+	int                   refcnt;
+	int                   bindcnt;
+};
+
+#define tc_gen \
+	__u32                 index; \
+	__u32                 capab; \
+	int                   action; \
+	int                   refcnt; \
+	int                   bindcnt
+
+enum {
+	TCA_POLICE_UNSPEC,
+	TCA_POLICE_TBF,
+	TCA_POLICE_RATE,
+	TCA_POLICE_PEAKRATE,
+	TCA_POLICE_AVRATE,
+	TCA_POLICE_RESULT,
+	TCA_POLICE_TM,
+	TCA_POLICE_PAD,
+	__TCA_POLICE_MAX
+#define TCA_POLICE_RESULT TCA_POLICE_RESULT
+};
+
+#define TCA_POLICE_MAX (__TCA_POLICE_MAX - 1)
+
+/* tca flags definitions */
+#define TCA_CLS_FLAGS_SKIP_HW	(1 << 0) /* don't offload filter to HW */
+#define TCA_CLS_FLAGS_SKIP_SW	(1 << 1) /* don't use filter in SW */
+#define TCA_CLS_FLAGS_IN_HW	(1 << 2) /* filter is offloaded to HW */
+#define TCA_CLS_FLAGS_NOT_IN_HW (1 << 3) /* filter isn't offloaded to HW */
+#define TCA_CLS_FLAGS_VERBOSE	(1 << 4) /* verbose logging */
+
+/* U32 filters */
+
+#define TC_U32_HTID(h) ((h)&0xFFF00000)
+#define TC_U32_USERHTID(h) (TC_U32_HTID(h)>>20)
+#define TC_U32_HASH(h) (((h)>>12)&0xFF)
+#define TC_U32_NODE(h) ((h)&0xFFF)
+#define TC_U32_KEY(h) ((h)&0xFFFFF)
+#define TC_U32_UNSPEC	0
+#define TC_U32_ROOT	(0xFFF00000)
+
+enum {
+	TCA_U32_UNSPEC,
+	TCA_U32_CLASSID,
+	TCA_U32_HASH,
+	TCA_U32_LINK,
+	TCA_U32_DIVISOR,
+	TCA_U32_SEL,
+	TCA_U32_POLICE,
+	TCA_U32_ACT,
+	TCA_U32_INDEV,
+	TCA_U32_PCNT,
+	TCA_U32_MARK,
+	TCA_U32_FLAGS,
+	TCA_U32_PAD,
+	__TCA_U32_MAX
+};
+
+#define TCA_U32_MAX (__TCA_U32_MAX - 1)
+
+struct tc_u32_key {
+	__be32		mask;
+	__be32		val;
+	int		off;
+	int		offmask;
+};
+
+struct tc_u32_sel {
+	unsigned char		flags;
+	unsigned char		offshift;
+	unsigned char		nkeys;
+
+	__be16			offmask;
+	__u16			off;
+	short			offoff;
+
+	short			hoff;
+	__be32			hmask;
+	struct tc_u32_key	keys[0];
+};
+
+struct tc_u32_mark {
+	__u32		val;
+	__u32		mask;
+	__u32		success;
+};
+
+struct tc_u32_pcnt {
+	__u64 rcnt;
+	__u64 rhit;
+	__u64 kcnts[0];
+};
+
+/* Flags */
+
+#define TC_U32_TERMINAL		1
+#define TC_U32_OFFSET		2
+#define TC_U32_VAROFFSET	4
+#define TC_U32_EAT		8
+
+#define TC_U32_MAXDEPTH 8
+
+
+/* RSVP filter */
+
+enum {
+	TCA_RSVP_UNSPEC,
+	TCA_RSVP_CLASSID,
+	TCA_RSVP_DST,
+	TCA_RSVP_SRC,
+	TCA_RSVP_PINFO,
+	TCA_RSVP_POLICE,
+	TCA_RSVP_ACT,
+	__TCA_RSVP_MAX
+};
+
+#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 )
+
+struct tc_rsvp_gpi {
+	__u32	key;
+	__u32	mask;
+	int	offset;
+};
+
+struct tc_rsvp_pinfo {
+	struct tc_rsvp_gpi dpi;
+	struct tc_rsvp_gpi spi;
+	__u8	protocol;
+	__u8	tunnelid;
+	__u8	tunnelhdr;
+	__u8	pad;
+};
+
+/* ROUTE filter */
+
+enum {
+	TCA_ROUTE4_UNSPEC,
+	TCA_ROUTE4_CLASSID,
+	TCA_ROUTE4_TO,
+	TCA_ROUTE4_FROM,
+	TCA_ROUTE4_IIF,
+	TCA_ROUTE4_POLICE,
+	TCA_ROUTE4_ACT,
+	__TCA_ROUTE4_MAX
+};
+
+#define TCA_ROUTE4_MAX (__TCA_ROUTE4_MAX - 1)
+
+
+/* FW filter */
+
+enum {
+	TCA_FW_UNSPEC,
+	TCA_FW_CLASSID,
+	TCA_FW_POLICE,
+	TCA_FW_INDEV, /*  used by CONFIG_NET_CLS_IND */
+	TCA_FW_ACT, /* used by CONFIG_NET_CLS_ACT */
+	TCA_FW_MASK,
+	__TCA_FW_MAX
+};
+
+#define TCA_FW_MAX (__TCA_FW_MAX - 1)
+
+/* TC index filter */
+
+enum {
+	TCA_TCINDEX_UNSPEC,
+	TCA_TCINDEX_HASH,
+	TCA_TCINDEX_MASK,
+	TCA_TCINDEX_SHIFT,
+	TCA_TCINDEX_FALL_THROUGH,
+	TCA_TCINDEX_CLASSID,
+	TCA_TCINDEX_POLICE,
+	TCA_TCINDEX_ACT,
+	__TCA_TCINDEX_MAX
+};
+
+#define TCA_TCINDEX_MAX     (__TCA_TCINDEX_MAX - 1)
+
+/* Flow filter */
+
+enum {
+	FLOW_KEY_SRC,
+	FLOW_KEY_DST,
+	FLOW_KEY_PROTO,
+	FLOW_KEY_PROTO_SRC,
+	FLOW_KEY_PROTO_DST,
+	FLOW_KEY_IIF,
+	FLOW_KEY_PRIORITY,
+	FLOW_KEY_MARK,
+	FLOW_KEY_NFCT,
+	FLOW_KEY_NFCT_SRC,
+	FLOW_KEY_NFCT_DST,
+	FLOW_KEY_NFCT_PROTO_SRC,
+	FLOW_KEY_NFCT_PROTO_DST,
+	FLOW_KEY_RTCLASSID,
+	FLOW_KEY_SKUID,
+	FLOW_KEY_SKGID,
+	FLOW_KEY_VLAN_TAG,
+	FLOW_KEY_RXHASH,
+	__FLOW_KEY_MAX,
+};
+
+#define FLOW_KEY_MAX	(__FLOW_KEY_MAX - 1)
+
+enum {
+	FLOW_MODE_MAP,
+	FLOW_MODE_HASH,
+};
+
+enum {
+	TCA_FLOW_UNSPEC,
+	TCA_FLOW_KEYS,
+	TCA_FLOW_MODE,
+	TCA_FLOW_BASECLASS,
+	TCA_FLOW_RSHIFT,
+	TCA_FLOW_ADDEND,
+	TCA_FLOW_MASK,
+	TCA_FLOW_XOR,
+	TCA_FLOW_DIVISOR,
+	TCA_FLOW_ACT,
+	TCA_FLOW_POLICE,
+	TCA_FLOW_EMATCHES,
+	TCA_FLOW_PERTURB,
+	__TCA_FLOW_MAX
+};
+
+#define TCA_FLOW_MAX	(__TCA_FLOW_MAX - 1)
+
+/* Basic filter */
+
+enum {
+	TCA_BASIC_UNSPEC,
+	TCA_BASIC_CLASSID,
+	TCA_BASIC_EMATCHES,
+	TCA_BASIC_ACT,
+	TCA_BASIC_POLICE,
+	__TCA_BASIC_MAX
+};
+
+#define TCA_BASIC_MAX (__TCA_BASIC_MAX - 1)
+
+
+/* Cgroup classifier */
+
+enum {
+	TCA_CGROUP_UNSPEC,
+	TCA_CGROUP_ACT,
+	TCA_CGROUP_POLICE,
+	TCA_CGROUP_EMATCHES,
+	__TCA_CGROUP_MAX,
+};
+
+#define TCA_CGROUP_MAX (__TCA_CGROUP_MAX - 1)
+
+/* BPF classifier */
+
+#define TCA_BPF_FLAG_ACT_DIRECT		(1 << 0)
+
+enum {
+	TCA_BPF_UNSPEC,
+	TCA_BPF_ACT,
+	TCA_BPF_POLICE,
+	TCA_BPF_CLASSID,
+	TCA_BPF_OPS_LEN,
+	TCA_BPF_OPS,
+	TCA_BPF_FD,
+	TCA_BPF_NAME,
+	TCA_BPF_FLAGS,
+	TCA_BPF_FLAGS_GEN,
+	TCA_BPF_TAG,
+	TCA_BPF_ID,
+	__TCA_BPF_MAX,
+};
+
+#define TCA_BPF_MAX (__TCA_BPF_MAX - 1)
+
+/* Flower classifier */
+
+enum {
+	TCA_FLOWER_UNSPEC,
+	TCA_FLOWER_CLASSID,
+	TCA_FLOWER_INDEV,
+	TCA_FLOWER_ACT,
+	TCA_FLOWER_KEY_ETH_DST,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_DST_MASK,	/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_SRC,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_SRC_MASK,	/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_TYPE,	/* be16 */
+	TCA_FLOWER_KEY_IP_PROTO,	/* u8 */
+	TCA_FLOWER_KEY_IPV4_SRC,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_SRC_MASK,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_DST,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_DST_MASK,	/* be32 */
+	TCA_FLOWER_KEY_IPV6_SRC,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_SRC_MASK,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_DST,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_DST_MASK,	/* struct in6_addr */
+	TCA_FLOWER_KEY_TCP_SRC,		/* be16 */
+	TCA_FLOWER_KEY_TCP_DST,		/* be16 */
+	TCA_FLOWER_KEY_UDP_SRC,		/* be16 */
+	TCA_FLOWER_KEY_UDP_DST,		/* be16 */
+
+	TCA_FLOWER_FLAGS,
+	TCA_FLOWER_KEY_VLAN_ID,		/* be16 */
+	TCA_FLOWER_KEY_VLAN_PRIO,	/* u8   */
+	TCA_FLOWER_KEY_VLAN_ETH_TYPE,	/* be16 */
+
+	TCA_FLOWER_KEY_ENC_KEY_ID,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_SRC,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_DST,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV6_SRC,	/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_DST,	/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,/* struct in6_addr */
+
+	TCA_FLOWER_KEY_TCP_SRC_MASK,	/* be16 */
+	TCA_FLOWER_KEY_TCP_DST_MASK,	/* be16 */
+	TCA_FLOWER_KEY_UDP_SRC_MASK,	/* be16 */
+	TCA_FLOWER_KEY_UDP_DST_MASK,	/* be16 */
+	TCA_FLOWER_KEY_SCTP_SRC_MASK,	/* be16 */
+	TCA_FLOWER_KEY_SCTP_DST_MASK,	/* be16 */
+
+	TCA_FLOWER_KEY_SCTP_SRC,	/* be16 */
+	TCA_FLOWER_KEY_SCTP_DST,	/* be16 */
+
+	TCA_FLOWER_KEY_ENC_UDP_SRC_PORT,	/* be16 */
+	TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK,	/* be16 */
+	TCA_FLOWER_KEY_ENC_UDP_DST_PORT,	/* be16 */
+	TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK,	/* be16 */
+
+	TCA_FLOWER_KEY_FLAGS,		/* be32 */
+	TCA_FLOWER_KEY_FLAGS_MASK,	/* be32 */
+
+	TCA_FLOWER_KEY_ICMPV4_CODE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV4_CODE_MASK,/* u8 */
+	TCA_FLOWER_KEY_ICMPV4_TYPE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV4_TYPE_MASK,/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_CODE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_CODE_MASK,/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_TYPE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_TYPE_MASK,/* u8 */
+
+	TCA_FLOWER_KEY_ARP_SIP,		/* be32 */
+	TCA_FLOWER_KEY_ARP_SIP_MASK,	/* be32 */
+	TCA_FLOWER_KEY_ARP_TIP,		/* be32 */
+	TCA_FLOWER_KEY_ARP_TIP_MASK,	/* be32 */
+	TCA_FLOWER_KEY_ARP_OP,		/* u8 */
+	TCA_FLOWER_KEY_ARP_OP_MASK,	/* u8 */
+	TCA_FLOWER_KEY_ARP_SHA,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ARP_SHA_MASK,	/* ETH_ALEN */
+	TCA_FLOWER_KEY_ARP_THA,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ARP_THA_MASK,	/* ETH_ALEN */
+
+	TCA_FLOWER_KEY_MPLS_TTL,	/* u8 - 8 bits */
+	TCA_FLOWER_KEY_MPLS_BOS,	/* u8 - 1 bit */
+	TCA_FLOWER_KEY_MPLS_TC,		/* u8 - 3 bits */
+	TCA_FLOWER_KEY_MPLS_LABEL,	/* be32 - 20 bits */
+
+	TCA_FLOWER_KEY_TCP_FLAGS,	/* be16 */
+	TCA_FLOWER_KEY_TCP_FLAGS_MASK,	/* be16 */
+
+	TCA_FLOWER_KEY_IP_TOS,		/* u8 */
+	TCA_FLOWER_KEY_IP_TOS_MASK,	/* u8 */
+	TCA_FLOWER_KEY_IP_TTL,		/* u8 */
+	TCA_FLOWER_KEY_IP_TTL_MASK,	/* u8 */
+
+	TCA_FLOWER_KEY_CVLAN_ID,	/* be16 */
+	TCA_FLOWER_KEY_CVLAN_PRIO,	/* u8   */
+	TCA_FLOWER_KEY_CVLAN_ETH_TYPE,	/* be16 */
+
+	TCA_FLOWER_KEY_ENC_IP_TOS,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TOS_MASK,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TTL,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TTL_MASK,	/* u8 */
+
+	TCA_FLOWER_KEY_ENC_OPTS,
+	TCA_FLOWER_KEY_ENC_OPTS_MASK,
+
+	TCA_FLOWER_IN_HW_COUNT,
+
+	__TCA_FLOWER_MAX,
+};
+
+#define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_ENC_OPTS_UNSPEC,
+	TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested
+					 * TCA_FLOWER_KEY_ENC_OPT_GENEVE_
+					 * attributes
+					 */
+	__TCA_FLOWER_KEY_ENC_OPTS_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPTS_MAX (__TCA_FLOWER_KEY_ENC_OPTS_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_UNSPEC,
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS,            /* u16 */
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE,             /* u8 */
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA,             /* 4 to 128 bytes */
+
+	__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX \
+		(__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0),
+	TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1),
+};
+
+/* Match-all classifier */
+
+enum {
+	TCA_MATCHALL_UNSPEC,
+	TCA_MATCHALL_CLASSID,
+	TCA_MATCHALL_ACT,
+	TCA_MATCHALL_FLAGS,
+	__TCA_MATCHALL_MAX,
+};
+
+#define TCA_MATCHALL_MAX (__TCA_MATCHALL_MAX - 1)
+
+/* Extended Matches */
+
+struct tcf_ematch_tree_hdr {
+	__u16		nmatches;
+	__u16		progid;
+};
+
+enum {
+	TCA_EMATCH_TREE_UNSPEC,
+	TCA_EMATCH_TREE_HDR,
+	TCA_EMATCH_TREE_LIST,
+	__TCA_EMATCH_TREE_MAX
+};
+#define TCA_EMATCH_TREE_MAX (__TCA_EMATCH_TREE_MAX - 1)
+
+struct tcf_ematch_hdr {
+	__u16		matchid;
+	__u16		kind;
+	__u16		flags;
+	__u16		pad; /* currently unused */
+};
+
+/*  0                   1
+ *  0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 
+ * +-----------------------+-+-+---+
+ * |         Unused        |S|I| R |
+ * +-----------------------+-+-+---+
+ *
+ * R(2) ::= relation to next ematch
+ *          where: 0 0 END (last ematch)
+ *                 0 1 AND
+ *                 1 0 OR
+ *                 1 1 Unused (invalid)
+ * I(1) ::= invert result
+ * S(1) ::= simple payload
+ */
+#define TCF_EM_REL_END	0
+#define TCF_EM_REL_AND	(1<<0)
+#define TCF_EM_REL_OR	(1<<1)
+#define TCF_EM_INVERT	(1<<2)
+#define TCF_EM_SIMPLE	(1<<3)
+
+#define TCF_EM_REL_MASK	3
+#define TCF_EM_REL_VALID(v) (((v) & TCF_EM_REL_MASK) != TCF_EM_REL_MASK)
+
+enum {
+	TCF_LAYER_LINK,
+	TCF_LAYER_NETWORK,
+	TCF_LAYER_TRANSPORT,
+	__TCF_LAYER_MAX
+};
+#define TCF_LAYER_MAX (__TCF_LAYER_MAX - 1)
+
+/* Ematch type assignments
+ *   1..32767		Reserved for ematches inside kernel tree
+ *   32768..65535	Free to use, not reliable
+ */
+#define	TCF_EM_CONTAINER	0
+#define	TCF_EM_CMP		1
+#define	TCF_EM_NBYTE		2
+#define	TCF_EM_U32		3
+#define	TCF_EM_META		4
+#define	TCF_EM_TEXT		5
+#define	TCF_EM_VLAN		6
+#define	TCF_EM_CANID		7
+#define	TCF_EM_IPSET		8
+#define	TCF_EM_IPT		9
+#define	TCF_EM_MAX		9
+
+enum {
+	TCF_EM_PROG_TC
+};
+
+enum {
+	TCF_EM_OPND_EQ,
+	TCF_EM_OPND_GT,
+	TCF_EM_OPND_LT
+};
+
+#endif
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index c0d7ea0bf5b6..b17201edfa09 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -212,6 +212,7 @@ struct prctl_mm_map {
 #define PR_SET_SPECULATION_CTRL		53
 /* Speculation control variants */
 # define PR_SPEC_STORE_BYPASS		0
+# define PR_SPEC_INDIRECT_BRANCH	1
 /* Return and control values for PR_SET/GET_SPECULATION_CTRL */
 # define PR_SPEC_NOT_AFFECTED		0
 # define PR_SPEC_PRCTL			(1UL << 0)
diff --git a/tools/include/uapi/linux/tc_act/tc_bpf.h b/tools/include/uapi/linux/tc_act/tc_bpf.h
new file mode 100644
index 000000000000..6e89a5df49a4
--- /dev/null
+++ b/tools/include/uapi/linux/tc_act/tc_bpf.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __LINUX_TC_BPF_H
+#define __LINUX_TC_BPF_H
+
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_BPF 13
+
+struct tc_act_bpf {
+	tc_gen;
+};
+
+enum {
+	TCA_ACT_BPF_UNSPEC,
+	TCA_ACT_BPF_TM,
+	TCA_ACT_BPF_PARMS,
+	TCA_ACT_BPF_OPS_LEN,
+	TCA_ACT_BPF_OPS,
+	TCA_ACT_BPF_FD,
+	TCA_ACT_BPF_NAME,
+	TCA_ACT_BPF_PAD,
+	TCA_ACT_BPF_TAG,
+	TCA_ACT_BPF_ID,
+	__TCA_ACT_BPF_MAX,
+};
+#define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1)
+
+#endif
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 6dbb9fae0f9d..b8f3cca8e58b 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -31,6 +31,8 @@
 #include "elf.h"
 #include "warn.h"
 
+#define MAX_NAME_LEN 128
+
 struct section *find_section_by_name(struct elf *elf, const char *name)
 {
 	struct section *sec;
@@ -298,6 +300,8 @@ static int read_symbols(struct elf *elf)
 	/* Create parent/child links for any cold subfunctions */
 	list_for_each_entry(sec, &elf->sections, list) {
 		list_for_each_entry(sym, &sec->symbol_list, list) {
+			char pname[MAX_NAME_LEN + 1];
+			size_t pnamelen;
 			if (sym->type != STT_FUNC)
 				continue;
 			sym->pfunc = sym->cfunc = sym;
@@ -305,14 +309,21 @@ static int read_symbols(struct elf *elf)
 			if (!coldstr)
 				continue;
 
-			coldstr[0] = '\0';
-			pfunc = find_symbol_by_name(elf, sym->name);
-			coldstr[0] = '.';
+			pnamelen = coldstr - sym->name;
+			if (pnamelen > MAX_NAME_LEN) {
+				WARN("%s(): parent function name exceeds maximum length of %d characters",
+				     sym->name, MAX_NAME_LEN);
+				return -1;
+			}
+
+			strncpy(pname, sym->name, pnamelen);
+			pname[pnamelen] = '\0';
+			pfunc = find_symbol_by_name(elf, pname);
 
 			if (!pfunc) {
 				WARN("%s(): can't find parent function",
 				     sym->name);
-				goto err;
+				return -1;
 			}
 
 			sym->pfunc = pfunc;
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 236b9b97dfdb..667c14e56031 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -55,7 +55,6 @@ counted. The following modifiers exist:
  S - read sample value (PERF_SAMPLE_READ)
  D - pin the event to the PMU
  W - group is weak and will fallback to non-group if not schedulable,
-     only supported in 'perf stat' for now.
 
 The 'p' modifier can be used for specifying how precise the instruction
 address should be. The 'p' modifier can be specified multiple times:
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index e30d20fb482d..a0e8c23f9125 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -299,6 +299,11 @@ ifndef NO_BIONIC
   endif
 endif
 
+ifeq ($(feature-get_current_dir_name), 1)
+  CFLAGS += -DHAVE_GET_CURRENT_DIR_NAME
+endif
+
+
 ifdef NO_LIBELF
   NO_DWARF := 1
   NO_DEMANGLE := 1
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 3ccb4f0bf088..d95655489f7e 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -387,7 +387,7 @@ SHELL = $(SHELL_PATH)
 
 linux_uapi_dir := $(srctree)/tools/include/uapi/linux
 asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic
-arch_asm_uapi_dir := $(srctree)/tools/arch/$(ARCH)/include/uapi/asm/
+arch_asm_uapi_dir := $(srctree)/tools/arch/$(SRCARCH)/include/uapi/asm/
 
 beauty_outdir := $(OUTPUT)trace/beauty/generated
 beauty_ioctl_outdir := $(beauty_outdir)/ioctl
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 10cf889c6d75..488779bc4c8d 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -391,7 +391,12 @@ try_again:
 					ui__warning("%s\n", msg);
 				goto try_again;
 			}
-
+			if ((errno == EINVAL || errno == EBADF) &&
+			    pos->leader != pos &&
+			    pos->weak_group) {
+			        pos = perf_evlist__reset_weak_group(evlist, pos);
+				goto try_again;
+			}
 			rc = -errno;
 			perf_evsel__open_strerror(pos, &opts->target,
 						  errno, msg, sizeof(msg));
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index d1028d7755bb..a635abfa77b6 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -383,32 +383,6 @@ static bool perf_evsel__should_store_id(struct perf_evsel *counter)
 	return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID;
 }
 
-static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel)
-{
-	struct perf_evsel *c2, *leader;
-	bool is_open = true;
-
-	leader = evsel->leader;
-	pr_debug("Weak group for %s/%d failed\n",
-			leader->name, leader->nr_members);
-
-	/*
-	 * for_each_group_member doesn't work here because it doesn't
-	 * include the first entry.
-	 */
-	evlist__for_each_entry(evsel_list, c2) {
-		if (c2 == evsel)
-			is_open = false;
-		if (c2->leader == leader) {
-			if (is_open)
-				perf_evsel__close(c2);
-			c2->leader = c2;
-			c2->nr_members = 0;
-		}
-	}
-	return leader;
-}
-
 static bool is_target_alive(struct target *_target,
 			    struct thread_map *threads)
 {
@@ -477,7 +451,7 @@ try_again:
 			if ((errno == EINVAL || errno == EBADF) &&
 			    counter->leader != counter &&
 			    counter->weak_group) {
-				counter = perf_evsel__reset_weak_group(counter);
+				counter = perf_evlist__reset_weak_group(evsel_list, counter);
 				goto try_again;
 			}
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index b2838de13de0..aa0c73e57924 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1429,6 +1429,9 @@ int cmd_top(int argc, const char **argv)
 		}
 	}
 
+	if (opts->branch_stack && callchain_param.enabled)
+		symbol_conf.show_branchflag_count = true;
+
 	sort__mode = SORT_MODE__TOP;
 	/* display thread wants entries to be collapsed in a different tree */
 	perf_hpp_list.need_collapse = 1;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index dc8a6c4986ce..835619476370 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -108,6 +108,7 @@ struct trace {
 	} stats;
 	unsigned int		max_stack;
 	unsigned int		min_stack;
+	bool			raw_augmented_syscalls;
 	bool			not_ev_qualifier;
 	bool			live;
 	bool			full_time;
@@ -1724,13 +1725,28 @@ static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel,
 	return printed;
 }
 
-static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size)
+static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size, bool raw_augmented)
 {
 	void *augmented_args = NULL;
+	/*
+	 * For now with BPF raw_augmented we hook into raw_syscalls:sys_enter
+	 * and there we get all 6 syscall args plus the tracepoint common
+	 * fields (sizeof(long)) and the syscall_nr (another long). So we check
+	 * if that is the case and if so don't look after the sc->args_size,
+	 * but always after the full raw_syscalls:sys_enter payload, which is
+	 * fixed.
+	 *
+	 * We'll revisit this later to pass s->args_size to the BPF augmenter
+	 * (now tools/perf/examples/bpf/augmented_raw_syscalls.c, so that it
+	 * copies only what we need for each syscall, like what happens when we
+	 * use syscalls:sys_enter_NAME, so that we reduce the kernel/userspace
+	 * traffic to just what is needed for each syscall.
+	 */
+	int args_size = raw_augmented ? (8 * (int)sizeof(long)) : sc->args_size;
 
-	*augmented_args_size = sample->raw_size - sc->args_size;
+	*augmented_args_size = sample->raw_size - args_size;
 	if (*augmented_args_size > 0)
-		augmented_args = sample->raw_data + sc->args_size;
+		augmented_args = sample->raw_data + args_size;
 
 	return augmented_args;
 }
@@ -1780,7 +1796,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	 * here and avoid using augmented syscalls when the evsel is the raw_syscalls one.
 	 */
 	if (evsel != trace->syscalls.events.sys_enter)
-		augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
+		augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls);
 	ttrace->entry_time = sample->time;
 	msg = ttrace->entry_str;
 	printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name);
@@ -1833,7 +1849,7 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse
 		goto out_put;
 
 	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
-	augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
+	augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls);
 	syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread);
 	fprintf(trace->output, "%s", msg);
 	err = 0;
@@ -3501,7 +3517,15 @@ int cmd_trace(int argc, const char **argv)
 		evsel->handler = trace__sys_enter;
 
 		evlist__for_each_entry(trace.evlist, evsel) {
+			bool raw_syscalls_sys_exit = strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_exit") == 0;
+
+			if (raw_syscalls_sys_exit) {
+				trace.raw_augmented_syscalls = true;
+				goto init_augmented_syscall_tp;
+			}
+
 			if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) {
+init_augmented_syscall_tp:
 				perf_evsel__init_augmented_syscall_tp(evsel);
 				perf_evsel__init_augmented_syscall_tp_ret(evsel);
 				evsel->handler = trace__sys_exit;
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
new file mode 100644
index 000000000000..90a19336310b
--- /dev/null
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Augment the raw_syscalls tracepoints with the contents of the pointer arguments.
+ *
+ * Test it with:
+ *
+ * perf trace -e tools/perf/examples/bpf/augmented_raw_syscalls.c cat /etc/passwd > /dev/null
+ *
+ * This exactly matches what is marshalled into the raw_syscall:sys_enter
+ * payload expected by the 'perf trace' beautifiers.
+ *
+ * For now it just uses the existing tracepoint augmentation code in 'perf
+ * trace', in the next csets we'll hook up these with the sys_enter/sys_exit
+ * code that will combine entry/exit in a strace like way.
+ */
+
+#include <stdio.h>
+#include <linux/socket.h>
+
+/* bpf-output associated map */
+struct bpf_map SEC("maps") __augmented_syscalls__ = {
+	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(u32),
+	.max_entries = __NR_CPUS__,
+};
+
+struct syscall_enter_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	unsigned long	   args[6];
+};
+
+struct syscall_exit_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   ret;
+};
+
+struct augmented_filename {
+	unsigned int	size;
+	int		reserved;
+	char		value[256];
+};
+
+#define SYS_OPEN 2
+#define SYS_OPENAT 257
+
+SEC("raw_syscalls:sys_enter")
+int sys_enter(struct syscall_enter_args *args)
+{
+	struct {
+		struct syscall_enter_args args;
+		struct augmented_filename filename;
+	} augmented_args;
+	unsigned int len = sizeof(augmented_args);
+	const void *filename_arg = NULL;
+
+	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
+	/*
+	 * Yonghong and Edward Cree sayz:
+	 *
+	 * https://www.spinics.net/lists/netdev/msg531645.html
+	 *
+	 * >>   R0=inv(id=0) R1=inv2 R6=ctx(id=0,off=0,imm=0) R7=inv64 R10=fp0,call_-1
+	 * >> 10: (bf) r1 = r6
+	 * >> 11: (07) r1 += 16
+	 * >> 12: (05) goto pc+2
+	 * >> 15: (79) r3 = *(u64 *)(r1 +0)
+	 * >> dereference of modified ctx ptr R1 off=16 disallowed
+	 * > Aha, we at least got a different error message this time.
+	 * > And indeed llvm has done that optimisation, rather than the more obvious
+	 * > 11: r3 = *(u64 *)(r1 +16)
+	 * > because it wants to have lots of reads share a single insn.  You may be able
+	 * > to defeat that optimisation by adding compiler barriers, idk.  Maybe someone
+	 * > with llvm knowledge can figure out how to stop it (ideally, llvm would know
+	 * > when it's generating for bpf backend and not do that).  -O0?  ¯\_(ツ)_/¯
+	 *
+	 * The optimization mostly likes below:
+	 *
+	 *	br1:
+	 * 	...
+	 *	r1 += 16
+	 *	goto merge
+	 *	br2:
+	 *	...
+	 *	r1 += 20
+	 *	goto merge
+	 *	merge:
+	 *	*(u64 *)(r1 + 0)
+	 *
+	 * The compiler tries to merge common loads. There is no easy way to
+	 * stop this compiler optimization without turning off a lot of other
+	 * optimizations. The easiest way is to add barriers:
+	 *
+	 * 	 __asm__ __volatile__("": : :"memory")
+	 *
+	 * 	 after the ctx memory access to prevent their down stream merging.
+	 */
+	switch (augmented_args.args.syscall_nr) {
+	case SYS_OPEN:	 filename_arg = (const void *)args->args[0];
+			__asm__ __volatile__("": : :"memory");
+			 break;
+	case SYS_OPENAT: filename_arg = (const void *)args->args[1];
+			 break;
+	}
+
+	if (filename_arg != NULL) {
+		augmented_args.filename.reserved = 0;
+		augmented_args.filename.size = probe_read_str(&augmented_args.filename.value,
+							      sizeof(augmented_args.filename.value),
+							      filename_arg);
+		if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) {
+			len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size;
+			len &= sizeof(augmented_args.filename.value) - 1;
+		}
+	} else {
+		len = sizeof(augmented_args.args);
+	}
+
+	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len);
+	return 0;
+}
+
+SEC("raw_syscalls:sys_exit")
+int sys_exit(struct syscall_exit_args *args)
+{
+	return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */
+}
+
+license(GPL);
diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c
index ac1bcdc17dae..f7eb63cbbc65 100644
--- a/tools/perf/jvmti/jvmti_agent.c
+++ b/tools/perf/jvmti/jvmti_agent.c
@@ -125,7 +125,7 @@ perf_get_timestamp(void)
 }
 
 static int
-debug_cache_init(void)
+create_jit_cache_dir(void)
 {
 	char str[32];
 	char *base, *p;
@@ -144,8 +144,13 @@ debug_cache_init(void)
 
 	strftime(str, sizeof(str), JIT_LANG"-jit-%Y%m%d", &tm);
 
-	snprintf(jit_path, PATH_MAX - 1, "%s/.debug/", base);
-
+	ret = snprintf(jit_path, PATH_MAX, "%s/.debug/", base);
+	if (ret >= PATH_MAX) {
+		warnx("jvmti: cannot generate jit cache dir because %s/.debug/"
+			" is too long, please check the cwd, JITDUMPDIR, and"
+			" HOME variables", base);
+		return -1;
+	}
 	ret = mkdir(jit_path, 0755);
 	if (ret == -1) {
 		if (errno != EEXIST) {
@@ -154,20 +159,32 @@ debug_cache_init(void)
 		}
 	}
 
-	snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit", base);
+	ret = snprintf(jit_path, PATH_MAX, "%s/.debug/jit", base);
+	if (ret >= PATH_MAX) {
+		warnx("jvmti: cannot generate jit cache dir because"
+			" %s/.debug/jit is too long, please check the cwd,"
+			" JITDUMPDIR, and HOME variables", base);
+		return -1;
+	}
 	ret = mkdir(jit_path, 0755);
 	if (ret == -1) {
 		if (errno != EEXIST) {
-			warn("cannot create jit cache dir %s", jit_path);
+			warn("jvmti: cannot create jit cache dir %s", jit_path);
 			return -1;
 		}
 	}
 
-	snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit/%s.XXXXXXXX", base, str);
-
+	ret = snprintf(jit_path, PATH_MAX, "%s/.debug/jit/%s.XXXXXXXX", base, str);
+	if (ret >= PATH_MAX) {
+		warnx("jvmti: cannot generate jit cache dir because"
+			" %s/.debug/jit/%s.XXXXXXXX is too long, please check"
+			" the cwd, JITDUMPDIR, and HOME variables",
+			base, str);
+		return -1;
+	}
 	p = mkdtemp(jit_path);
 	if (p != jit_path) {
-		warn("cannot create jit cache dir %s", jit_path);
+		warn("jvmti: cannot create jit cache dir %s", jit_path);
 		return -1;
 	}
 
@@ -228,7 +245,7 @@ void *jvmti_open(void)
 {
 	char dump_path[PATH_MAX];
 	struct jitheader header;
-	int fd;
+	int fd, ret;
 	FILE *fp;
 
 	init_arch_timestamp();
@@ -245,12 +262,22 @@ void *jvmti_open(void)
 
 	memset(&header, 0, sizeof(header));
 
-	debug_cache_init();
+	/*
+	 * jitdump file dir
+	 */
+	if (create_jit_cache_dir() < 0)
+		return NULL;
 
 	/*
 	 * jitdump file name
 	 */
-	scnprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
+	ret = snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
+	if (ret >= PATH_MAX) {
+		warnx("jvmti: cannot generate jitdump file full path because"
+			" %s/jit-%i.dump is too long, please check the cwd,"
+			" JITDUMPDIR, and HOME variables", jit_path, getpid());
+		return NULL;
+	}
 
 	fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666);
 	if (fd == -1)
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 24cb0bd56afa..f278ce5ebab7 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -119,6 +119,14 @@ def dsoname(name):
 		return "[kernel]"
 	return name
 
+def findnth(s, sub, n, offs=0):
+	pos = s.find(sub)
+	if pos < 0:
+		return pos
+	if n <= 1:
+		return offs + pos
+	return findnth(s[pos + 1:], sub, n - 1, offs + pos + 1)
+
 # Percent to one decimal place
 
 def PercentToOneDP(n, d):
@@ -1464,6 +1472,317 @@ class BranchWindow(QMdiSubWindow):
 		else:
 			self.find_bar.NotFound()
 
+# Dialog data item converted and validated using a SQL table
+
+class SQLTableDialogDataItem():
+
+	def __init__(self, glb, label, placeholder_text, table_name, match_column, column_name1, column_name2, parent):
+		self.glb = glb
+		self.label = label
+		self.placeholder_text = placeholder_text
+		self.table_name = table_name
+		self.match_column = match_column
+		self.column_name1 = column_name1
+		self.column_name2 = column_name2
+		self.parent = parent
+
+		self.value = ""
+
+		self.widget = QLineEdit()
+		self.widget.editingFinished.connect(self.Validate)
+		self.widget.textChanged.connect(self.Invalidate)
+		self.red = False
+		self.error = ""
+		self.validated = True
+
+		self.last_id = 0
+		self.first_time = 0
+		self.last_time = 2 ** 64
+		if self.table_name == "<timeranges>":
+			query = QSqlQuery(self.glb.db)
+			QueryExec(query, "SELECT id, time FROM samples ORDER BY id DESC LIMIT 1")
+			if query.next():
+				self.last_id = int(query.value(0))
+				self.last_time = int(query.value(1))
+			QueryExec(query, "SELECT time FROM samples WHERE time != 0 ORDER BY id LIMIT 1")
+			if query.next():
+				self.first_time = int(query.value(0))
+			if placeholder_text:
+				placeholder_text += ", between " + str(self.first_time) + " and " + str(self.last_time)
+
+		if placeholder_text:
+			self.widget.setPlaceholderText(placeholder_text)
+
+	def ValueToIds(self, value):
+		ids = []
+		query = QSqlQuery(self.glb.db)
+		stmt = "SELECT id FROM " + self.table_name + " WHERE " + self.match_column + " = '" + value + "'"
+		ret = query.exec_(stmt)
+		if ret:
+			while query.next():
+				ids.append(str(query.value(0)))
+		return ids
+
+	def IdBetween(self, query, lower_id, higher_id, order):
+		QueryExec(query, "SELECT id FROM samples WHERE id > " + str(lower_id) + " AND id < " + str(higher_id) + " ORDER BY id " + order + " LIMIT 1")
+		if query.next():
+			return True, int(query.value(0))
+		else:
+			return False, 0
+
+	def BinarySearchTime(self, lower_id, higher_id, target_time, get_floor):
+		query = QSqlQuery(self.glb.db)
+		while True:
+			next_id = int((lower_id + higher_id) / 2)
+			QueryExec(query, "SELECT time FROM samples WHERE id = " + str(next_id))
+			if not query.next():
+				ok, dbid = self.IdBetween(query, lower_id, next_id, "DESC")
+				if not ok:
+					ok, dbid = self.IdBetween(query, next_id, higher_id, "")
+					if not ok:
+						return str(higher_id)
+				next_id = dbid
+				QueryExec(query, "SELECT time FROM samples WHERE id = " + str(next_id))
+			next_time = int(query.value(0))
+			if get_floor:
+				if target_time > next_time:
+					lower_id = next_id
+				else:
+					higher_id = next_id
+				if higher_id <= lower_id + 1:
+					return str(higher_id)
+			else:
+				if target_time >= next_time:
+					lower_id = next_id
+				else:
+					higher_id = next_id
+				if higher_id <= lower_id + 1:
+					return str(lower_id)
+
+	def ConvertRelativeTime(self, val):
+		print "val ", val
+		mult = 1
+		suffix = val[-2:]
+		if suffix == "ms":
+			mult = 1000000
+		elif suffix == "us":
+			mult = 1000
+		elif suffix == "ns":
+			mult = 1
+		else:
+			return val
+		val = val[:-2].strip()
+		if not self.IsNumber(val):
+			return val
+		val = int(val) * mult
+		if val >= 0:
+			val += self.first_time
+		else:
+			val += self.last_time
+		return str(val)
+
+	def ConvertTimeRange(self, vrange):
+		print "vrange ", vrange
+		if vrange[0] == "":
+			vrange[0] = str(self.first_time)
+		if vrange[1] == "":
+			vrange[1] = str(self.last_time)
+		vrange[0] = self.ConvertRelativeTime(vrange[0])
+		vrange[1] = self.ConvertRelativeTime(vrange[1])
+		print "vrange2 ", vrange
+		if not self.IsNumber(vrange[0]) or not self.IsNumber(vrange[1]):
+			return False
+		print "ok1"
+		beg_range = max(int(vrange[0]), self.first_time)
+		end_range = min(int(vrange[1]), self.last_time)
+		if beg_range > self.last_time or end_range < self.first_time:
+			return False
+		print "ok2"
+		vrange[0] = self.BinarySearchTime(0, self.last_id, beg_range, True)
+		vrange[1] = self.BinarySearchTime(1, self.last_id + 1, end_range, False)
+		print "vrange3 ", vrange
+		return True
+
+	def AddTimeRange(self, value, ranges):
+		print "value ", value
+		n = value.count("-")
+		if n == 1:
+			pass
+		elif n == 2:
+			if value.split("-")[1].strip() == "":
+				n = 1
+		elif n == 3:
+			n = 2
+		else:
+			return False
+		pos = findnth(value, "-", n)
+		vrange = [value[:pos].strip() ,value[pos+1:].strip()]
+		if self.ConvertTimeRange(vrange):
+			ranges.append(vrange)
+			return True
+		return False
+
+	def InvalidValue(self, value):
+		self.value = ""
+		palette = QPalette()
+		palette.setColor(QPalette.Text,Qt.red)
+		self.widget.setPalette(palette)
+		self.red = True
+		self.error = self.label + " invalid value '" + value + "'"
+		self.parent.ShowMessage(self.error)
+
+	def IsNumber(self, value):
+		try:
+			x = int(value)
+		except:
+			x = 0
+		return str(x) == value
+
+	def Invalidate(self):
+		self.validated = False
+
+	def Validate(self):
+		input_string = self.widget.text()
+		self.validated = True
+		if self.red:
+			palette = QPalette()
+			self.widget.setPalette(palette)
+			self.red = False
+		if not len(input_string.strip()):
+			self.error = ""
+			self.value = ""
+			return
+		if self.table_name == "<timeranges>":
+			ranges = []
+			for value in [x.strip() for x in input_string.split(",")]:
+				if not self.AddTimeRange(value, ranges):
+					return self.InvalidValue(value)
+			ranges = [("(" + self.column_name1 + " >= " + r[0] + " AND " + self.column_name1 + " <= " + r[1] + ")") for r in ranges]
+			self.value = " OR ".join(ranges)
+		elif self.table_name == "<ranges>":
+			singles = []
+			ranges = []
+			for value in [x.strip() for x in input_string.split(",")]:
+				if "-" in value:
+					vrange = value.split("-")
+					if len(vrange) != 2 or not self.IsNumber(vrange[0]) or not self.IsNumber(vrange[1]):
+						return self.InvalidValue(value)
+					ranges.append(vrange)
+				else:
+					if not self.IsNumber(value):
+						return self.InvalidValue(value)
+					singles.append(value)
+			ranges = [("(" + self.column_name1 + " >= " + r[0] + " AND " + self.column_name1 + " <= " + r[1] + ")") for r in ranges]
+			if len(singles):
+				ranges.append(self.column_name1 + " IN (" + ",".join(singles) + ")")
+			self.value = " OR ".join(ranges)
+		elif self.table_name:
+			all_ids = []
+			for value in [x.strip() for x in input_string.split(",")]:
+				ids = self.ValueToIds(value)
+				if len(ids):
+					all_ids.extend(ids)
+				else:
+					return self.InvalidValue(value)
+			self.value = self.column_name1 + " IN (" + ",".join(all_ids) + ")"
+			if self.column_name2:
+				self.value = "( " + self.value + " OR " + self.column_name2 + " IN (" + ",".join(all_ids) + ") )"
+		else:
+			self.value = input_string.strip()
+		self.error = ""
+		self.parent.ClearMessage()
+
+	def IsValid(self):
+		if not self.validated:
+			self.Validate()
+		if len(self.error):
+			self.parent.ShowMessage(self.error)
+			return False
+		return True
+
+# Selected branch report creation dialog
+
+class SelectedBranchDialog(QDialog):
+
+	def __init__(self, glb, parent=None):
+		super(SelectedBranchDialog, self).__init__(parent)
+
+		self.glb = glb
+
+		self.name = ""
+		self.where_clause = ""
+
+		self.setWindowTitle("Selected Branches")
+		self.setMinimumWidth(600)
+
+		items = (
+			("Report name:", "Enter a name to appear in the window title bar", "", "", "", ""),
+			("Time ranges:", "Enter time ranges", "<timeranges>", "", "samples.id", ""),
+			("CPUs:", "Enter CPUs or ranges e.g. 0,5-6", "<ranges>", "", "cpu", ""),
+			("Commands:", "Only branches with these commands will be included", "comms", "comm", "comm_id", ""),
+			("PIDs:", "Only branches with these process IDs will be included", "threads", "pid", "thread_id", ""),
+			("TIDs:", "Only branches with these thread IDs will be included", "threads", "tid", "thread_id", ""),
+			("DSOs:", "Only branches with these DSOs will be included", "dsos", "short_name", "samples.dso_id", "to_dso_id"),
+			("Symbols:", "Only branches with these symbols will be included", "symbols", "name", "symbol_id", "to_symbol_id"),
+			("Raw SQL clause: ", "Enter a raw SQL WHERE clause", "", "", "", ""),
+			)
+		self.data_items = [SQLTableDialogDataItem(glb, *x, parent=self) for x in items]
+
+		self.grid = QGridLayout()
+
+		for row in xrange(len(self.data_items)):
+			self.grid.addWidget(QLabel(self.data_items[row].label), row, 0)
+			self.grid.addWidget(self.data_items[row].widget, row, 1)
+
+		self.status = QLabel()
+
+		self.ok_button = QPushButton("Ok", self)
+		self.ok_button.setDefault(True)
+		self.ok_button.released.connect(self.Ok)
+		self.ok_button.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+		self.cancel_button = QPushButton("Cancel", self)
+		self.cancel_button.released.connect(self.reject)
+		self.cancel_button.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+		self.hbox = QHBoxLayout()
+		#self.hbox.addStretch()
+		self.hbox.addWidget(self.status)
+		self.hbox.addWidget(self.ok_button)
+		self.hbox.addWidget(self.cancel_button)
+
+		self.vbox = QVBoxLayout()
+		self.vbox.addLayout(self.grid)
+		self.vbox.addLayout(self.hbox)
+
+		self.setLayout(self.vbox);
+
+	def Ok(self):
+		self.name = self.data_items[0].value
+		if not self.name:
+			self.ShowMessage("Report name is required")
+			return
+		for d in self.data_items:
+			if not d.IsValid():
+				return
+		for d in self.data_items[1:]:
+			if len(d.value):
+				if len(self.where_clause):
+					self.where_clause += " AND "
+				self.where_clause += d.value
+		if len(self.where_clause):
+			self.where_clause = " AND ( " + self.where_clause + " ) "
+		else:
+			self.ShowMessage("No selection")
+			return
+		self.accept()
+
+	def ShowMessage(self, msg):
+		self.status.setText("<font color=#FF0000>" + msg)
+
+	def ClearMessage(self):
+		self.status.setText("")
+
 # Event list
 
 def GetEventList(db):
@@ -1656,7 +1975,7 @@ class TableWindow(QMdiSubWindow, ResizeColumnsToContentsBase):
 	def FindDone(self, row):
 		self.find_bar.Idle()
 		if row >= 0:
-			self.view.setCurrentIndex(self.model.index(row, 0, QModelIndex()))
+			self.view.setCurrentIndex(self.model.mapFromSource(self.data_model.index(row, 0, QModelIndex())))
 		else:
 			self.find_bar.NotFound()
 
@@ -1765,6 +2084,149 @@ class WindowMenu():
 	def setActiveSubWindow(self, nr):
 		self.mdi_area.setActiveSubWindow(self.mdi_area.subWindowList()[nr - 1])
 
+# Help text
+
+glb_help_text = """
+<h1>Contents</h1>
+<style>
+p.c1 {
+    text-indent: 40px;
+}
+p.c2 {
+    text-indent: 80px;
+}
+}
+</style>
+<p class=c1><a href=#reports>1. Reports</a></p>
+<p class=c2><a href=#callgraph>1.1 Context-Sensitive Call Graph</a></p>
+<p class=c2><a href=#allbranches>1.2 All branches</a></p>
+<p class=c2><a href=#selectedbranches>1.3 Selected branches</a></p>
+<p class=c1><a href=#tables>2. Tables</a></p>
+<h1 id=reports>1. Reports</h1>
+<h2 id=callgraph>1.1 Context-Sensitive Call Graph</h2>
+The result is a GUI window with a tree representing a context-sensitive
+call-graph. Expanding a couple of levels of the tree and adjusting column
+widths to suit will display something like:
+<pre>
+                                         Call Graph: pt_example
+Call Path                          Object      Count   Time(ns)  Time(%)  Branch Count   Branch Count(%)
+v- ls
+    v- 2638:2638
+        v- _start                  ld-2.19.so    1     10074071   100.0         211135            100.0
+          |- unknown               unknown       1        13198     0.1              1              0.0
+          >- _dl_start             ld-2.19.so    1      1400980    13.9          19637              9.3
+          >- _d_linit_internal     ld-2.19.so    1       448152     4.4          11094              5.3
+          v-__libc_start_main@plt  ls            1      8211741    81.5         180397             85.4
+             >- _dl_fixup          ld-2.19.so    1         7607     0.1            108              0.1
+             >- __cxa_atexit       libc-2.19.so  1        11737     0.1             10              0.0
+             >- __libc_csu_init    ls            1        10354     0.1             10              0.0
+             |- _setjmp            libc-2.19.so  1            0     0.0              4              0.0
+             v- main               ls            1      8182043    99.6         180254             99.9
+</pre>
+<h3>Points to note:</h3>
+<ul>
+<li>The top level is a command name (comm)</li>
+<li>The next level is a thread (pid:tid)</li>
+<li>Subsequent levels are functions</li>
+<li>'Count' is the number of calls</li>
+<li>'Time' is the elapsed time until the function returns</li>
+<li>Percentages are relative to the level above</li>
+<li>'Branch Count' is the total number of branches for that function and all functions that it calls
+</ul>
+<h3>Find</h3>
+Ctrl-F displays a Find bar which finds function names by either an exact match or a pattern match.
+The pattern matching symbols are ? for any character and * for zero or more characters.
+<h2 id=allbranches>1.2 All branches</h2>
+The All branches report displays all branches in chronological order.
+Not all data is fetched immediately. More records can be fetched using the Fetch bar provided.
+<h3>Disassembly</h3>
+Open a branch to display disassembly. This only works if:
+<ol>
+<li>The disassembler is available. Currently, only Intel XED is supported - see <a href=#xed>Intel XED Setup</a></li>
+<li>The object code is available. Currently, only the perf build ID cache is searched for object code.
+The default directory ~/.debug can be overridden by setting environment variable PERF_BUILDID_DIR.
+One exception is kcore where the DSO long name is used (refer dsos_view on the Tables menu),
+or alternatively, set environment variable PERF_KCORE to the kcore file name.</li>
+</ol>
+<h4 id=xed>Intel XED Setup</h4>
+To use Intel XED, libxed.so must be present.  To build and install libxed.so:
+<pre>
+git clone https://github.com/intelxed/mbuild.git mbuild
+git clone https://github.com/intelxed/xed
+cd xed
+./mfile.py --share
+sudo ./mfile.py --prefix=/usr/local install
+sudo ldconfig
+</pre>
+<h3>Find</h3>
+Ctrl-F displays a Find bar which finds substrings by either an exact match or a regular expression match.
+Refer to Python documentation for the regular expression syntax.
+All columns are searched, but only currently fetched rows are searched.
+<h2 id=selectedbranches>1.3 Selected branches</h2>
+This is the same as the <a href=#allbranches>All branches</a> report but with the data reduced
+by various selection criteria. A dialog box displays available criteria which are AND'ed together.
+<h3>1.3.1 Time ranges</h3>
+The time ranges hint text shows the total time range. Relative time ranges can also be entered in
+ms, us or ns. Also, negative values are relative to the end of trace.  Examples:
+<pre>
+	81073085947329-81073085958238	From 81073085947329 to 81073085958238
+	100us-200us		From 100us to 200us
+	10ms-			From 10ms to the end
+	-100ns			The first 100ns
+	-10ms-			The last 10ms
+</pre>
+N.B. Due to the granularity of timestamps, there could be no branches in any given time range.
+<h1 id=tables>2. Tables</h1>
+The Tables menu shows all tables and views in the database. Most tables have an associated view
+which displays the information in a more friendly way. Not all data for large tables is fetched
+immediately. More records can be fetched using the Fetch bar provided. Columns can be sorted,
+but that can be slow for large tables.
+<p>There are also tables of database meta-information.
+For SQLite3 databases, the sqlite_master table is included.
+For PostgreSQL databases, information_schema.tables/views/columns are included.
+<h3>Find</h3>
+Ctrl-F displays a Find bar which finds substrings by either an exact match or a regular expression match.
+Refer to Python documentation for the regular expression syntax.
+All columns are searched, but only currently fetched rows are searched.
+<p>N.B. Results are found in id order, so if the table is re-ordered, find-next and find-previous
+will go to the next/previous result in id order, instead of display order.
+"""
+
+# Help window
+
+class HelpWindow(QMdiSubWindow):
+
+	def __init__(self, glb, parent=None):
+		super(HelpWindow, self).__init__(parent)
+
+		self.text = QTextBrowser()
+		self.text.setHtml(glb_help_text)
+		self.text.setReadOnly(True)
+		self.text.setOpenExternalLinks(True)
+
+		self.setWidget(self.text)
+
+		AddSubWindow(glb.mainwindow.mdi_area, self, "Exported SQL Viewer Help")
+
+# Main window that only displays the help text
+
+class HelpOnlyWindow(QMainWindow):
+
+	def __init__(self, parent=None):
+		super(HelpOnlyWindow, self).__init__(parent)
+
+		self.setMinimumSize(200, 100)
+		self.resize(800, 600)
+		self.setWindowTitle("Exported SQL Viewer Help")
+		self.setWindowIcon(self.style().standardIcon(QStyle.SP_MessageBoxInformation))
+
+		self.text = QTextBrowser()
+		self.text.setHtml(glb_help_text)
+		self.text.setReadOnly(True)
+		self.text.setOpenExternalLinks(True)
+
+		self.setCentralWidget(self.text)
+
 # Font resize
 
 def ResizeFont(widget, diff):
@@ -1851,6 +2313,9 @@ class MainWindow(QMainWindow):
 
 		self.window_menu = WindowMenu(self.mdi_area, menu)
 
+		help_menu = menu.addMenu("&Help")
+		help_menu.addAction(CreateAction("&Exported SQL Viewer Help", "Helpful information", self.Help, self, QKeySequence.HelpContents))
+
 	def Find(self):
 		win = self.mdi_area.activeSubWindow()
 		if win:
@@ -1888,6 +2353,8 @@ class MainWindow(QMainWindow):
 			if event == "branches":
 				label = "All branches" if branches_events == 1 else "All branches " + "(id=" + dbid + ")"
 				reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewBranchView(x), self))
+				label = "Selected branches" if branches_events == 1 else "Selected branches " + "(id=" + dbid + ")"
+				reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewSelectedBranchView(x), self))
 
 	def TableMenu(self, tables, menu):
 		table_menu = menu.addMenu("&Tables")
@@ -1900,9 +2367,18 @@ class MainWindow(QMainWindow):
 	def NewBranchView(self, event_id):
 		BranchWindow(self.glb, event_id, "", "", self)
 
+	def NewSelectedBranchView(self, event_id):
+		dialog = SelectedBranchDialog(self.glb, self)
+		ret = dialog.exec_()
+		if ret:
+			BranchWindow(self.glb, event_id, dialog.name, dialog.where_clause, self)
+
 	def NewTableView(self, table_name):
 		TableWindow(self.glb, table_name, self)
 
+	def Help(self):
+		HelpWindow(self.glb, self)
+
 # XED Disassembler
 
 class xed_state_t(Structure):
@@ -1929,7 +2405,12 @@ class XEDInstruction():
 class LibXED():
 
 	def __init__(self):
-		self.libxed = CDLL("libxed.so")
+		try:
+			self.libxed = CDLL("libxed.so")
+		except:
+			self.libxed = None
+		if not self.libxed:
+			self.libxed = CDLL("/usr/local/lib/libxed.so")
 
 		self.xed_tables_init = self.libxed.xed_tables_init
 		self.xed_tables_init.restype = None
@@ -2097,10 +2578,16 @@ class DBRef():
 
 def Main():
 	if (len(sys.argv) < 2):
-		print >> sys.stderr, "Usage is: exported-sql-viewer.py <database name>"
+		print >> sys.stderr, "Usage is: exported-sql-viewer.py {<database name> | --help-only}"
 		raise Exception("Too few arguments")
 
 	dbname = sys.argv[1]
+	if dbname == "--help-only":
+		app = QApplication(sys.argv)
+		mainwindow = HelpOnlyWindow()
+		mainwindow.show()
+		err = app.exec_()
+		sys.exit(err)
 
 	is_sqlite3 = False
 	try:
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
index 37940665f736..efd0157b9d22 100644
--- a/tools/perf/tests/attr/base-record
+++ b/tools/perf/tests/attr/base-record
@@ -9,7 +9,7 @@ size=112
 config=0
 sample_period=*
 sample_type=263
-read_format=0
+read_format=0|4
 disabled=1
 inherit=1
 pinned=0
diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling
index 8a33ca4f9e1f..f0729c454f16 100644
--- a/tools/perf/tests/attr/test-record-group-sampling
+++ b/tools/perf/tests/attr/test-record-group-sampling
@@ -37,4 +37,3 @@ sample_freq=0
 sample_period=0
 freq=0
 write_backward=0
-sample_id_all=0
diff --git a/tools/perf/trace/beauty/ioctl.c b/tools/perf/trace/beauty/ioctl.c
index 5d2a7fd8d407..eae59ad15ce3 100644
--- a/tools/perf/trace/beauty/ioctl.c
+++ b/tools/perf/trace/beauty/ioctl.c
@@ -31,6 +31,7 @@ static size_t ioctl__scnprintf_tty_cmd(int nr, int dir, char *bf, size_t size)
 	"TCSETSW2", "TCSETSF2", "TIOCGRS48", "TIOCSRS485", "TIOCGPTN", "TIOCSPTLCK",
 	"TIOCGDEV", "TCSETX", "TCSETXF", "TCSETXW", "TIOCSIG", "TIOCVHANGUP", "TIOCGPKT",
 	"TIOCGPTLCK", [_IOC_NR(TIOCGEXCL)] = "TIOCGEXCL", "TIOCGPTPEER",
+	"TIOCGISO7816", "TIOCSISO7816",
 	[_IOC_NR(FIONCLEX)] = "FIONCLEX", "FIOCLEX", "FIOASYNC", "TIOCSERCONFIG",
 	"TIOCSERGWILD", "TIOCSERSWILD", "TIOCGLCKTRMIOS", "TIOCSLCKTRMIOS",
 	"TIOCSERGSTRUCT", "TIOCSERGETLSR", "TIOCSERGETMULTI", "TIOCSERSETMULTI",
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index ecd9f9ceda77..b7bf201fe8a8 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -10,6 +10,7 @@ libperf-y += evlist.o
 libperf-y += evsel.o
 libperf-y += evsel_fprintf.o
 libperf-y += find_bit.o
+libperf-y += get_current_dir_name.o
 libperf-y += kallsyms.o
 libperf-y += levenshtein.o
 libperf-y += llvm-utils.o
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e88e6f9b1463..668d2a9ef0f4 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1810,3 +1810,30 @@ void perf_evlist__force_leader(struct perf_evlist *evlist)
 		leader->forced_leader = true;
 	}
 }
+
+struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evsel_list,
+						 struct perf_evsel *evsel)
+{
+	struct perf_evsel *c2, *leader;
+	bool is_open = true;
+
+	leader = evsel->leader;
+	pr_debug("Weak group for %s/%d failed\n",
+			leader->name, leader->nr_members);
+
+	/*
+	 * for_each_group_member doesn't work here because it doesn't
+	 * include the first entry.
+	 */
+	evlist__for_each_entry(evsel_list, c2) {
+		if (c2 == evsel)
+			is_open = false;
+		if (c2->leader == leader) {
+			if (is_open)
+				perf_evsel__close(c2);
+			c2->leader = c2;
+			c2->nr_members = 0;
+		}
+	}
+	return leader;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index dc66436add98..9919eed6d15b 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -312,4 +312,7 @@ bool perf_evlist__exclude_kernel(struct perf_evlist *evlist);
 
 void perf_evlist__force_leader(struct perf_evlist *evlist);
 
+struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evlist,
+						 struct perf_evsel *evsel);
+
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 6d187059a373..dbc0466db368 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -956,7 +956,6 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		attr->sample_freq    = 0;
 		attr->sample_period  = 0;
 		attr->write_backward = 0;
-		attr->sample_id_all  = 0;
 	}
 
 	if (opts->no_samples)
@@ -1093,7 +1092,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		attr->exclude_user   = 1;
 	}
 
-	if (evsel->own_cpus)
+	if (evsel->own_cpus || evsel->unit)
 		evsel->attr.read_format |= PERF_FORMAT_ID;
 
 	/*
diff --git a/tools/perf/util/get_current_dir_name.c b/tools/perf/util/get_current_dir_name.c
new file mode 100644
index 000000000000..267aa609a582
--- /dev/null
+++ b/tools/perf/util/get_current_dir_name.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+//
+#ifndef HAVE_GET_CURRENT_DIR_NAME
+#include "util.h"
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdlib.h>
+
+/* Android's 'bionic' library, for one, doesn't have this */
+
+char *get_current_dir_name(void)
+{
+	char pwd[PATH_MAX];
+
+	return getcwd(pwd, sizeof(pwd)) == NULL ? NULL : strdup(pwd);
+}
+#endif // HAVE_GET_CURRENT_DIR_NAME
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 58f6a9ceb590..4503f3ca45ab 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1474,6 +1474,8 @@ static void intel_pt_calc_mtc_timestamp(struct intel_pt_decoder *decoder)
 		decoder->have_calc_cyc_to_tsc = false;
 		intel_pt_calc_cyc_to_tsc(decoder, true);
 	}
+
+	intel_pt_log_to("Setting timestamp", decoder->timestamp);
 }
 
 static void intel_pt_calc_cbr(struct intel_pt_decoder *decoder)
@@ -1514,6 +1516,8 @@ static void intel_pt_calc_cyc_timestamp(struct intel_pt_decoder *decoder)
 		decoder->timestamp = timestamp;
 
 	decoder->timestamp_insn_cnt = 0;
+
+	intel_pt_log_to("Setting timestamp", decoder->timestamp);
 }
 
 /* Walk PSB+ packets when already in sync. */
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.c b/tools/perf/util/intel-pt-decoder/intel-pt-log.c
index e02bc7b166a0..5e64da270f97 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-log.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.c
@@ -31,6 +31,11 @@ static FILE *f;
 static char log_name[MAX_LOG_NAME];
 bool intel_pt_enable_logging;
 
+void *intel_pt_log_fp(void)
+{
+	return f;
+}
+
 void intel_pt_log_enable(void)
 {
 	intel_pt_enable_logging = true;
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.h b/tools/perf/util/intel-pt-decoder/intel-pt-log.h
index 45b64f93f358..cc084937f701 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-log.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.h
@@ -22,6 +22,7 @@
 
 struct intel_pt_pkt;
 
+void *intel_pt_log_fp(void);
 void intel_pt_log_enable(void);
 void intel_pt_log_disable(void);
 void intel_pt_log_set_name(const char *name);
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 86cc9a64e982..149ff361ca78 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -206,6 +206,16 @@ static void intel_pt_dump_event(struct intel_pt *pt, unsigned char *buf,
 	intel_pt_dump(pt, buf, len);
 }
 
+static void intel_pt_log_event(union perf_event *event)
+{
+	FILE *f = intel_pt_log_fp();
+
+	if (!intel_pt_enable_logging || !f)
+		return;
+
+	perf_event__fprintf(event, f);
+}
+
 static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a,
 				   struct auxtrace_buffer *b)
 {
@@ -2010,9 +2020,9 @@ static int intel_pt_process_event(struct perf_session *session,
 		 event->header.type == PERF_RECORD_SWITCH_CPU_WIDE)
 		err = intel_pt_context_switch(pt, event, sample);
 
-	intel_pt_log("event %s (%u): cpu %d time %"PRIu64" tsc %#"PRIx64"\n",
-		     perf_event__name(event->header.type), event->header.type,
-		     sample->cpu, sample->time, timestamp);
+	intel_pt_log("event %u: cpu %d time %"PRIu64" tsc %#"PRIx64" ",
+		     event->header.type, sample->cpu, sample->time, timestamp);
+	intel_pt_log_event(event);
 
 	return err;
 }
diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c
index cf8bd123cf73..aed170bd4384 100644
--- a/tools/perf/util/namespaces.c
+++ b/tools/perf/util/namespaces.c
@@ -18,6 +18,7 @@
 #include <stdio.h>
 #include <string.h>
 #include <unistd.h>
+#include <asm/bug.h>
 
 struct namespaces *namespaces__new(struct namespaces_event *event)
 {
@@ -186,6 +187,7 @@ void nsinfo__mountns_enter(struct nsinfo *nsi,
 	char curpath[PATH_MAX];
 	int oldns = -1;
 	int newns = -1;
+	char *oldcwd = NULL;
 
 	if (nc == NULL)
 		return;
@@ -199,9 +201,13 @@ void nsinfo__mountns_enter(struct nsinfo *nsi,
 	if (snprintf(curpath, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX)
 		return;
 
+	oldcwd = get_current_dir_name();
+	if (!oldcwd)
+		return;
+
 	oldns = open(curpath, O_RDONLY);
 	if (oldns < 0)
-		return;
+		goto errout;
 
 	newns = open(nsi->mntns_path, O_RDONLY);
 	if (newns < 0)
@@ -210,11 +216,13 @@ void nsinfo__mountns_enter(struct nsinfo *nsi,
 	if (setns(newns, CLONE_NEWNS) < 0)
 		goto errout;
 
+	nc->oldcwd = oldcwd;
 	nc->oldns = oldns;
 	nc->newns = newns;
 	return;
 
 errout:
+	free(oldcwd);
 	if (oldns > -1)
 		close(oldns);
 	if (newns > -1)
@@ -223,11 +231,16 @@ errout:
 
 void nsinfo__mountns_exit(struct nscookie *nc)
 {
-	if (nc == NULL || nc->oldns == -1 || nc->newns == -1)
+	if (nc == NULL || nc->oldns == -1 || nc->newns == -1 || !nc->oldcwd)
 		return;
 
 	setns(nc->oldns, CLONE_NEWNS);
 
+	if (nc->oldcwd) {
+		WARN_ON_ONCE(chdir(nc->oldcwd));
+		zfree(&nc->oldcwd);
+	}
+
 	if (nc->oldns > -1) {
 		close(nc->oldns);
 		nc->oldns = -1;
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index cae1a9a39722..d5f46c09ea31 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -38,6 +38,7 @@ struct nsinfo {
 struct nscookie {
 	int			oldns;
 	int			newns;
+	char			*oldcwd;
 };
 
 int nsinfo__init(struct nsinfo *nsi);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 7799788f662f..7e49baad304d 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -773,7 +773,7 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
 
 		if (!is_arm_pmu_core(name)) {
 			pname = pe->pmu ? pe->pmu : "cpu";
-			if (strncmp(pname, name, strlen(pname)))
+			if (strcmp(pname, name))
 				continue;
 		}
 
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 14508ee7707a..ece040b799f6 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -59,6 +59,10 @@ int fetch_kernel_version(unsigned int *puint,
 
 const char *perf_tip(const char *dirpath);
 
+#ifndef HAVE_GET_CURRENT_DIR_NAME
+char *get_current_dir_name(void);
+#endif
+
 #ifndef HAVE_SCHED_GETCPU_SUPPORT
 int sched_getcpu(void);
 #endif
diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile
index 1dd5f4fcffd5..db66a952c173 100644
--- a/tools/power/cpupower/Makefile
+++ b/tools/power/cpupower/Makefile
@@ -129,7 +129,7 @@ WARNINGS += $(call cc-supports,-Wno-pointer-sign)
 WARNINGS += $(call cc-supports,-Wdeclaration-after-statement)
 WARNINGS += -Wshadow
 
-CFLAGS += -DVERSION=\"$(VERSION)\" -DPACKAGE=\"$(PACKAGE)\" \
+override CFLAGS += -DVERSION=\"$(VERSION)\" -DPACKAGE=\"$(PACKAGE)\" \
 		-DPACKAGE_BUGREPORT=\"$(PACKAGE_BUGREPORT)\" -D_GNU_SOURCE
 
 UTIL_OBJS =  utils/helpers/amd.o utils/helpers/msr.o \
@@ -156,12 +156,12 @@ LIB_SRC = 	lib/cpufreq.c lib/cpupower.c lib/cpuidle.c
 LIB_OBJS = 	lib/cpufreq.o lib/cpupower.o lib/cpuidle.o
 LIB_OBJS :=	$(addprefix $(OUTPUT),$(LIB_OBJS))
 
-CFLAGS +=	-pipe
+override CFLAGS +=	-pipe
 
 ifeq ($(strip $(NLS)),true)
 	INSTALL_NLS += install-gmo
 	COMPILE_NLS += create-gmo
-	CFLAGS += -DNLS
+	override CFLAGS += -DNLS
 endif
 
 ifeq ($(strip $(CPUFREQ_BENCH)),true)
@@ -175,7 +175,7 @@ ifeq ($(strip $(STATIC)),true)
         UTIL_SRC += $(LIB_SRC)
 endif
 
-CFLAGS += $(WARNINGS)
+override CFLAGS += $(WARNINGS)
 
 ifeq ($(strip $(V)),false)
 	QUIET=@
@@ -188,10 +188,10 @@ export QUIET ECHO
 
 # if DEBUG is enabled, then we do not strip or optimize
 ifeq ($(strip $(DEBUG)),true)
-	CFLAGS += -O1 -g -DDEBUG
+	override CFLAGS += -O1 -g -DDEBUG
 	STRIPCMD = /bin/true -Since_we_are_debugging
 else
-	CFLAGS += $(OPTIMIZATION) -fomit-frame-pointer
+	override CFLAGS += $(OPTIMIZATION) -fomit-frame-pointer
 	STRIPCMD = $(STRIP) -s --remove-section=.note --remove-section=.comment
 endif
 
diff --git a/tools/power/cpupower/bench/Makefile b/tools/power/cpupower/bench/Makefile
index d79ab161cc75..f68b4bc55273 100644
--- a/tools/power/cpupower/bench/Makefile
+++ b/tools/power/cpupower/bench/Makefile
@@ -9,7 +9,7 @@ endif
 ifeq ($(strip $(STATIC)),true)
 LIBS = -L../ -L$(OUTPUT) -lm
 OBJS = $(OUTPUT)main.o $(OUTPUT)parse.o $(OUTPUT)system.o $(OUTPUT)benchmark.o \
-       $(OUTPUT)../lib/cpufreq.o $(OUTPUT)../lib/sysfs.o
+       $(OUTPUT)../lib/cpufreq.o $(OUTPUT)../lib/cpupower.o
 else
 LIBS = -L../ -L$(OUTPUT) -lm -lcpupower
 OBJS = $(OUTPUT)main.o $(OUTPUT)parse.o $(OUTPUT)system.o $(OUTPUT)benchmark.o
diff --git a/tools/power/cpupower/debug/x86_64/Makefile b/tools/power/cpupower/debug/x86_64/Makefile
index 59af84b8ef45..b1b6c43644e7 100644
--- a/tools/power/cpupower/debug/x86_64/Makefile
+++ b/tools/power/cpupower/debug/x86_64/Makefile
@@ -13,10 +13,10 @@ INSTALL = /usr/bin/install
 default: all
 
 $(OUTPUT)centrino-decode: ../i386/centrino-decode.c
-	$(CC) $(CFLAGS) -o $@ $<
+	$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $<
 
 $(OUTPUT)powernow-k8-decode: ../i386/powernow-k8-decode.c
-	$(CC) $(CFLAGS) -o $@ $<
+	$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $<
 
 all: $(OUTPUT)centrino-decode $(OUTPUT)powernow-k8-decode
 
diff --git a/tools/power/cpupower/lib/cpufreq.c b/tools/power/cpupower/lib/cpufreq.c
index 1b993fe1ce23..0c0f3e3f0d80 100644
--- a/tools/power/cpupower/lib/cpufreq.c
+++ b/tools/power/cpupower/lib/cpufreq.c
@@ -28,7 +28,7 @@ static unsigned int sysfs_cpufreq_read_file(unsigned int cpu, const char *fname,
 
 	snprintf(path, sizeof(path), PATH_TO_CPU "cpu%u/cpufreq/%s",
 			 cpu, fname);
-	return sysfs_read_file(path, buf, buflen);
+	return cpupower_read_sysfs(path, buf, buflen);
 }
 
 /* helper function to write a new value to a /sys file */
diff --git a/tools/power/cpupower/lib/cpuidle.c b/tools/power/cpupower/lib/cpuidle.c
index 9bd4c7655fdb..852d25462388 100644
--- a/tools/power/cpupower/lib/cpuidle.c
+++ b/tools/power/cpupower/lib/cpuidle.c
@@ -319,7 +319,7 @@ static unsigned int sysfs_cpuidle_read_file(const char *fname, char *buf,
 
 	snprintf(path, sizeof(path), PATH_TO_CPU "cpuidle/%s", fname);
 
-	return sysfs_read_file(path, buf, buflen);
+	return cpupower_read_sysfs(path, buf, buflen);
 }
 
 
diff --git a/tools/power/cpupower/lib/cpupower.c b/tools/power/cpupower/lib/cpupower.c
index 9c395ec924de..9711d628b0f4 100644
--- a/tools/power/cpupower/lib/cpupower.c
+++ b/tools/power/cpupower/lib/cpupower.c
@@ -15,7 +15,7 @@
 #include "cpupower.h"
 #include "cpupower_intern.h"
 
-unsigned int sysfs_read_file(const char *path, char *buf, size_t buflen)
+unsigned int cpupower_read_sysfs(const char *path, char *buf, size_t buflen)
 {
 	int fd;
 	ssize_t numread;
@@ -95,7 +95,7 @@ static int sysfs_topology_read_file(unsigned int cpu, const char *fname, int *re
 
 	snprintf(path, sizeof(path), PATH_TO_CPU "cpu%u/topology/%s",
 			 cpu, fname);
-	if (sysfs_read_file(path, linebuf, MAX_LINE_LEN) == 0)
+	if (cpupower_read_sysfs(path, linebuf, MAX_LINE_LEN) == 0)
 		return -1;
 	*result = strtol(linebuf, &endp, 0);
 	if (endp == linebuf || errno == ERANGE)
diff --git a/tools/power/cpupower/lib/cpupower_intern.h b/tools/power/cpupower/lib/cpupower_intern.h
index 92affdfbe417..4887c76d23f8 100644
--- a/tools/power/cpupower/lib/cpupower_intern.h
+++ b/tools/power/cpupower/lib/cpupower_intern.h
@@ -3,4 +3,4 @@
 #define MAX_LINE_LEN 4096
 #define SYSFS_PATH_MAX 255
 
-unsigned int sysfs_read_file(const char *path, char *buf, size_t buflen);
+unsigned int cpupower_read_sysfs(const char *path, char *buf, size_t buflen);
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 9527d47a1070..01ec04bf91b5 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -140,8 +140,8 @@ static u32 handle[] = {
 	[6] = NFIT_DIMM_HANDLE(1, 0, 0, 0, 1),
 };
 
-static unsigned long dimm_fail_cmd_flags[NUM_DCR];
-static int dimm_fail_cmd_code[NUM_DCR];
+static unsigned long dimm_fail_cmd_flags[ARRAY_SIZE(handle)];
+static int dimm_fail_cmd_code[ARRAY_SIZE(handle)];
 
 static const struct nd_intel_smart smart_def = {
 	.flags = ND_INTEL_SMART_HEALTH_VALID
@@ -205,7 +205,7 @@ struct nfit_test {
 		unsigned long deadline;
 		spinlock_t lock;
 	} ars_state;
-	struct device *dimm_dev[NUM_DCR];
+	struct device *dimm_dev[ARRAY_SIZE(handle)];
 	struct nd_intel_smart *smart;
 	struct nd_intel_smart_threshold *smart_threshold;
 	struct badrange badrange;
@@ -2680,7 +2680,7 @@ static int nfit_test_probe(struct platform_device *pdev)
 		u32 nfit_handle = __to_nfit_memdev(nfit_mem)->device_handle;
 		int i;
 
-		for (i = 0; i < NUM_DCR; i++)
+		for (i = 0; i < ARRAY_SIZE(handle); i++)
 			if (nfit_handle == handle[i])
 				dev_set_drvdata(nfit_test->dimm_dev[i],
 						nfit_mem);
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index f1fe492c8e17..f0017c831e57 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -24,6 +24,7 @@ TARGETS += memory-hotplug
 TARGETS += mount
 TARGETS += mqueue
 TARGETS += net
+TARGETS += netfilter
 TARGETS += nsfs
 TARGETS += powerpc
 TARGETS += proc
diff --git a/tools/testing/selftests/bpf/test_netcnt.c b/tools/testing/selftests/bpf/test_netcnt.c
index 7887df693399..44ed7f29f8ab 100644
--- a/tools/testing/selftests/bpf/test_netcnt.c
+++ b/tools/testing/selftests/bpf/test_netcnt.c
@@ -81,7 +81,10 @@ int main(int argc, char **argv)
 		goto err;
 	}
 
-	assert(system("ping localhost -6 -c 10000 -f -q > /dev/null") == 0);
+	if (system("which ping6 &>/dev/null") == 0)
+		assert(!system("ping6 localhost -c 10000 -f -q > /dev/null"));
+	else
+		assert(!system("ping -6 localhost -c 10000 -f -q > /dev/null"));
 
 	if (bpf_prog_query(cgroup_fd, BPF_CGROUP_INET_EGRESS, 0, NULL, NULL,
 			   &prog_cnt)) {
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 6f61df62f690..550b7e46bf4a 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -13896,6 +13896,25 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = ACCEPT,
 	},
+	{
+		"calls: ctx read at start of subprog",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5),
+			BPF_JMP_REG(BPF_JSGT, BPF_REG_0, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_EXIT_INSN(),
+			BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_1, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+		.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+		.result_unpriv = REJECT,
+		.result = ACCEPT,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
new file mode 100644
index 000000000000..47ed6cef93fb
--- /dev/null
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for netfilter selftests
+
+TEST_PROGS := nft_trans_stress.sh
+
+include ../lib.mk
diff --git a/tools/testing/selftests/netfilter/config b/tools/testing/selftests/netfilter/config
new file mode 100644
index 000000000000..1017313e41a8
--- /dev/null
+++ b/tools/testing/selftests/netfilter/config
@@ -0,0 +1,2 @@
+CONFIG_NET_NS=y
+NF_TABLES_INET=y
diff --git a/tools/testing/selftests/netfilter/nft_trans_stress.sh b/tools/testing/selftests/netfilter/nft_trans_stress.sh
new file mode 100755
index 000000000000..f1affd12c4b1
--- /dev/null
+++ b/tools/testing/selftests/netfilter/nft_trans_stress.sh
@@ -0,0 +1,78 @@
+#!/bin/bash
+#
+# This test is for stress-testing the nf_tables config plane path vs.
+# packet path processing: Make sure we never release rules that are
+# still visible to other cpus.
+#
+# set -e
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+testns=testns1
+tables="foo bar baz quux"
+
+nft --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without nft tool"
+	exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+tmp=$(mktemp)
+
+for table in $tables; do
+	echo add table inet "$table" >> "$tmp"
+	echo flush table inet "$table" >> "$tmp"
+
+	echo "add chain inet $table INPUT { type filter hook input priority 0; }" >> "$tmp"
+	echo "add chain inet $table OUTPUT { type filter hook output priority 0; }" >> "$tmp"
+	for c in $(seq 1 400); do
+		chain=$(printf "chain%03u" "$c")
+		echo "add chain inet $table $chain" >> "$tmp"
+	done
+
+	for c in $(seq 1 400); do
+		chain=$(printf "chain%03u" "$c")
+		for BASE in INPUT OUTPUT; do
+			echo "add rule inet $table $BASE counter jump $chain" >> "$tmp"
+		done
+		echo "add rule inet $table $chain counter return" >> "$tmp"
+	done
+done
+
+ip netns add "$testns"
+ip -netns "$testns" link set lo up
+
+lscpu | grep ^CPU\(s\): | ( read cpu cpunum ;
+cpunum=$((cpunum-1))
+for i in $(seq 0 $cpunum);do
+	mask=$(printf 0x%x $((1<<$i)))
+        ip netns exec "$testns" taskset $mask ping -4 127.0.0.1 -fq > /dev/null &
+        ip netns exec "$testns" taskset $mask ping -6 ::1 -fq > /dev/null &
+done)
+
+sleep 1
+
+for i in $(seq 1 10) ; do ip netns exec "$testns" nft -f "$tmp" & done
+
+for table in $tables;do
+	randsleep=$((RANDOM%10))
+	sleep $randsleep
+	ip netns exec "$testns" nft delete table inet $table 2>/dev/null
+done
+
+randsleep=$((RANDOM%10))
+sleep $randsleep
+
+pkill -9 ping
+
+wait
+
+rm -f "$tmp"
+ip netns del "$testns"
diff --git a/tools/testing/selftests/powerpc/mm/wild_bctr.c b/tools/testing/selftests/powerpc/mm/wild_bctr.c
index 1b0e9e9a2ddc..f2fa101c5a6a 100644
--- a/tools/testing/selftests/powerpc/mm/wild_bctr.c
+++ b/tools/testing/selftests/powerpc/mm/wild_bctr.c
@@ -47,8 +47,9 @@ static int ok(void)
 	return 0;
 }
 
-#define REG_POISON	0x5a5aUL
-#define POISONED_REG(n)	((REG_POISON << 48) | ((n) << 32) | (REG_POISON << 16) | (n))
+#define REG_POISON	0x5a5a
+#define POISONED_REG(n)	((((unsigned long)REG_POISON) << 48) | ((n) << 32) | \
+			 (((unsigned long)REG_POISON) << 16) | (n))
 
 static inline void poison_regs(void)
 {
@@ -105,6 +106,20 @@ static void dump_regs(void)
 	}
 }
 
+#ifdef _CALL_AIXDESC
+struct opd {
+	unsigned long ip;
+	unsigned long toc;
+	unsigned long env;
+};
+static struct opd bad_opd = {
+	.ip = BAD_NIP,
+};
+#define BAD_FUNC (&bad_opd)
+#else
+#define BAD_FUNC BAD_NIP
+#endif
+
 int test_wild_bctr(void)
 {
 	int (*func_ptr)(void);
@@ -133,7 +148,7 @@ int test_wild_bctr(void)
 
 		poison_regs();
 
-		func_ptr = (int (*)(void))BAD_NIP;
+		func_ptr = (int (*)(void))BAD_FUNC;
 		func_ptr();
 
 		FAIL_IF(1); /* we didn't segv? */
diff --git a/tools/testing/selftests/proc/proc-self-map-files-002.c b/tools/testing/selftests/proc/proc-self-map-files-002.c
index 6f1f4a6e1ecb..85744425b08d 100644
--- a/tools/testing/selftests/proc/proc-self-map-files-002.c
+++ b/tools/testing/selftests/proc/proc-self-map-files-002.c
@@ -13,7 +13,7 @@
  * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
  * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
  */
-/* Test readlink /proc/self/map_files/... with address 0. */
+/* Test readlink /proc/self/map_files/... with minimum address. */
 #include <errno.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -47,6 +47,11 @@ static void fail(const char *fmt, unsigned long a, unsigned long b)
 int main(void)
 {
 	const unsigned int PAGE_SIZE = sysconf(_SC_PAGESIZE);
+#ifdef __arm__
+	unsigned long va = 2 * PAGE_SIZE;
+#else
+	unsigned long va = 0;
+#endif
 	void *p;
 	int fd;
 	unsigned long a, b;
@@ -55,7 +60,7 @@ int main(void)
 	if (fd == -1)
 		return 1;
 
-	p = mmap(NULL, PAGE_SIZE, PROT_NONE, MAP_PRIVATE|MAP_FILE|MAP_FIXED, fd, 0);
+	p = mmap((void *)va, PAGE_SIZE, PROT_NONE, MAP_PRIVATE|MAP_FILE|MAP_FIXED, fd, 0);
 	if (p == MAP_FAILED) {
 		if (errno == EPERM)
 			return 2;
diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index 87a04a8a5945..7607ba3e3cbe 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -134,9 +134,9 @@ def exec_cmd(args, pm, stage, command):
     (rawout, serr) = proc.communicate()
 
     if proc.returncode != 0 and len(serr) > 0:
-        foutput = serr.decode("utf-8")
+        foutput = serr.decode("utf-8", errors="ignore")
     else:
-        foutput = rawout.decode("utf-8")
+        foutput = rawout.decode("utf-8", errors="ignore")
 
     proc.stdout.close()
     proc.stderr.close()
@@ -169,6 +169,8 @@ def prepare_env(args, pm, stage, prefix, cmdlist, output = None):
                   file=sys.stderr)
             print("\n{} *** Error message: \"{}\"".format(prefix, foutput),
                   file=sys.stderr)
+            print("returncode {}; expected {}".format(proc.returncode,
+                                                      exit_codes))
             print("\n{} *** Aborting test run.".format(prefix), file=sys.stderr)
             print("\n\n{} *** stdout ***".format(proc.stdout), file=sys.stderr)
             print("\n\n{} *** stderr ***".format(proc.stderr), file=sys.stderr)
@@ -195,12 +197,18 @@ def run_one_test(pm, args, index, tidx):
         print('-----> execute stage')
     pm.call_pre_execute()
     (p, procout) = exec_cmd(args, pm, 'execute', tidx["cmdUnderTest"])
-    exit_code = p.returncode
+    if p:
+        exit_code = p.returncode
+    else:
+        exit_code = None
+
     pm.call_post_execute()
 
-    if (exit_code != int(tidx["expExitCode"])):
+    if (exit_code is None or exit_code != int(tidx["expExitCode"])):
         result = False
-        print("exit:", exit_code, int(tidx["expExitCode"]))
+        print("exit: {!r}".format(exit_code))
+        print("exit: {}".format(int(tidx["expExitCode"])))
+        #print("exit: {!r} {}".format(exit_code, int(tidx["expExitCode"])))
         print(procout)
     else:
         if args.verbose > 0: