Merge branch 'for-4.12/asus' into for-linus

212 files changed, 8075 insertions, 2419 deletions

diff --git a/tools/build/Makefile b/tools/build/Makefile
index aaf7ed329a45..477f00eda591 100644
--- a/tools/build/Makefile
+++ b/tools/build/Makefile
@@ -35,8 +35,8 @@ all: $(OUTPUT)fixdep
 
 clean:
         $(call QUIET_CLEAN, fixdep)
-        $(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
-        $(Q)rm -f fixdep
+        $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
+        $(Q)rm -f $(OUTPUT)fixdep
 
 $(OUTPUT)fixdep-in.o: FORCE
         $(Q)$(MAKE) $(build)=fixdep
diff --git a/tools/build/Makefile.include b/tools/build/Makefile.include
index ad22e4e7bc59..d360f39a445b 100644
--- a/tools/build/Makefile.include
+++ b/tools/build/Makefile.include
@@ -3,4 +3,7 @@ build := -f $(srctree)/tools/build/Makefile.build dir=. obj
 fixdep:
         $(Q)$(MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= $(OUTPUT)fixdep
 
+fixdep-clean:
+        $(Q)$(MAKE) -C $(srctree)/tools/build clean
+
 .PHONY: fixdep
diff --git a/tools/gpio/.gitignore b/tools/gpio/.gitignore
new file mode 100644
index 000000000000..9e9dd4b681b2
--- /dev/null
+++ b/tools/gpio/.gitignore
@@ -0,0 +1,4 @@
+gpio-event-mon
+gpio-hammer
+lsgpio
+
diff --git a/tools/gpio/gpio-hammer.c b/tools/gpio/gpio-hammer.c
index f1eab587dfea..4bcb234c0fca 100644
--- a/tools/gpio/gpio-hammer.c
+++ b/tools/gpio/gpio-hammer.c
@@ -38,7 +38,7 @@ int hammer_device(const char *device_name, unsigned int *lines, int nlines,
         memset(&data.values, 0, sizeof(data.values));
         ret = gpiotools_request_linehandle(device_name, lines, nlines,
                                            GPIOHANDLE_REQUEST_OUTPUT, &data,
-                                           "gpio-hammler");
+                                           "gpio-hammer");
         if (ret < 0)
                 goto exit_error;
         else
diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c
index d9b7e0f306c6..b61245e1181d 100644
--- a/tools/iio/iio_event_monitor.c
+++ b/tools/iio/iio_event_monitor.c
@@ -57,6 +57,7 @@ static const char * const iio_chan_type_name_spec[] = {
         [IIO_RESISTANCE] = "resistance",
         [IIO_PH] = "ph",
         [IIO_UVINDEX] = "uvindex",
+        [IIO_GRAVITY] = "gravity",
 };
 
 static const char * const iio_ev_type_text[] = {
@@ -149,6 +150,7 @@ static bool event_is_known(struct iio_event_data *event)
         case IIO_RESISTANCE:
         case IIO_PH:
         case IIO_UVINDEX:
+        case IIO_GRAVITY:
                 break;
         default:
                 return false;
diff --git a/tools/include/asm-generic/bitops/atomic.h b/tools/include/asm-generic/bitops/atomic.h
index 18663f59d72f..68b8c1516c5a 100644
--- a/tools/include/asm-generic/bitops/atomic.h
+++ b/tools/include/asm-generic/bitops/atomic.h
@@ -20,4 +20,7 @@ static __always_inline int test_bit(unsigned int nr, const unsigned long *addr)
                 (((unsigned long *)addr)[nr / __BITS_PER_LONG])) != 0;
 }
 
+#define __set_bit(nr, addr)     set_bit(nr, addr)
+#define __clear_bit(nr, addr)   clear_bit(nr, addr)
+
 #endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_ */
diff --git a/tools/include/asm/bug.h b/tools/include/asm/bug.h
index beda1a884b50..4790f047a89c 100644
--- a/tools/include/asm/bug.h
+++ b/tools/include/asm/bug.h
@@ -12,6 +12,14 @@
         unlikely(__ret_warn_on);                \
 })
 
+#define WARN_ON(condition) ({                                   \
+        int __ret_warn_on = !!(condition);                      \
+        if (unlikely(__ret_warn_on))                            \
+                __WARN_printf("assertion failed at %s:%d\n",    \
+                                __FILE__, __LINE__);            \
+        unlikely(__ret_warn_on);                                \
+})
+
 #define WARN_ON_ONCE(condition) ({                      \
         static int __warned;                            \
         int __ret_warn_once = !!(condition);            \
diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index eef41d500e9e..e8b9f518e36b 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -4,6 +4,7 @@
 #include <string.h>
 #include <linux/bitops.h>
 #include <stdlib.h>
+#include <linux/kernel.h>
 
 #define DECLARE_BITMAP(name,bits) \
         unsigned long name[BITS_TO_LONGS(bits)]
diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h
index fc446343ff41..1aecad369af5 100644
--- a/tools/include/linux/bitops.h
+++ b/tools/include/linux/bitops.h
@@ -2,7 +2,6 @@
 #define _TOOLS_LINUX_BITOPS_H_
 
 #include <asm/types.h>
-#include <linux/kernel.h>
 #include <linux/compiler.h>
 
 #ifndef __WORDSIZE
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 6326ede9aece..8de163b17c0d 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -25,6 +25,8 @@
 #endif
 
 #define __user
+#define __rcu
+#define __read_mostly
 
 #ifndef __attribute_const__
 # define __attribute_const__
@@ -54,6 +56,8 @@
 # define unlikely(x)            __builtin_expect(!!(x), 0)
 #endif
 
+#define uninitialized_var(x) x = *(&(x))
+
 #define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
 
 #include <linux/types.h>
diff --git a/tools/include/linux/log2.h b/tools/include/linux/log2.h
index 41446668ccce..d5677d39c1e4 100644
--- a/tools/include/linux/log2.h
+++ b/tools/include/linux/log2.h
@@ -13,12 +13,6 @@
 #define _TOOLS_LINUX_LOG2_H
 
 /*
- * deal with unrepresentable constant logarithms
- */
-extern __attribute__((const, noreturn))
-int ____ilog2_NaN(void);
-
-/*
  * non-constant log of base 2 calculators
  * - the arch may override these in asm/bitops.h if they can be implemented
  *   more efficiently than using fls() and fls64()
@@ -78,7 +72,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
 #define ilog2(n)                                \
 (                                               \
         __builtin_constant_p(n) ? (             \
-                (n) < 1 ? ____ilog2_NaN() :     \
+                (n) < 2 ? 0 :                   \
                 (n) & (1ULL << 63) ? 63 :       \
                 (n) & (1ULL << 62) ? 62 :       \
                 (n) & (1ULL << 61) ? 61 :       \
@@ -141,10 +135,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
                 (n) & (1ULL <<  4) ?  4 :       \
                 (n) & (1ULL <<  3) ?  3 :       \
                 (n) & (1ULL <<  2) ?  2 :       \
-                (n) & (1ULL <<  1) ?  1 :       \
-                (n) & (1ULL <<  0) ?  0 :       \
-                ____ilog2_NaN()                 \
-                                   ) :          \
+                1 ) :                           \
         (sizeof(n) <= 4) ?                      \
         __ilog2_u32(n) :                        \
         __ilog2_u64(n)                          \
diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h
new file mode 100644
index 000000000000..58397dcb19d6
--- /dev/null
+++ b/tools/include/linux/spinlock.h
@@ -0,0 +1,5 @@
+#define spinlock_t              pthread_mutex_t
+#define DEFINE_SPINLOCK(x)      pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER;
+
+#define spin_lock_irqsave(x, f)         (void)f, pthread_mutex_lock(x)
+#define spin_unlock_irqrestore(x, f)    (void)f, pthread_mutex_unlock(x)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index d2b0ac799d03..0539a0ceef38 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -63,6 +63,12 @@ struct bpf_insn {
         __s32   imm;            /* signed immediate constant */
 };
 
+/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */
+struct bpf_lpm_trie_key {
+        __u32   prefixlen;      /* up to 32 for AF_INET, 128 for AF_INET6 */
+        __u8    data[0];        /* Arbitrary size */
+};
+
 /* BPF syscall commands, see bpf(2) man-page for details. */
 enum bpf_cmd {
         BPF_MAP_CREATE,
@@ -89,6 +95,7 @@ enum bpf_map_type {
         BPF_MAP_TYPE_CGROUP_ARRAY,
         BPF_MAP_TYPE_LRU_HASH,
         BPF_MAP_TYPE_LRU_PERCPU_HASH,
+        BPF_MAP_TYPE_LPM_TRIE,
 };
 
 enum bpf_prog_type {
@@ -437,6 +444,18 @@ union bpf_attr {
  *     @xdp_md: pointer to xdp_md
  *     @delta: An positive/negative integer to be added to xdp_md.data
  *     Return: 0 on success or negative on error
+ *
+ * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr)
+ *     Copy a NUL terminated string from unsafe address. In case the string
+ *     length is smaller than size, the target is not padded with further NUL
+ *     bytes. In case the string length is larger than size, just count-1
+ *     bytes are copied and the last byte is set to NUL.
+ *     @dst: destination address
+ *     @size: maximum number of bytes to copy, including the trailing NUL
+ *     @unsafe_ptr: unsafe address
+ *     Return:
+ *       > 0 length of the string including the trailing NUL on success
+ *       < 0 error
  */
 #define __BPF_FUNC_MAPPER(FN)           \
         FN(unspec),                     \
@@ -483,7 +502,8 @@ union bpf_attr {
         FN(set_hash_invalid),           \
         FN(get_numa_node_id),           \
         FN(skb_change_head),            \
-        FN(xdp_adjust_head),
+        FN(xdp_adjust_head),            \
+        FN(probe_read_str),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -509,6 +529,7 @@ enum bpf_func_id {
 /* BPF_FUNC_l4_csum_replace flags. */
 #define BPF_F_PSEUDO_HDR                (1ULL << 4)
 #define BPF_F_MARK_MANGLED_0            (1ULL << 5)
+#define BPF_F_MARK_ENFORCE              (1ULL << 6)
 
 /* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */
 #define BPF_F_INGRESS                   (1ULL << 0)
diff --git a/tools/include/uapi/linux/bpf_perf_event.h b/tools/include/uapi/linux/bpf_perf_event.h
new file mode 100644
index 000000000000..067427259820
--- /dev/null
+++ b/tools/include/uapi/linux/bpf_perf_event.h
@@ -0,0 +1,18 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef _UAPI__LINUX_BPF_PERF_EVENT_H__
+#define _UAPI__LINUX_BPF_PERF_EVENT_H__
+
+#include <linux/types.h>
+#include <linux/ptrace.h>
+
+struct bpf_perf_event_data {
+        struct pt_regs regs;
+        __u64 sample_period;
+};
+
+#endif /* _UAPI__LINUX_BPF_PERF_EVENT_H__ */
diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c
index 11c8d9bc762e..5d19fdf80292 100644
--- a/tools/lguest/lguest.c
+++ b/tools/lguest/lguest.c
@@ -1387,7 +1387,7 @@ static bool pci_data_iowrite(u16 port, u32 mask, u32 val)
                 /* Allow writing to any other BAR, or expansion ROM */
                 iowrite(portoff, val, mask, &d->config_words[reg]);
                 return true;
-                /* We let them overide latency timer and cacheline size */
+                /* We let them override latency timer and cacheline size */
         } else if (&d->config_words[reg] == (void *)&d->config.cacheline_size) {
                 /* Only let them change the first two fields. */
                 if (mask == 0xFFFFFFFF)
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index e2efddf10231..1f5300e56b44 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -132,7 +132,7 @@ else
   Q = @
 endif
 
-# Disable command line variables (CFLAGS) overide from top
+# Disable command line variables (CFLAGS) override from top
 # level Makefile (perf), otherwise build Makefile will get
 # the same command line setup.
 MAKEOVERRIDES=
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index ae752fa4eaa7..207c2eeddab0 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -27,7 +27,7 @@
 #include "bpf.h"
 
 /*
- * When building perf, unistd.h is overrided. __NR_bpf is
+ * When building perf, unistd.h is overridden. __NR_bpf is
  * required to be defined explicitly.
  */
 #ifndef __NR_bpf
@@ -42,13 +42,13 @@
 # endif
 #endif
 
-static __u64 ptr_to_u64(void *ptr)
+static inline __u64 ptr_to_u64(const void *ptr)
 {
         return (__u64) (unsigned long) ptr;
 }
 
-static int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
-                   unsigned int size)
+static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
+                          unsigned int size)
 {
         return syscall(__NR_bpf, cmd, attr, size);
 }
@@ -69,8 +69,8 @@ int bpf_create_map(enum bpf_map_type map_type, int key_size,
         return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
 }
 
-int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns,
-                     size_t insns_cnt, char *license,
+int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
+                     size_t insns_cnt, const char *license,
                      __u32 kern_version, char *log_buf, size_t log_buf_sz)
 {
         int fd;
@@ -98,7 +98,7 @@ int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns,
         return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
 }
 
-int bpf_map_update_elem(int fd, void *key, void *value,
+int bpf_map_update_elem(int fd, const void *key, const void *value,
                         __u64 flags)
 {
         union bpf_attr attr;
@@ -112,7 +112,7 @@ int bpf_map_update_elem(int fd, void *key, void *value,
         return sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
 }
 
-int bpf_map_lookup_elem(int fd, void *key, void *value)
+int bpf_map_lookup_elem(int fd, const void *key, void *value)
 {
         union bpf_attr attr;
 
@@ -124,7 +124,7 @@ int bpf_map_lookup_elem(int fd, void *key, void *value)
         return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
 }
 
-int bpf_map_delete_elem(int fd, void *key)
+int bpf_map_delete_elem(int fd, const void *key)
 {
         union bpf_attr attr;
 
@@ -135,7 +135,7 @@ int bpf_map_delete_elem(int fd, void *key)
         return sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
 }
 
-int bpf_map_get_next_key(int fd, void *key, void *next_key)
+int bpf_map_get_next_key(int fd, const void *key, void *next_key)
 {
         union bpf_attr attr;
 
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 44fb7c5f8ae6..09c3dcac0496 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -29,17 +29,17 @@ int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
 
 /* Recommend log buffer size */
 #define BPF_LOG_BUF_SIZE 65536
-int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns,
-                     size_t insns_cnt, char *license,
+int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
+                     size_t insns_cnt, const char *license,
                      __u32 kern_version, char *log_buf,
                      size_t log_buf_sz);
 
-int bpf_map_update_elem(int fd, void *key, void *value,
+int bpf_map_update_elem(int fd, const void *key, const void *value,
                         __u64 flags);
 
-int bpf_map_lookup_elem(int fd, void *key, void *value);
-int bpf_map_delete_elem(int fd, void *key);
-int bpf_map_get_next_key(int fd, void *key, void *next_key);
+int bpf_map_lookup_elem(int fd, const void *key, void *value);
+int bpf_map_delete_elem(int fd, const void *key);
+int bpf_map_get_next_key(int fd, const void *key, void *next_key);
 int bpf_obj_pin(int fd, const char *pathname);
 int bpf_obj_get(const char *pathname);
 int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type,
diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c
index 6d8b8f22cf55..42c15f906aac 100644
--- a/tools/lib/find_bit.c
+++ b/tools/lib/find_bit.c
@@ -34,7 +34,7 @@ static unsigned long _find_next_bit(const unsigned long *addr,
 {
         unsigned long tmp;
 
-        if (!nbits || start >= nbits)
+        if (unlikely(start >= nbits))
                 return nbits;
 
         tmp = addr[start / BITS_PER_LONG] ^ invert;
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 47076b15eebe..9b8555ea3459 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -135,7 +135,7 @@ else
   Q = @
 endif
 
-# Disable command line variables (CFLAGS) overide from top
+# Disable command line variables (CFLAGS) override from top
 # level Makefile (perf), otherwise build Makefile will get
 # the same command line setup.
 MAKEOVERRIDES=
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 14a4f623c1a5..7ce724fc0544 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -831,6 +831,7 @@ static void free_arg(struct print_arg *arg)
                 free_flag_sym(arg->symbol.symbols);
                 break;
         case PRINT_HEX:
+        case PRINT_HEX_STR:
                 free_arg(arg->hex.field);
                 free_arg(arg->hex.size);
                 break;
@@ -2629,10 +2630,11 @@ out_free:
 }
 
 static enum event_type
-process_hex(struct event_format *event, struct print_arg *arg, char **tok)
+process_hex_common(struct event_format *event, struct print_arg *arg,
+                   char **tok, enum print_arg_type type)
 {
         memset(arg, 0, sizeof(*arg));
-        arg->type = PRINT_HEX;
+        arg->type = type;
 
         if (alloc_and_process_delim(event, ",", &arg->hex.field))
                 goto out;
@@ -2651,6 +2653,19 @@ out:
 }
 
 static enum event_type
+process_hex(struct event_format *event, struct print_arg *arg, char **tok)
+{
+        return process_hex_common(event, arg, tok, PRINT_HEX);
+}
+
+static enum event_type
+process_hex_str(struct event_format *event, struct print_arg *arg,
+                char **tok)
+{
+        return process_hex_common(event, arg, tok, PRINT_HEX_STR);
+}
+
+static enum event_type
 process_int_array(struct event_format *event, struct print_arg *arg, char **tok)
 {
         memset(arg, 0, sizeof(*arg));
@@ -3009,6 +3024,10 @@ process_function(struct event_format *event, struct print_arg *arg,
                 free_token(token);
                 return process_hex(event, arg, tok);
         }
+        if (strcmp(token, "__print_hex_str") == 0) {
+                free_token(token);
+                return process_hex_str(event, arg, tok);
+        }
         if (strcmp(token, "__print_array") == 0) {
                 free_token(token);
                 return process_int_array(event, arg, tok);
@@ -3547,6 +3566,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
         case PRINT_SYMBOL:
         case PRINT_INT_ARRAY:
         case PRINT_HEX:
+        case PRINT_HEX_STR:
                 break;
         case PRINT_TYPE:
                 val = eval_num_arg(data, size, event, arg->typecast.item);
@@ -3962,6 +3982,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
                 }
                 break;
         case PRINT_HEX:
+        case PRINT_HEX_STR:
                 if (arg->hex.field->type == PRINT_DYNAMIC_ARRAY) {
                         unsigned long offset;
                         offset = pevent_read_number(pevent,
@@ -3981,7 +4002,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
                 }
                 len = eval_num_arg(data, size, event, arg->hex.size);
                 for (i = 0; i < len; i++) {
-                        if (i)
+                        if (i && arg->type == PRINT_HEX)
                                 trace_seq_putc(s, ' ');
                         trace_seq_printf(s, "%02x", hex[i]);
                 }
@@ -5204,13 +5225,13 @@ int pevent_data_pid(struct pevent *pevent, struct pevent_record *rec)
 }
 
 /**
- * pevent_data_prempt_count - parse the preempt count from the record
+ * pevent_data_preempt_count - parse the preempt count from the record
  * @pevent: a handle to the pevent
  * @rec: the record to parse
  *
  * This returns the preempt count from a record.
  */
-int pevent_data_prempt_count(struct pevent *pevent, struct pevent_record *rec)
+int pevent_data_preempt_count(struct pevent *pevent, struct pevent_record *rec)
 {
         return parse_common_pc(pevent, rec->data);
 }
@@ -5727,6 +5748,13 @@ static void print_args(struct print_arg *args)
                 print_args(args->hex.size);
                 printf(")");
                 break;
+        case PRINT_HEX_STR:
+                printf("__print_hex_str(");
+                print_args(args->hex.field);
+                printf(", ");
+                print_args(args->hex.size);
+                printf(")");
+                break;
         case PRINT_INT_ARRAY:
                 printf("__print_array(");
                 print_args(args->int_array.field);
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 7aae746ec2fe..0c03538df74c 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -140,7 +140,7 @@ struct pevent_plugin_option {
  *   struct pevent_plugin_option PEVENT_PLUGIN_OPTIONS[] = {
  *      {
  *              .name = "option-name",
- *              .plugin_alias = "overide-file-name", (optional)
+ *              .plugin_alias = "override-file-name", (optional)
  *              .description = "description of option to show users",
  *      },
  *      {
@@ -292,6 +292,7 @@ enum print_arg_type {
         PRINT_FUNC,
         PRINT_BITMASK,
         PRINT_DYNAMIC_ARRAY_LEN,
+        PRINT_HEX_STR,
 };
 
 struct print_arg {
@@ -709,7 +710,7 @@ void pevent_data_lat_fmt(struct pevent *pevent,
 int pevent_data_type(struct pevent *pevent, struct pevent_record *rec);
 struct event_format *pevent_data_event_from_type(struct pevent *pevent, int type);
 int pevent_data_pid(struct pevent *pevent, struct pevent_record *rec);
-int pevent_data_prempt_count(struct pevent *pevent, struct pevent_record *rec);
+int pevent_data_preempt_count(struct pevent *pevent, struct pevent_record *rec);
 int pevent_data_flags(struct pevent *pevent, struct pevent_record *rec);
 const char *pevent_data_comm_from_pid(struct pevent *pevent, int pid);
 struct cmdline;
diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h
index f7350fcedc70..a59e061c0b4a 100644
--- a/tools/objtool/arch.h
+++ b/tools/objtool/arch.h
@@ -31,9 +31,8 @@
 #define INSN_CALL_DYNAMIC       8
 #define INSN_RETURN             9
 #define INSN_CONTEXT_SWITCH     10
-#define INSN_BUG                11
-#define INSN_NOP                12
-#define INSN_OTHER              13
+#define INSN_NOP                11
+#define INSN_OTHER              12
 #define INSN_LAST               INSN_OTHER
 
 int arch_decode_instruction(struct elf *elf, struct section *sec,
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 039636ffb6c8..6ac99e3266eb 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -118,9 +118,6 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
                          op2 == 0x35)
                         /* sysenter, sysret */
                         *type = INSN_CONTEXT_SWITCH;
-                else if (op2 == 0x0b || op2 == 0xb9)
-                        /* ud2 */
-                        *type = INSN_BUG;
                 else if (op2 == 0x0d || op2 == 0x1f)
                         /* nopl/nopw */
                         *type = INSN_NOP;
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index e8a1f699058a..066086dd59a8 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -51,7 +51,7 @@ struct instruction {
         unsigned int len, state;
         unsigned char type;
         unsigned long immediate;
-        bool alt_group, visited;
+        bool alt_group, visited, dead_end;
         struct symbol *call_dest;
         struct instruction *jump_dest;
         struct list_head alts;
@@ -330,6 +330,54 @@ static int decode_instructions(struct objtool_file *file)
 }
 
 /*
+ * Find all uses of the unreachable() macro, which are code path dead ends.
+ */
+static int add_dead_ends(struct objtool_file *file)
+{
+        struct section *sec;
+        struct rela *rela;
+        struct instruction *insn;
+        bool found;
+
+        sec = find_section_by_name(file->elf, ".rela.discard.unreachable");
+        if (!sec)
+                return 0;
+
+        list_for_each_entry(rela, &sec->rela_list, list) {
+                if (rela->sym->type != STT_SECTION) {
+                        WARN("unexpected relocation symbol type in %s", sec->name);
+                        return -1;
+                }
+                insn = find_insn(file, rela->sym->sec, rela->addend);
+                if (insn)
+                        insn = list_prev_entry(insn, list);
+                else if (rela->addend == rela->sym->sec->len) {
+                        found = false;
+                        list_for_each_entry_reverse(insn, &file->insn_list, list) {
+                                if (insn->sec == rela->sym->sec) {
+                                        found = true;
+                                        break;
+                                }
+                        }
+
+                        if (!found) {
+                                WARN("can't find unreachable insn at %s+0x%x",
+                                     rela->sym->sec->name, rela->addend);
+                                return -1;
+                        }
+                } else {
+                        WARN("can't find unreachable insn at %s+0x%x",
+                             rela->sym->sec->name, rela->addend);
+                        return -1;
+                }
+
+                insn->dead_end = true;
+        }
+
+        return 0;
+}
+
+/*
  * Warnings shouldn't be reported for ignored functions.
  */
 static void add_ignores(struct objtool_file *file)
@@ -757,11 +805,20 @@ static struct rela *find_switch_table(struct objtool_file *file,
                      insn->jump_dest->offset > orig_insn->offset))
                     break;
 
+                /* look for a relocation which references .rodata */
                 text_rela = find_rela_by_dest_range(insn->sec, insn->offset,
                                                     insn->len);
-                if (text_rela && text_rela->sym == file->rodata->sym)
-                        return find_rela_by_dest(file->rodata,
-                                                 text_rela->addend);
+                if (!text_rela || text_rela->sym != file->rodata->sym)
+                        continue;
+
+                /*
+                 * Make sure the .rodata address isn't associated with a
+                 * symbol.  gcc jump tables are anonymous data.
+                 */
+                if (find_symbol_containing(file->rodata, text_rela->addend))
+                        continue;
+
+                return find_rela_by_dest(file->rodata, text_rela->addend);
         }
 
         return NULL;
@@ -843,6 +900,10 @@ static int decode_sections(struct objtool_file *file)
         if (ret)
                 return ret;
 
+        ret = add_dead_ends(file);
+        if (ret)
+                return ret;
+
         add_ignores(file);
 
         ret = add_jump_destinations(file);
@@ -1037,13 +1098,13 @@ static int validate_branch(struct objtool_file *file,
 
                         return 0;
 
-                case INSN_BUG:
-                        return 0;
-
                 default:
                         break;
                 }
 
+                if (insn->dead_end)
+                        return 0;
+
                 insn = next_insn_same_sec(file, insn);
                 if (!insn) {
                         WARN("%s: unexpected end of section", sec->name);
@@ -1220,7 +1281,7 @@ int cmd_check(int argc, const char **argv)
 
         INIT_LIST_HEAD(&file.insn_list);
         hash_init(file.insn_hash);
-        file.whitelist = find_section_by_name(file.elf, "__func_stack_frame_non_standard");
+        file.whitelist = find_section_by_name(file.elf, ".discard.func_stack_frame_non_standard");
         file.rodata = find_section_by_name(file.elf, ".rodata");
         file.ignore_unreachables = false;
         file.c_file = find_section_by_name(file.elf, ".comment");
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 0d7983ac63ef..d897702ce742 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -85,6 +85,18 @@ struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset)
         return NULL;
 }
 
+struct symbol *find_symbol_containing(struct section *sec, unsigned long offset)
+{
+        struct symbol *sym;
+
+        list_for_each_entry(sym, &sec->symbol_list, list)
+                if (sym->type != STT_SECTION &&
+                    offset >= sym->offset && offset < sym->offset + sym->len)
+                        return sym;
+
+        return NULL;
+}
+
 struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
                                      unsigned int len)
 {
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index aa1ff6596684..731973e1a3f5 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -79,6 +79,7 @@ struct elf {
 struct elf *elf_open(const char *name);
 struct section *find_section_by_name(struct elf *elf, const char *name);
 struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset);
+struct symbol *find_symbol_containing(struct section *sec, unsigned long offset);
 struct rela *find_rela_by_dest(struct section *sec, unsigned long offset);
 struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
                                      unsigned int len);
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 8ffbd272952d..a89273d8e744 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -39,6 +39,10 @@ OPTIONS
 --verbose::
         Be more verbose. (Show symbol address, etc)
 
+-q::
+--quiet::
+        Do not show any message.  (Suppress -v)
+
 -D::
 --dump-raw-trace::
         Dump raw trace in ASCII.
diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt
index 66dbe3dee74b..a79c84ae61aa 100644
--- a/tools/perf/Documentation/perf-diff.txt
+++ b/tools/perf/Documentation/perf-diff.txt
@@ -73,6 +73,10 @@ OPTIONS
         Be verbose, for instance, show the raw counts in addition to the
         diff.
 
+-q::
+--quiet::
+        Do not show any message.  (Suppress -v)
+
 -f::
 --force::
         Don't do ownership validation.
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 27256bc68eda..b16003ec14a7 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -157,7 +157,7 @@ OPTIONS
 
 -a::
 --all-cpus::
-        System-wide collection from all CPUs.
+        System-wide collection from all CPUs (default if no target is specified).
 
 -p::
 --pid=::
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index f2914f03ae7b..c04cc0647c16 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -25,6 +25,10 @@ OPTIONS
 --verbose::
         Be more verbose. (show symbol address, etc)
 
+-q::
+--quiet::
+        Do not show any message.  (Suppress -v)
+
 -n::
 --show-nr-samples::
         Show the number of samples for each symbol
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index d96ccd4844df..aecf2a87e7d6 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -63,7 +63,7 @@ report::
 
 -a::
 --all-cpus::
-        system-wide collection from all CPUs
+        system-wide collection from all CPUs (default if no target is specified)
 
 -c::
 --scale::
diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt
index 8a6479c0eac9..170b0289a7bc 100644
--- a/tools/perf/Documentation/tips.txt
+++ b/tools/perf/Documentation/tips.txt
@@ -22,7 +22,7 @@ If you have debuginfo enabled, try: perf report -s sym,srcline
 For memory address profiling, try: perf mem record / perf mem report
 For tracepoint events, try: perf report -s trace_fields
 To record callchains for each sample: perf record -g
-To record every process run by an user: perf record -u <user>
+To record every process run by a user: perf record -u <user>
 Skip collecing build-id when recording: perf record -B
 To change sampling frequency to 100 Hz: perf record -F 100
 See assembly instructions with percentage: perf annotate <symbol>
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 2b941efadb04..27c9fbca7bd9 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -175,6 +175,10 @@ PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
 PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
 PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
 
+ifeq ($(CC), clang)
+  PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
+endif
+
 FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
 FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
 FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
@@ -601,6 +605,9 @@ else
       PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
       PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
       PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+      ifeq ($(CC), clang)
+        PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
+      endif
       FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
 
       ifneq ($(feature-libpython), 1)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 4da19b6ba94a..79fe31f20a17 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -726,13 +726,13 @@ config-clean:
         $(call QUIET_CLEAN, config)
         $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ $(if $(OUTPUT),OUTPUT=$(OUTPUT)feature/,) clean >/dev/null
 
-clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean
+clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean fixdep-clean
         $(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
         $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
         $(Q)$(RM) $(OUTPUT).config-detected
         $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(OUTPUT)pmu-events/jevents $(OUTPUT)$(LIBJVMTI).so
         $(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \
-                $(OUTPUT)util/intel-pt-decoder/inat-tables.c $(OUTPUT)fixdep \
+                $(OUTPUT)util/intel-pt-decoder/inat-tables.c \
                 $(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \
                 $(OUTPUT)pmu-events/pmu-events.c
         $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index ebb628332a6e..4f52d85f5ebc 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -410,6 +410,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
         OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
         OPT_INCR('v', "verbose", &verbose,
                     "be more verbose (show symbol address, etc)"),
+        OPT_BOOLEAN('q', "quiet", &quiet, "do now show any message"),
         OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
                     "dump raw trace in ASCII"),
         OPT_BOOLEAN(0, "gtk", &annotate.use_gtk, "Use the GTK interface"),
@@ -463,6 +464,9 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
                 annotate.sym_hist_filter = argv[0];
         }
 
+        if (quiet)
+                perf_quiet_option();
+
         file.path  = input_name;
 
         annotate.session = perf_session__new(&file, false, &annotate.tool);
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 70a289347591..1b96a3122228 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -691,7 +691,7 @@ static void hists__process(struct hists *hists)
         hists__precompute(hists);
         hists__output_resort(hists, NULL);
 
-        hists__fprintf(hists, true, 0, 0, 0, stdout,
+        hists__fprintf(hists, !quiet, 0, 0, 0, stdout,
                        symbol_conf.use_callchain);
 }
 
@@ -739,12 +739,14 @@ static void data_process(void)
                                 hists__link(hists_base, hists);
                 }
 
-                fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n",
-                        perf_evsel__name(evsel_base));
+                if (!quiet) {
+                        fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n",
+                                perf_evsel__name(evsel_base));
+                }
 
                 first = false;
 
-                if (verbose || data__files_cnt > 2)
+                if (verbose > 0 || ((data__files_cnt > 2) && !quiet))
                         data__fprintf();
 
                 /* Don't sort callchain for perf diff */
@@ -807,6 +809,7 @@ static const char * const diff_usage[] = {
 static const struct option options[] = {
         OPT_INCR('v', "verbose", &verbose,
                     "be more verbose (show symbol address, etc)"),
+        OPT_BOOLEAN('q', "quiet", &quiet, "Do not show any message"),
         OPT_BOOLEAN('b', "baseline-only", &show_baseline_only,
                     "Show only items with match in baseline"),
         OPT_CALLBACK('c', "compute", &compute,
@@ -1328,6 +1331,9 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
 
         argc = parse_options(argc, argv, options, diff_usage, 0);
 
+        if (quiet)
+                perf_quiet_option();
+
         if (symbol__init(NULL) < 0)
                 return -1;
 
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index cd7bc4d104e2..6114e07ca613 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -42,8 +42,8 @@ static int parse_record_events(const struct option *opt,
 
                 fprintf(stderr, "%-13s%-*s%s\n",
                         e->tag,
-                        verbose ? 25 : 0,
-                        verbose ? perf_mem_events__name(j) : "",
+                        verbose > 0 ? 25 : 0,
+                        verbose > 0 ? perf_mem_events__name(j) : "",
                         e->supported ? ": available" : "");
         }
         exit(0);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 6cd6776052e7..bc84a375295d 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -432,7 +432,7 @@ static int record__open(struct record *rec)
 try_again:
                 if (perf_evsel__open(pos, pos->cpus, pos->threads) < 0) {
                         if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) {
-                                if (verbose)
+                                if (verbose > 0)
                                         ui__warning("%s\n", msg);
                                 goto try_again;
                         }
@@ -1677,8 +1677,12 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 
         argc = parse_options(argc, argv, record_options, record_usage,
                             PARSE_OPT_STOP_AT_NON_OPTION);
+        if (quiet)
+                perf_quiet_option();
+
+        /* Make system wide (-a) the default target. */
         if (!argc && target__none(&rec->opts.target))
-                usage_with_options(record_usage, record_options);
+                rec->opts.target.system_wide = true;
 
         if (nr_cgroups && !rec->opts.target.system_wide) {
                 usage_with_options_msg(record_usage, record_options,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index dbd7fa028861..0a88670e56f3 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -320,6 +320,9 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
         size_t size = sizeof(buf);
         int socked_id = hists->socket_filter;
 
+        if (quiet)
+                return 0;
+
         if (symbol_conf.filter_relative) {
                 nr_samples = hists->stats.nr_non_filtered_samples;
                 nr_events = hists->stats.total_non_filtered_period;
@@ -372,7 +375,11 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 {
         struct perf_evsel *pos;
 
-        fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n", evlist->stats.total_lost_samples);
+        if (!quiet) {
+                fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n",
+                        evlist->stats.total_lost_samples);
+        }
+
         evlist__for_each_entry(evlist, pos) {
                 struct hists *hists = evsel__hists(pos);
                 const char *evname = perf_evsel__name(pos);
@@ -382,7 +389,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
                         continue;
 
                 hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
-                hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout,
+                hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout,
                                symbol_conf.use_callchain);
                 fprintf(stdout, "\n\n");
         }
@@ -716,6 +723,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
                     "input file name"),
         OPT_INCR('v', "verbose", &verbose,
                     "be more verbose (show symbol address, etc)"),
+        OPT_BOOLEAN('q', "quiet", &quiet, "Do not show any message"),
         OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
                     "dump raw trace in ASCII"),
         OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
@@ -863,6 +871,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
                 report.symbol_filter_str = argv[0];
         }
 
+        if (quiet)
+                perf_quiet_option();
+
         if (symbol_conf.vmlinux_name &&
             access(symbol_conf.vmlinux_name, R_OK)) {
                 pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name);
@@ -983,14 +994,14 @@ repeat:
                 goto error;
         }
 
-        if (report.header || report.header_only) {
+        if ((report.header || report.header_only) && !quiet) {
                 perf_session__fprintf_info(session, stdout,
                                            report.show_full_info);
                 if (report.header_only) {
                         ret = 0;
                         goto error;
                 }
-        } else if (use_browser == 0) {
+        } else if (use_browser == 0 && !quiet) {
                 fputs("# To display the perf.data header info, please use --header/--header-only options.\n#\n",
                       stdout);
         }
@@ -1009,7 +1020,7 @@ repeat:
                  * providing it only in verbose mode not to bloat too
                  * much struct symbol.
                  */
-                if (verbose) {
+                if (verbose > 0) {
                         /*
                          * XXX: Need to provide a less kludgy way to ask for
                          * more space per symbol, the u32 is for the index on
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 270eb2d8ca6b..b94cf0de715a 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -460,7 +460,7 @@ static struct task_desc *register_pid(struct perf_sched *sched,
         BUG_ON(!sched->tasks);
         sched->tasks[task->nr] = task;
 
-        if (verbose)
+        if (verbose > 0)
                 printf("registered task #%ld, PID %ld (%s)\n", sched->nr_tasks, pid, comm);
 
         return task;
@@ -794,7 +794,7 @@ replay_wakeup_event(struct perf_sched *sched,
         const u32 pid    = perf_evsel__intval(evsel, sample, "pid");
         struct task_desc *waker, *wakee;
 
-        if (verbose) {
+        if (verbose > 0) {
                 printf("sched_wakeup event %p\n", evsel);
 
                 printf(" ... pid %d woke up %s/%d\n", sample->tid, comm, pid);
@@ -822,7 +822,7 @@ static int replay_switch_event(struct perf_sched *sched,
         int cpu = sample->cpu;
         s64 delta;
 
-        if (verbose)
+        if (verbose > 0)
                 printf("sched_switch event %p\n", evsel);
 
         if (cpu >= MAX_CPUS || cpu < 0)
@@ -870,7 +870,7 @@ static int replay_fork_event(struct perf_sched *sched,
                 goto out_put;
         }
 
-        if (verbose) {
+        if (verbose > 0) {
                 printf("fork event\n");
                 printf("... parent: %s/%d\n", thread__comm_str(parent), parent->tid);
                 printf("...  child: %s/%d\n", thread__comm_str(child), child->tid);
@@ -1573,7 +1573,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 
         timestamp__scnprintf_usec(timestamp, stimestamp, sizeof(stimestamp));
         color_fprintf(stdout, color, "  %12s secs ", stimestamp);
-        if (new_shortname || (verbose && sched_in->tid)) {
+        if (new_shortname || (verbose > 0 && sched_in->tid)) {
                 const char *pid_color = color;
 
                 if (thread__has_color(sched_in))
@@ -2050,7 +2050,7 @@ static void save_task_callchain(struct perf_sched *sched,
 
         if (thread__resolve_callchain(thread, cursor, evsel, sample,
                                       NULL, NULL, sched->max_stack + 2) != 0) {
-                if (verbose)
+                if (verbose > 0)
                         error("Failed to resolve callchain. Skipping\n");
 
                 return;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f28719178b51..13b54999ad79 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -573,7 +573,7 @@ try_again:
                         if (errno == EINVAL || errno == ENOSYS ||
                             errno == ENOENT || errno == EOPNOTSUPP ||
                             errno == ENXIO) {
-                                if (verbose)
+                                if (verbose > 0)
                                         ui__warning("%s event is not supported by the kernel.\n",
                                                     perf_evsel__name(counter));
                                 counter->supported = false;
@@ -582,7 +582,7 @@ try_again:
                                     !(counter->leader->nr_members > 1))
                                         continue;
                         } else if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
-                                if (verbose)
+                                if (verbose > 0)
                                         ui__warning("%s\n", msg);
                                 goto try_again;
                         }
@@ -1765,7 +1765,7 @@ static inline int perf_env__get_cpu(struct perf_env *env, struct cpu_map *map, i
 
         cpu = map->map[idx];
 
-        if (cpu >= env->nr_cpus_online)
+        if (cpu >= env->nr_cpus_avail)
                 return -1;
 
         return cpu;
@@ -2445,8 +2445,9 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
         } else if (big_num_opt == 0) /* User passed --no-big-num */
                 big_num = false;
 
+        /* Make system wide (-a) the default target. */
         if (!argc && target__none(&target))
-                usage_with_options(stat_usage, stat_options);
+                target.system_wide = true;
 
         if (run_count < 0) {
                 pr_err("Run count must be a positive number\n");
@@ -2538,7 +2539,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 
         status = 0;
         for (run_idx = 0; forever || run_idx < run_count; run_idx++) {
-                if (run_count != 1 && verbose)
+                if (run_count != 1 && verbose > 0)
                         fprintf(output, "[ perf stat: executing run #%d ... ]\n",
                                 run_idx + 1);
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 5a7fd7af3a6d..ab9077915763 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -871,7 +871,7 @@ try_again:
                 if (perf_evsel__open(counter, top->evlist->cpus,
                                      top->evlist->threads) < 0) {
                         if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
-                                if (verbose)
+                                if (verbose > 0)
                                         ui__warning("%s\n", msg);
                                 goto try_again;
                         }
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 40ef9b293d1b..256f1fac6f7e 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1399,7 +1399,7 @@ static struct syscall *trace__syscall_info(struct trace *trace,
         return &trace->syscalls.table[id];
 
 out_cant_read:
-        if (verbose) {
+        if (verbose > 0) {
                 fprintf(trace->output, "Problems reading syscall %d", id);
                 if (id <= trace->syscalls.max && trace->syscalls.table[id].name != NULL)
                         fprintf(trace->output, "(%s)", trace->syscalls.table[id].name);
@@ -1801,10 +1801,10 @@ static void print_location(FILE *f, struct perf_sample *sample,
                            bool print_dso, bool print_sym)
 {
 
-        if ((verbose || print_dso) && al->map)
+        if ((verbose > 0 || print_dso) && al->map)
                 fprintf(f, "%s@", al->map->dso->long_name);
 
-        if ((verbose || print_sym) && al->sym)
+        if ((verbose > 0 || print_sym) && al->sym)
                 fprintf(f, "%s+0x%" PRIx64, al->sym->name,
                         al->addr - al->sym->start);
         else if (al->map)
diff --git a/tools/perf/pmu-events/json.c b/tools/perf/pmu-events/json.c
index f67bbb0aa36e..0544398d6e2d 100644
--- a/tools/perf/pmu-events/json.c
+++ b/tools/perf/pmu-events/json.c
@@ -49,7 +49,7 @@ static char *mapfile(const char *fn, size_t *size)
         int err;
         int fd = open(fn, O_RDONLY);
 
-        if (fd < 0 && verbose && fn) {
+        if (fd < 0 && verbose > 0 && fn) {
                 pr_err("Error opening events file '%s': %s\n", fn,
                                 strerror(errno));
         }
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 28d1605b0338..88dc51f4c27b 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -144,7 +144,7 @@ static int run_dir(const char *d, const char *perf)
         int vcnt = min(verbose, (int) sizeof(v) - 1);
         char cmd[3*PATH_MAX];
 
-        if (verbose)
+        if (verbose > 0)
                 vcnt++;
 
         snprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %.*s",
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 37e326bfd2dc..83c4669cbc5b 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -299,7 +299,7 @@ static int run_test(struct test *test, int subtest)
                 if (!dont_fork) {
                         pr_debug("test child forked, pid %d\n", getpid());
 
-                        if (!verbose) {
+                        if (verbose <= 0) {
                                 int nullfd = open("/dev/null", O_WRONLY);
 
                                 if (nullfd >= 0) {
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index ff5bc6363a79..d1f693041324 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -599,7 +599,7 @@ static int do_test_code_reading(bool try_kcore)
                                 continue;
                         }
 
-                        if (verbose) {
+                        if (verbose > 0) {
                                 char errbuf[512];
                                 perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));
                                 pr_debug("perf_evlist__open() failed!\n%s\n", errbuf);
diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c
index a2b5ff9bf83d..bc5982f42dc3 100644
--- a/tools/perf/tests/fdarray.c
+++ b/tools/perf/tests/fdarray.c
@@ -19,7 +19,7 @@ static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE
 {
         int printed = 0;
 
-        if (!verbose)
+        if (verbose <= 0)
                 return 0;
 
         printed += fprintf(fp, "\n%s: ", prefix);
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index d357dab72e68..482b5365e68d 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -76,7 +76,7 @@ test_llvm__fetch_bpf_obj(void **p_obj_buf,
          * Skip this test if user's .perfconfig doesn't set [llvm] section
          * and clang is not found in $PATH, and this is not perf test -v
          */
-        if (!force && (verbose == 0 &&
+        if (!force && (verbose <= 0 &&
                        !llvm_param.user_set_param &&
                        llvm__search_clang())) {
                 pr_debug("No clang and no verbosive, skip this test\n");
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index aa9276bfe3e9..1dc838014422 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1808,7 +1808,7 @@ static void debug_warn(const char *warn, va_list params)
 {
         char msg[1024];
 
-        if (!verbose)
+        if (verbose <= 0)
                 return;
 
         vsnprintf(msg, sizeof(msg), warn, params);
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 541da7a68f91..87893f3ba5f1 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -172,13 +172,13 @@ int test__PERF_RECORD(int subtest __maybe_unused)
 
                                 err = perf_evlist__parse_sample(evlist, event, &sample);
                                 if (err < 0) {
-                                        if (verbose)
+                                        if (verbose > 0)
                                                 perf_event__fprintf(event, stderr);
                                         pr_debug("Couldn't parse sample\n");
                                         goto out_delete_evlist;
                                 }
 
-                                if (verbose) {
+                                if (verbose > 0) {
                                         pr_info("%" PRIu64" %d ", sample.time, sample.cpu);
                                         perf_event__fprintf(event, stderr);
                                 }
diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c
index 7a52834ee0d0..fa79509da535 100644
--- a/tools/perf/tests/python-use.c
+++ b/tools/perf/tests/python-use.c
@@ -15,7 +15,7 @@ int test__python_use(int subtest __maybe_unused)
         int ret;
 
         if (asprintf(&cmd, "echo \"import sys ; sys.path.append('%s'); import perf\" | %s %s",
-                     PYTHONPATH, PYTHON, verbose ? "" : "2> /dev/null") < 0)
+                     PYTHONPATH, PYTHON, verbose > 0 ? "" : "2> /dev/null") < 0)
                 return -1;
 
         ret = system(cmd) ? -1 : 0;
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
index a4a4b4625ac3..f2d2e542d0ee 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -109,7 +109,7 @@ int test__thread_map_remove(int subtest __maybe_unused)
         TEST_ASSERT_VAL("failed to allocate thread_map",
                         threads);
 
-        if (verbose)
+        if (verbose > 0)
                 thread_map__fprintf(threads, stderr);
 
         TEST_ASSERT_VAL("failed to remove thread",
@@ -117,7 +117,7 @@ int test__thread_map_remove(int subtest __maybe_unused)
 
         TEST_ASSERT_VAL("thread_map count != 1", threads->nr == 1);
 
-        if (verbose)
+        if (verbose > 0)
                 thread_map__fprintf(threads, stderr);
 
         TEST_ASSERT_VAL("failed to remove thread",
@@ -125,7 +125,7 @@ int test__thread_map_remove(int subtest __maybe_unused)
 
         TEST_ASSERT_VAL("thread_map count != 0", threads->nr == 0);
 
-        if (verbose)
+        if (verbose > 0)
                 thread_map__fprintf(threads, stderr);
 
         TEST_ASSERT_VAL("failed to not remove thread",
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 98fe69ac553c..803f893550d6 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -65,7 +65,9 @@ static int check_cpu_topology(char *path, struct cpu_map *map)
         session = perf_session__new(&file, false, NULL);
         TEST_ASSERT_VAL("can't get session", session);
 
-        for (i = 0; i < session->header.env.nr_cpus_online; i++) {
+        for (i = 0; i < session->header.env.nr_cpus_avail; i++) {
+                if (!cpu_map__has(map, i))
+                        continue;
                 pr_debug("CPU %d, core %d, socket %d\n", i,
                          session->header.env.cpu[i].core_id,
                          session->header.env.cpu[i].socket_id);
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index a5082331f246..862b043e5924 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -168,7 +168,7 @@ next_pair:
                 err = -1;
         }
 
-        if (!verbose)
+        if (verbose <= 0)
                 goto out;
 
         header_printed = false;
diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c
index 98a34664bb7e..9ce142de536d 100644
--- a/tools/perf/ui/browsers/map.c
+++ b/tools/perf/ui/browsers/map.c
@@ -73,7 +73,7 @@ static int map_browser__run(struct map_browser *browser)
 
         if (ui_browser__show(&browser->b, browser->map->dso->long_name,
                              "Press ESC to exit, %s / to search",
-                             verbose ? "" : "restart with -v to use") < 0)
+                             verbose > 0 ? "" : "restart with -v to use") < 0)
                 return -1;
 
         while (1) {
@@ -81,7 +81,7 @@ static int map_browser__run(struct map_browser *browser)
 
                 switch (key) {
                 case '/':
-                        if (verbose)
+                        if (verbose > 0)
                                 map_browser__search(browser);
                 default:
                         break;
@@ -117,7 +117,7 @@ int map__browse(struct map *map)
 
                 if (maxaddr < pos->end)
                         maxaddr = pos->end;
-                if (verbose) {
+                if (verbose > 0) {
                         u32 *idx = symbol__browser_index(pos);
                         *idx = mb.b.nr_entries;
                 }
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 18cfcdc90356..5d632dca672a 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -648,7 +648,7 @@ unsigned int hists__sort_list_width(struct hists *hists)
                 ret += fmt->width(fmt, &dummy_hpp, hists);
         }
 
-        if (verbose && hists__has(hists, sym)) /* Addr + origin */
+        if (verbose > 0 && hists__has(hists, sym)) /* Addr + origin */
                 ret += 3 + BITS_PER_LONG / 4;
 
         return ret;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 06cc04e5806a..273f21fa32b5 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1768,7 +1768,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
         printf("%-*.*s----\n",
                graph_dotted_len, graph_dotted_len, graph_dotted_line);
 
-        if (verbose)
+        if (verbose > 0)
                 symbol__annotate_hits(sym, evsel);
 
         list_for_each_entry(pos, &notes->src->source, node) {
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 8fdee24725a7..eafbf11442b2 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -12,8 +12,8 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen)
 {
         FILE *fp;
         char mountpoint[PATH_MAX + 1], tokens[PATH_MAX + 1], type[PATH_MAX + 1];
+        char path_v1[PATH_MAX + 1], path_v2[PATH_MAX + 2], *path;
         char *token, *saved_ptr = NULL;
-        int found = 0;
 
         fp = fopen("/proc/mounts", "r");
         if (!fp)
@@ -24,31 +24,43 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen)
          * and inspect every cgroupfs mount point to find one that has
          * perf_event subsystem
          */
+        path_v1[0] = '\0';
+        path_v2[0] = '\0';
+
         while (fscanf(fp, "%*s %"STR(PATH_MAX)"s %"STR(PATH_MAX)"s %"
                                 STR(PATH_MAX)"s %*d %*d\n",
                                 mountpoint, type, tokens) == 3) {
 
-                if (!strcmp(type, "cgroup")) {
+                if (!path_v1[0] && !strcmp(type, "cgroup")) {
 
                         token = strtok_r(tokens, ",", &saved_ptr);
 
                         while (token != NULL) {
                                 if (!strcmp(token, "perf_event")) {
-                                        found = 1;
+                                        strcpy(path_v1, mountpoint);
                                         break;
                                 }
                                 token = strtok_r(NULL, ",", &saved_ptr);
                         }
                 }
-                if (found)
+
+                if (!path_v2[0] && !strcmp(type, "cgroup2"))
+                        strcpy(path_v2, mountpoint);
+
+                if (path_v1[0] && path_v2[0])
                         break;
         }
         fclose(fp);
-        if (!found)
+
+        if (path_v1[0])
+                path = path_v1;
+        else if (path_v2[0])
+                path = path_v2;
+        else
                 return -1;
 
-        if (strlen(mountpoint) < maxlen) {
-                strcpy(buf, mountpoint);
+        if (strlen(path) < maxlen) {
+                strcpy(buf, path);
                 return 0;
         }
         return -1;
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 2c0b52264a46..8c7504939113 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -9,6 +9,7 @@
 #include "asm/bug.h"
 
 static int max_cpu_num;
+static int max_present_cpu_num;
 static int max_node_num;
 static int *cpunode_map;
 
@@ -442,6 +443,7 @@ static void set_max_cpu_num(void)
 
         /* set up default */
         max_cpu_num = 4096;
+        max_present_cpu_num = 4096;
 
         mnt = sysfs__mountpoint();
         if (!mnt)
@@ -455,6 +457,17 @@ static void set_max_cpu_num(void)
         }
 
         ret = get_max_num(path, &max_cpu_num);
+        if (ret)
+                goto out;
+
+        /* get the highest present cpu number for a sparse allocation */
+        ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/present", mnt);
+        if (ret == PATH_MAX) {
+                pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
+                goto out;
+        }
+
+        ret = get_max_num(path, &max_present_cpu_num);
 
 out:
         if (ret)
@@ -505,6 +518,15 @@ int cpu__max_cpu(void)
         return max_cpu_num;
 }
 
+int cpu__max_present_cpu(void)
+{
+        if (unlikely(!max_present_cpu_num))
+                set_max_cpu_num();
+
+        return max_present_cpu_num;
+}
+
+
 int cpu__get_node(int cpu)
 {
         if (unlikely(cpunode_map == NULL)) {
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 06bd689f5989..1a0549af8f5c 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -62,6 +62,7 @@ int cpu__setup_cpunode_map(void);
 
 int cpu__max_node(void);
 int cpu__max_cpu(void);
+int cpu__max_present_cpu(void);
 int cpu__get_node(int cpu);
 
 int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index c1838b643108..03eb81f30d0d 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -203,11 +203,28 @@ int perf_debug_option(const char *str)
                 v = (v < 0) || (v > 10) ? 0 : v;
         }
 
+        if (quiet)
+                v = -1;
+
         *var->ptr = v;
         free(s);
         return 0;
 }
 
+int perf_quiet_option(void)
+{
+        struct debug_variable *var = &debug_variables[0];
+
+        /* disable all debug messages */
+        while (var->name) {
+                *var->ptr = -1;
+                var++;
+        }
+
+        quiet = true;
+        return 0;
+}
+
 #define DEBUG_WRAPPER(__n, __l)                         \
 static int pr_ ## __n ## _wrapper(const char *fmt, ...) \
 {                                                       \
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index d242adc3d5a2..98832f5531d3 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -54,5 +54,6 @@ int veprintf(int level, int var, const char *fmt, va_list args);
 
 int perf_debug_option(const char *str);
 void perf_debug_setup(void);
+int perf_quiet_option(void);
 
 #endif  /* __PERF_DEBUG_H */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 28d41e709128..d38b62a700ca 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -951,7 +951,7 @@ static struct dso *__dso__findlink_by_longname(struct rb_root *root,
                 if (rc == 0) {
                         /*
                          * In case the new DSO is a duplicate of an existing
-                         * one, print an one-time warning & put the new entry
+                         * one, print a one-time warning & put the new entry
                          * at the end of the list of duplicates.
                          */
                         if (!dso || (dso == this))
@@ -1058,7 +1058,7 @@ int dso__name_len(const struct dso *dso)
 {
         if (!dso)
                 return strlen("[unknown]");
-        if (verbose)
+        if (verbose > 0)
                 return dso->long_name_len;
 
         return dso->short_name_len;
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index bb964e86b09d..075fc77286bf 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -66,7 +66,7 @@ int perf_env__read_cpu_topology_map(struct perf_env *env)
                 return 0;
 
         if (env->nr_cpus_avail == 0)
-                env->nr_cpus_avail = sysconf(_SC_NPROCESSORS_CONF);
+                env->nr_cpus_avail = cpu__max_present_cpu();
 
         nr_cpus = env->nr_cpus_avail;
         if (nr_cpus == -1)
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 3d12c16e5103..05714d548584 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -295,11 +295,7 @@ static int write_nrcpus(int fd, struct perf_header *h __maybe_unused,
         u32 nrc, nra;
         int ret;
 
-        nr = sysconf(_SC_NPROCESSORS_CONF);
-        if (nr < 0)
-                return -1;
-
-        nrc = (u32)(nr & UINT_MAX);
+        nrc = cpu__max_present_cpu();
 
         nr = sysconf(_SC_NPROCESSORS_ONLN);
         if (nr < 0)
@@ -505,24 +501,29 @@ static void free_cpu_topo(struct cpu_topo *tp)
 
 static struct cpu_topo *build_cpu_topology(void)
 {
-        struct cpu_topo *tp;
+        struct cpu_topo *tp = NULL;
         void *addr;
         u32 nr, i;
         size_t sz;
         long ncpus;
         int ret = -1;
+        struct cpu_map *map;
 
-        ncpus = sysconf(_SC_NPROCESSORS_CONF);
-        if (ncpus < 0)
+        ncpus = cpu__max_present_cpu();
+
+        /* build online CPU map */
+        map = cpu_map__new(NULL);
+        if (map == NULL) {
+                pr_debug("failed to get system cpumap\n");
                 return NULL;
+        }
 
         nr = (u32)(ncpus & UINT_MAX);
 
         sz = nr * sizeof(char *);
-
         addr = calloc(1, sizeof(*tp) + 2 * sz);
         if (!addr)
-                return NULL;
+                goto out_free;
 
         tp = addr;
         tp->cpu_nr = nr;
@@ -532,10 +533,16 @@ static struct cpu_topo *build_cpu_topology(void)
         tp->thread_siblings = addr;
 
         for (i = 0; i < nr; i++) {
+                if (!cpu_map__has(map, i))
+                        continue;
+
                 ret = build_cpu_topo(tp, i);
                 if (ret < 0)
                         break;
         }
+
+out_free:
+        cpu_map__put(map);
         if (ret) {
                 free_cpu_topo(tp);
                 tp = NULL;
@@ -1126,7 +1133,7 @@ static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused,
 {
         int nr, i;
         char *str;
-        int cpu_nr = ph->env.nr_cpus_online;
+        int cpu_nr = ph->env.nr_cpus_avail;
 
         nr = ph->env.nr_sibling_cores;
         str = ph->env.sibling_cores;
@@ -1781,7 +1788,7 @@ static int process_cpu_topology(struct perf_file_section *section,
         u32 nr, i;
         char *str;
         struct strbuf sb;
-        int cpu_nr = ph->env.nr_cpus_online;
+        int cpu_nr = ph->env.nr_cpus_avail;
         u64 size = 0;
 
         ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu));
@@ -1862,7 +1869,7 @@ static int process_cpu_topology(struct perf_file_section *section,
                 if (ph->needs_swap)
                         nr = bswap_32(nr);
 
-                if (nr > (u32)cpu_nr) {
+                if (nr != (u32)-1 && nr > (u32)cpu_nr) {
                         pr_debug("socket_id number is too big."
                                  "You may need to upgrade the perf tool.\n");
                         goto free_cpu;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 32c6a939e4cc..eaf72a938fb4 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -69,7 +69,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
          */
         if (h->ms.sym) {
                 symlen = h->ms.sym->namelen + 4;
-                if (verbose)
+                if (verbose > 0)
                         symlen += BITS_PER_LONG / 4 + 2 + 3;
                 hists__new_col_len(hists, HISTC_SYMBOL, symlen);
         } else {
@@ -93,7 +93,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
         if (h->branch_info) {
                 if (h->branch_info->from.sym) {
                         symlen = (int)h->branch_info->from.sym->namelen + 4;
-                        if (verbose)
+                        if (verbose > 0)
                                 symlen += BITS_PER_LONG / 4 + 2 + 3;
                         hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen);
 
@@ -107,7 +107,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 
                 if (h->branch_info->to.sym) {
                         symlen = (int)h->branch_info->to.sym->namelen + 4;
-                        if (verbose)
+                        if (verbose > 0)
                                 symlen += BITS_PER_LONG / 4 + 2 + 3;
                         hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
 
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
index 7913363bde5c..4f3c758d875d 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
@@ -31,7 +31,7 @@
 #error Instruction buffer size too small
 #endif
 
-/* Based on branch_type() from perf_event_intel_lbr.c */
+/* Based on branch_type() from arch/x86/events/intel/lbr.c */
 static void intel_pt_insn_decoder(struct insn *insn,
                                   struct intel_pt_insn *intel_pt_insn)
 {
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 281e44af31e2..67a8aebc67ab 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -2318,24 +2318,20 @@ int parse_events__is_hardcoded_term(struct parse_events_term *term)
         return term->type_term != PARSE_EVENTS__TERM_TYPE_USER;
 }
 
-static int new_term(struct parse_events_term **_term, int type_val,
-                    int type_term, char *config,
-                    char *str, u64 num, int err_term, int err_val)
+static int new_term(struct parse_events_term **_term,
+                    struct parse_events_term *temp,
+                    char *str, u64 num)
 {
         struct parse_events_term *term;
 
-        term = zalloc(sizeof(*term));
+        term = malloc(sizeof(*term));
         if (!term)
                 return -ENOMEM;
 
+        *term = *temp;
         INIT_LIST_HEAD(&term->list);
-        term->type_val  = type_val;
-        term->type_term = type_term;
-        term->config = config;
-        term->err_term = err_term;
-        term->err_val  = err_val;
 
-        switch (type_val) {
+        switch (term->type_val) {
         case PARSE_EVENTS__TERM_TYPE_NUM:
                 term->val.num = num;
                 break;
@@ -2353,15 +2349,22 @@ static int new_term(struct parse_events_term **_term, int type_val,
 
 int parse_events_term__num(struct parse_events_term **term,
                            int type_term, char *config, u64 num,
+                           bool no_value,
                            void *loc_term_, void *loc_val_)
 {
         YYLTYPE *loc_term = loc_term_;
         YYLTYPE *loc_val = loc_val_;
 
-        return new_term(term, PARSE_EVENTS__TERM_TYPE_NUM, type_term,
-                        config, NULL, num,
-                        loc_term ? loc_term->first_column : 0,
-                        loc_val ? loc_val->first_column : 0);
+        struct parse_events_term temp = {
+                .type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
+                .type_term = type_term,
+                .config    = config,
+                .no_value  = no_value,
+                .err_term  = loc_term ? loc_term->first_column : 0,
+                .err_val   = loc_val  ? loc_val->first_column  : 0,
+        };
+
+        return new_term(term, &temp, NULL, num);
 }
 
 int parse_events_term__str(struct parse_events_term **term,
@@ -2371,37 +2374,45 @@ int parse_events_term__str(struct parse_events_term **term,
         YYLTYPE *loc_term = loc_term_;
         YYLTYPE *loc_val = loc_val_;
 
-        return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, type_term,
-                        config, str, 0,
-                        loc_term ? loc_term->first_column : 0,
-                        loc_val ? loc_val->first_column : 0);
+        struct parse_events_term temp = {
+                .type_val  = PARSE_EVENTS__TERM_TYPE_STR,
+                .type_term = type_term,
+                .config    = config,
+                .err_term  = loc_term ? loc_term->first_column : 0,
+                .err_val   = loc_val  ? loc_val->first_column  : 0,
+        };
+
+        return new_term(term, &temp, str, 0);
 }
 
 int parse_events_term__sym_hw(struct parse_events_term **term,
                               char *config, unsigned idx)
 {
         struct event_symbol *sym;
+        struct parse_events_term temp = {
+                .type_val  = PARSE_EVENTS__TERM_TYPE_STR,
+                .type_term = PARSE_EVENTS__TERM_TYPE_USER,
+                .config    = config ?: (char *) "event",
+        };
 
         BUG_ON(idx >= PERF_COUNT_HW_MAX);
         sym = &event_symbols_hw[idx];
 
-        if (config)
-                return new_term(term, PARSE_EVENTS__TERM_TYPE_STR,
-                                PARSE_EVENTS__TERM_TYPE_USER, config,
-                                (char *) sym->symbol, 0, 0, 0);
-        else
-                return new_term(term, PARSE_EVENTS__TERM_TYPE_STR,
-                                PARSE_EVENTS__TERM_TYPE_USER,
-                                (char *) "event", (char *) sym->symbol,
-                                0, 0, 0);
+        return new_term(term, &temp, (char *) sym->symbol, 0);
 }
 
 int parse_events_term__clone(struct parse_events_term **new,
                              struct parse_events_term *term)
 {
-        return new_term(new, term->type_val, term->type_term, term->config,
-                        term->val.str, term->val.num,
-                        term->err_term, term->err_val);
+        struct parse_events_term temp = {
+                .type_val  = term->type_val,
+                .type_term = term->type_term,
+                .config    = term->config,
+                .err_term  = term->err_term,
+                .err_val   = term->err_val,
+        };
+
+        return new_term(new, &temp, term->val.str, term->val.num);
 }
 
 void parse_events_terms__purge(struct list_head *terms)
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index da246a3ddb69..1af6a267c21b 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -94,6 +94,7 @@ struct parse_events_term {
         int type_term;
         struct list_head list;
         bool used;
+        bool no_value;
 
         /* error string indexes for within parsed string */
         int err_term;
@@ -122,6 +123,7 @@ void parse_events__shrink_config_terms(void);
 int parse_events__is_hardcoded_term(struct parse_events_term *term);
 int parse_events_term__num(struct parse_events_term **term,
                            int type_term, char *config, u64 num,
+                           bool novalue,
                            void *loc_term, void *loc_val);
 int parse_events_term__str(struct parse_events_term **term,
                            int type_term, char *config, char *str,
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index a14b47ab3879..30f018ea1370 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -252,7 +252,7 @@ PE_KERNEL_PMU_EVENT sep_dc
                         if (!strcasecmp(alias->name, $1)) {
                                 ALLOC_LIST(head);
                                 ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-                                        $1, 1, &@1, NULL));
+                                        $1, 1, false, &@1, NULL));
                                 list_add_tail(&term->list, head);
 
                                 if (!parse_events_add_pmu(data, list,
@@ -282,7 +282,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
 
         ALLOC_LIST(head);
         ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-                                        &pmu_name, 1, &@1, NULL));
+                                        &pmu_name, 1, false, &@1, NULL));
         list_add_tail(&term->list, head);
 
         ALLOC_LIST(list);
@@ -548,7 +548,7 @@ PE_NAME '=' PE_VALUE
         struct parse_events_term *term;
 
         ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-                                        $1, $3, &@1, &@3));
+                                        $1, $3, false, &@1, &@3));
         $$ = term;
 }
 |
@@ -566,7 +566,7 @@ PE_NAME
         struct parse_events_term *term;
 
         ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-                                        $1, 1, &@1, NULL));
+                                        $1, 1, true, &@1, NULL));
         $$ = term;
 }
 |
@@ -591,7 +591,7 @@ PE_TERM '=' PE_VALUE
 {
         struct parse_events_term *term;
 
-        ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3, &@1, &@3));
+        ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3, false, &@1, &@3));
         $$ = term;
 }
 |
@@ -599,7 +599,7 @@ PE_TERM
 {
         struct parse_events_term *term;
 
-        ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, &@1, NULL));
+        ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, true, &@1, NULL));
         $$ = term;
 }
 |
@@ -620,7 +620,7 @@ PE_NAME array '=' PE_VALUE
         struct parse_events_term *term;
 
         ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-                                        $1, $4, &@1, &@4));
+                                        $1, $4, false, &@1, &@4));
         term->array = $2;
         $$ = term;
 }
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 49bfee0e3d9e..12f84dd2ac5d 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -745,7 +745,7 @@ static int pmu_resolve_param_term(struct parse_events_term *term,
                 }
         }
 
-        if (verbose)
+        if (verbose > 0)
                 printf("Required parameter '%s' not specified\n", term->config);
 
         return -1;
@@ -803,7 +803,7 @@ static int pmu_config_term(struct list_head *formats,
 
         format = pmu_find_format(formats, term->config);
         if (!format) {
-                if (verbose)
+                if (verbose > 0)
                         printf("Invalid event/parameter '%s'\n", term->config);
                 if (err) {
                         char *pmu_term = pmu_formats_string(formats);
@@ -834,11 +834,20 @@ static int pmu_config_term(struct list_head *formats,
          * Either directly use a numeric term, or try to translate string terms
          * using event parameters.
          */
-        if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
+        if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) {
+                if (term->no_value &&
+                    bitmap_weight(format->bits, PERF_PMU_FORMAT_BITS) > 1) {
+                        if (err) {
+                                err->idx = term->err_val;
+                                err->str = strdup("no value assigned for term");
+                        }
+                        return -EINVAL;
+                }
+
                 val = term->val.num;
-        else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
+        } else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
                 if (strcmp(term->val.str, "?")) {
-                        if (verbose) {
+                        if (verbose > 0) {
                                 pr_info("Invalid sysfs entry %s=%s\n",
                                                 term->config, term->val.str);
                         }
@@ -1223,7 +1232,7 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
                         printf("%*s", 8, "[");
                         wordwrap(aliases[j].desc, 8, columns, 0);
                         printf("]\n");
-                        if (verbose)
+                        if (verbose > 0)
                                 printf("%*s%s/%s/\n", 8, "", aliases[j].pmu, aliases[j].str);
                 } else
                         printf("  %-50s [Kernel PMU event]\n", aliases[j].name);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 35f5b7b7715c..28fb62c32678 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -594,7 +594,7 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
         pr_debug("try to find information at %" PRIx64 " in %s\n", addr,
                  tp->module ? : "kernel");
 
-        dinfo = debuginfo_cache__open(tp->module, verbose == 0);
+        dinfo = debuginfo_cache__open(tp->module, verbose <= 0);
         if (dinfo)
                 ret = debuginfo__find_probe_point(dinfo,
                                                  (unsigned long)addr, pp);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 0d9d6e0803b8..57cd268d4275 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -464,7 +464,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
                 /* Verify it is a data structure  */
                 tag = dwarf_tag(&type);
                 if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) {
-                        pr_warning("%s is not a data structure nor an union.\n",
+                        pr_warning("%s is not a data structure nor a union.\n",
                                    varname);
                         return -EINVAL;
                 }
@@ -479,7 +479,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
         } else {
                 /* Verify it is a data structure  */
                 if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) {
-                        pr_warning("%s is not a data structure nor an union.\n",
+                        pr_warning("%s is not a data structure nor a union.\n",
                                    varname);
                         return -EINVAL;
                 }
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index c1555fd0035a..dff043a29589 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -217,6 +217,7 @@ static void define_event_symbols(struct event_format *event,
                                        cur_field_name);
                 break;
         case PRINT_HEX:
+        case PRINT_HEX_STR:
                 define_event_symbols(event, ev_name, args->hex.field);
                 define_event_symbols(event, ev_name, args->hex.size);
                 break;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 089438da1f7f..783326cfbaa6 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -236,6 +236,7 @@ static void define_event_symbols(struct event_format *event,
                               cur_field_name);
                 break;
         case PRINT_HEX:
+        case PRINT_HEX_STR:
                 define_event_symbols(event, ev_name, args->hex.field);
                 define_event_symbols(event, ev_name, args->hex.size);
                 break;
@@ -368,10 +369,10 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
                 if (node->map) {
                         struct map *map = node->map;
                         const char *dsoname = "[unknown]";
-                        if (map && map->dso && (map->dso->name || map->dso->long_name)) {
+                        if (map && map->dso) {
                                 if (symbol_conf.show_kernel_path && map->dso->long_name)
                                         dsoname = map->dso->long_name;
-                                else if (map->dso->name)
+                                else
                                         dsoname = map->dso->name;
                         }
                         pydict_set_item_string_decref(pyelem, "dso",
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 4cdbc8f5f14d..1dd617d116b5 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -932,7 +932,7 @@ static void branch_stack__printf(struct perf_sample *sample)
 
                 printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n",
                         i, e->from, e->to,
-                        e->flags.cycles,
+                        (unsigned short)e->flags.cycles,
                         e->flags.mispred ? "M" : " ",
                         e->flags.predicted ? "P" : " ",
                         e->flags.abort ? "A" : " ",
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index c8680984d2d6..af415febbc46 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -1,8 +1,15 @@
 #!/usr/bin/python2
 
-from distutils.core import setup, Extension
 from os import getenv
 
+cc = getenv("CC")
+if cc == "clang":
+    from _sysconfigdata import build_time_vars
+    from re import sub
+    build_time_vars["CFLAGS"] = sub("-specs=[^ ]+", "", build_time_vars["CFLAGS"])
+
+from distutils.core import setup, Extension
+
 from distutils.command.build_ext   import build_ext   as _build_ext
 from distutils.command.install_lib import install_lib as _install_lib
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index df622f4e301e..0ff622288d24 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -151,7 +151,7 @@ static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r)
         if (!dso_l || !dso_r)
                 return cmp_null(dso_r, dso_l);
 
-        if (verbose) {
+        if (verbose > 0) {
                 dso_name_l = dso_l->long_name;
                 dso_name_r = dso_r->long_name;
         } else {
@@ -172,8 +172,8 @@ static int _hist_entry__dso_snprintf(struct map *map, char *bf,
                                      size_t size, unsigned int width)
 {
         if (map && map->dso) {
-                const char *dso_name = !verbose ? map->dso->short_name :
-                        map->dso->long_name;
+                const char *dso_name = verbose > 0 ? map->dso->long_name :
+                        map->dso->short_name;
                 return repsep_snprintf(bf, size, "%-*.*s", width, width, dso_name);
         }
 
@@ -261,7 +261,7 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
 {
         size_t ret = 0;
 
-        if (verbose) {
+        if (verbose > 0) {
                 char o = map ? dso__symtab_origin(map->dso) : '!';
                 ret += repsep_snprintf(bf, size, "%-#*llx %c ",
                                        BITS_PER_LONG / 4 + 2, ip, o);
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 7aff317fc7c4..796c847e2f00 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -108,7 +108,7 @@ struct hist_entry {
                 /*
                  * Since perf diff only supports the stdio output, TUI
                  * fields are only accessed from perf report (or perf
-                 * top).  So make it an union to reduce memory usage.
+                 * top).  So make it a union to reduce memory usage.
                  */
                 struct hist_entry_diff  diff;
                 struct /* for TUI */ {
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 39345c2ddfc2..0d51334a9b46 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -344,7 +344,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
         for (i = 0; i < 3; i++)
                 update_stats(&ps->res_stats[i], count[i]);
 
-        if (verbose) {
+        if (verbose > 0) {
                 fprintf(config->output, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
                         perf_evsel__name(counter), count[0], count[1], count[2]);
         }
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index adbc6c02c3aa..4e59ddeb4eda 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -213,7 +213,7 @@ static bool want_demangle(bool is_kernel_sym)
 
 static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name)
 {
-        int demangle_flags = verbose ? (DMGL_PARAMS | DMGL_ANSI) : DMGL_NO_OPTS;
+        int demangle_flags = verbose > 0 ? (DMGL_PARAMS | DMGL_ANSI) : DMGL_NO_OPTS;
         char *demangled = NULL;
 
         /*
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 70e389bc4af7..9b4d8ba22fed 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -202,7 +202,7 @@ void symbols__fixup_end(struct rb_root *symbols)
 
         /* Last entry */
         if (curr->end == curr->start)
-                curr->end = roundup(curr->start, 4096);
+                curr->end = roundup(curr->start, 4096) + 4096;
 }
 
 void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c
index 590d12a25f6e..3e701f0e9c14 100644
--- a/tools/power/cpupower/utils/cpufreq-info.c
+++ b/tools/power/cpupower/utils/cpufreq-info.c
@@ -285,20 +285,24 @@ static int get_freq_hardware(unsigned int cpu, unsigned int human)
 
 /* --hwlimits / -l */
 
-static int get_hardware_limits(unsigned int cpu)
+static int get_hardware_limits(unsigned int cpu, unsigned int human)
 {
         unsigned long min, max;
 
-        printf(_("  hardware limits: "));
         if (cpufreq_get_hardware_limits(cpu, &min, &max)) {
                 printf(_("Not Available\n"));
                 return -EINVAL;
         }
 
-        print_speed(min);
-        printf(" - ");
-        print_speed(max);
-        printf("\n");
+        if (human) {
+                printf(_("  hardware limits: "));
+                print_speed(min);
+                printf(" - ");
+                print_speed(max);
+                printf("\n");
+        } else {
+                printf("%lu %lu\n", min, max);
+        }
         return 0;
 }
 
@@ -456,7 +460,7 @@ static void debug_output_one(unsigned int cpu)
         get_related_cpus(cpu);
         get_affected_cpus(cpu);
         get_latency(cpu, 1);
-        get_hardware_limits(cpu);
+        get_hardware_limits(cpu, 1);
 
         freqs = cpufreq_get_available_frequencies(cpu);
         if (freqs) {
@@ -622,7 +626,7 @@ int cmd_freq_info(int argc, char **argv)
                         ret = get_driver(cpu);
                         break;
                 case 'l':
-                        ret = get_hardware_limits(cpu);
+                        ret = get_hardware_limits(cpu, human);
                         break;
                 case 'w':
                         ret = get_freq_hardware(cpu, human);
@@ -639,7 +643,6 @@ int cmd_freq_info(int argc, char **argv)
                 }
                 if (ret)
                         return ret;
-                printf("\n");
         }
         return ret;
 }
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index 03cb639b292e..fedca3285326 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -16,9 +16,9 @@ idle power-state statistics, temperature and power on X86 processors.
 There are two ways to invoke turbostat.
 The first method is to supply a
 \fBcommand\fP, which is forked and statistics are printed
-upon its completion.
+in one-shot upon its completion.
 The second method is to omit the command,
-and turbostat displays statistics every 5 seconds.
+and turbostat displays statistics every 5 seconds interval.
 The 5-second interval can be changed using the --interval option.
 .PP
 Some information is not available on older processors.
@@ -28,9 +28,10 @@ name as necessary to disambiguate it from others is necessary.  Note that option
 .PP
 \fB--add attributes\fP add column with counter having specified 'attributes'.  The 'location' attribute is required, all others are optional.
 .nf
-        location: {\fBmsrDDD\fP | \fBmsr0xXXX\fP}
+        location: {\fBmsrDDD\fP | \fBmsr0xXXX\fP | \fB/sys/path...\fP}
                 msrDDD is a decimal offset, eg. msr16
                 msr0xXXX is a hex offset, eg. msr0x10
+                /sys/path... is an absolute path to a sysfs attribute
 
         scope: {\fBcpu\fP | \fBcore\fP | \fBpackage\fP}
                 sample and print the counter for every cpu, core, or package.
@@ -45,12 +46,21 @@ name as necessary to disambiguate it from others is necessary.  Note that option
                 'delta' shows the difference in values during the measurement interval.
                 'percent' shows the delta as a percentage of the cycles elapsed.
                 default: delta
+
+        name: "name_string"
+                Any string that does not match a key-word above is used
+                as the column header.
 .fi
 .PP
+\fB--cpu cpu-set\fP limit output to system summary plus the specified cpu-set.  If cpu-set is the string "core", then the system summary plus the first CPU in each core are printed -- eg. subsequent HT siblings are not printed.  Or if cpu-set is the string "package", then the system summary plus the first CPU in each package is printed.  Otherwise, the system summary plus the specified set of CPUs are printed.  The cpu-set is ordered from low to high, comma delimited with ".." and "-" permitted to denote a range. eg. 1,2,8,14..17,21-44
+.PP
+\fB--hide column\fP do not show the specified columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--hide sysfs" to hide the sysfs statistics columns as a group.
+.PP
+\fB--show column\fP show only the specified columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--show sysfs" to show the sysfs statistics columns as a group.
+.PP
 \fB--Dump\fP displays the raw counter values.
 .PP
-\fB--debug\fP displays additional system configuration information.  Invoking this parameter
-more than once may also enable internal turbostat debug information.
+\fB--quiet\fP Do not decode and print the system configuration header information.
 .PP
 \fB--interval seconds\fP overrides the default 5.0 second measurement interval.
 .PP
@@ -61,9 +71,7 @@ The file is truncated if it already exists, and it is created if it does not exi
 .PP
 \fB--Joules\fP displays energy in Joules, rather than dividing Joules by time to print power in Watts.
 .PP
-\fB--Package\fP limits output to the system summary plus the 1st thread in each Package.
-.PP
-\fB--processor\fP limits output to the system summary plus the 1st thread in each processor of each package.  Ie. it skips hyper-threaded siblings.
+\fB--list\fP display column header names available for use by --show and --hide, then exit.
 .PP
 \fB--Summary\fP limits output to a 1-line System Summary for each interval.
 .PP
@@ -74,24 +82,25 @@ The file is truncated if it already exists, and it is created if it does not exi
 The \fBcommand\fP parameter forks \fBcommand\fP, and upon its exit,
 displays the statistics gathered since it was forked.
 .PP
-.SH DEFAULT FIELD DESCRIPTIONS
+.SH ROW DESCRIPTIONS
+The system configuration dump (if --quiet is not used) is followed by statistics.  The first row of the statistics labels the content of each column (below).  The second row of statistics is the system summary line.  The system summary line has a '-' in the columns for the Package, Core, and CPU.  The contents of the system summary line depends on the type of column.  Columns that count items (eg. IRQ) show the sum across all CPUs in the system.  Columns that show a percentage show the average across all CPUs in the system.  Columns that dump raw MSR values simply show 0 in the summary.  After the system summary row, each row describes a specific Package/Core/CPU.  Note that if the --cpu parameter is used to limit which specific CPUs are displayed, turbostat will still collect statistics for all CPUs in the system and will still show the system summary for all CPUs in the system.
+.SH COLUMN DESCRIPTIONS
 .nf
+\fBCore\fP processor core number.  Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology (HT).
 \fBCPU\fP Linux CPU (logical processor) number.  Yes, it is okay that on many systems the CPUs are not listed in numerical order -- for efficiency reasons, turbostat runs in topology order, so HT siblings appear together.
-\fBAVG_MHz\fP number of cycles executed divided by time elapsed.
-\fBBusy%\fP percent of the interval that the CPU retired instructions, aka. % of time in "C0" state.
-\fBBzy_MHz\fP average clock rate while the CPU was busy (in "c0" state).
+\fBPackage\fP processor package number -- not present on systems with a single processor package.
+\fBAvg_MHz\fP number of cycles executed divided by time elapsed.  Note that this includes idle-time when 0 instructions are executed.
+\fBBusy%\fP percent of the measurement interval that the CPU executes instructions, aka. % of time in "C0" state.
+\fBBzy_MHz\fP average clock rate while the CPU was not idle (ie. in "c0" state).
 \fBTSC_MHz\fP average MHz that the TSC ran during the entire interval.
-.fi
-.PP
-.SH DEBUG FIELD DESCRIPTIONS
-.nf
-\fBPackage\fP processor package number.
-\fBCore\fP processor core number.
-Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology (HT).
-\fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states.
+\fBIRQ\fP The number of interrupts serviced by that CPU during the measurement interval.  The system total line is the sum of interrupts serviced across all CPUs.  turbostat parses /proc/interrupts to generate this summary.
+\fBSMI\fP The number of System Management Interrupts  serviced CPU during the measurement interval.  While this counter is actually per-CPU, SMI are triggered on all processors, so the number should be the same for all CPUs.
+\fBC1, C2, C3...\fP The number times Linux requested the C1, C2, C3 idle state during the measurement interval.  The system summary line shows the sum for all CPUs.  These are C-state names as exported in /sys/devices/system/cpu/cpu*/cpuidle/state*/name.  While their names are generic, their attributes are processor specific. They the system description section of output shows what MWAIT sub-states they are mapped to on each system.
+\fBC1%, C2%, C3%\fP The residency percentage that Linux requested C1, C2, C3....  The system summary is the average of all CPUs in the system.  Note that these are software, reflecting what was requested.  The hardware counters reflect what was actually achieved.
+\fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states.  These numbers are from hardware residency counters.
 \fBCoreTmp\fP Degrees Celsius reported by the per-core Digital Thermal Sensor.
 \fBPkgTtmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
-\fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states.
+\fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states.  These numbers are from hardware residency counters.
 \fBPkgWatt\fP Watts consumed by the whole package.
 \fBCorWatt\fP Watts consumed by the core part of the package.
 \fBGFXWatt\fP Watts consumed by the Graphics part of the package -- available only on client processors.
@@ -99,51 +108,110 @@ Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading T
 \fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package.
 \fBRAM_%\fP percent of the interval that RAPL throttling was active on DRAM.
 .fi
+.SH TOO MUCH INFORMATION EXAMPLE
+By default, turbostat dumps all possible information -- a system configuration header, followed by columns for all counters.
+This is ideal for remote debugging, use the "--out" option to save everything to a text file, and get that file to the expert helping you debug.
 .PP
-.SH PERIODIC EXAMPLE
-Without any parameters, turbostat displays statistics ever 5 seconds.
-Periodic output goes to stdout, by default, unless --out is used to specify an output file.
-The 5-second interval can be changed with th "-i sec" option.
-Or a command may be specified as in "FORK EXAMPLE" below.
+When you are not interested in all that information, and there are several ways to see only what you want.  First the "--quiet" option will skip the configuration information, and turbostat will show only the counter columns.  Second, you can reduce the columns with the "--hide" and "--show" options.  If you use the "--show" option, then turbostat will show only the columns you list.  If you use the "--hide" option, turbostat will show all columns, except the ones you list.
+.PP
+To find out what columns are available for --show and --hide, the "--list" option is available.  For convenience, the special strings "sysfs" can be used to refer to all of the sysfs C-state counters at once:
+.nf
+sudo ./turbostat --show sysfs --quiet sleep 10
+10.003837 sec
+        C1      C1E     C3      C6      C7s     C1%     C1E%    C3%     C6%     C7s%
+        4       21      2       2       459     0.14    0.82    0.00    0.00    98.93
+        1       17      2       2       130     0.00    0.02    0.00    0.00    99.80
+        0       0       0       0       31      0.00    0.00    0.00    0.00    99.95
+        2       1       0       0       52      1.14    6.49    0.00    0.00    92.21
+        1       2       0       0       52      0.00    0.08    0.00    0.00    99.86
+        0       0       0       0       71      0.00    0.00    0.00    0.00    99.89
+        0       0       0       0       25      0.00    0.00    0.00    0.00    99.96
+        0       0       0       0       74      0.00    0.00    0.00    0.00    99.94
+        0       1       0       0       24      0.00    0.00    0.00    0.00    99.84
+.fi
+.PP
+.SH ONE SHOT COMMAND EXAMPLE
+If turbostat is invoked with a command, it will fork that command
+and output the statistics gathered after the command exits.
+In this case, turbostat output goes to stderr, by default.
+Output can instead be saved to a file using the --out option.
+In this example, the "sleep 10" command is forked, and turbostat waits for it to complete before saving all statistics into "ts.out".  Note that "sleep 10" is not part of turbostat, but is simply an example of a command that turbostat can fork.  The "ts.out" file is what you want to edit in a very wide window, paste into a spreadsheet, or attach to a bugzilla entry.
+
 .nf
-[root@hsw]# ./turbostat
-     CPU Avg_MHz   Busy% Bzy_MHz TSC_MHz
-       -     488   12.51    3898    3498
-       0       0    0.01    3885    3498
-       4    3897   99.99    3898    3498
-       1       0    0.00    3861    3498
-       5       0    0.00    3882    3498
-       2       1    0.02    3894    3498
-       6       2    0.06    3898    3498
-       3       0    0.00    3849    3498
-       7       0    0.00    3877    3498
+[root@hsw]# ./turbostat -o ts.out sleep 10
+[root@hsw]#
+.fi
 
+.SH PERIODIC INTERVAL EXAMPLE
+Without a command to fork, turbostat displays statistics ever 5 seconds.
+Periodic output goes to stdout, by default, unless --out is used to specify an output file.
+The 5-second interval can be changed with the "-i sec" option.
+.nf
+sudo ./turbostat --quiet --hide sysfs,IRQ,SMI,CoreTmp,PkgTmp,GFX%rc6,GFXMHz,PkgWatt,CorWatt,GFXWatt
+        Core    CPU     Avg_MHz Busy%   Bzy_MHz TSC_MHz CPU%c1  CPU%c3  CPU%c6  CPU%c7
+        -       -       488     12.52   3900    3498    12.50   0.00    0.00    74.98
+        0       0       5       0.13    3900    3498    99.87   0.00    0.00    0.00
+        0       4       3897    99.99   3900    3498    0.01
+        1       1       0       0.00    3856    3498    0.01    0.00    0.00    99.98
+        1       5       0       0.00    3861    3498    0.01
+        2       2       1       0.02    3889    3498    0.03    0.00    0.00    99.95
+        2       6       0       0.00    3863    3498    0.05
+        3       3       0       0.01    3869    3498    0.02    0.00    0.00    99.97
+        3       7       0       0.00    3878    3498    0.03
+        Core    CPU     Avg_MHz Busy%   Bzy_MHz TSC_MHz CPU%c1  CPU%c3  CPU%c6  CPU%c7
+        -       -       491     12.59   3900    3498    12.42   0.00    0.00    74.99
+        0       0       27      0.69    3900    3498    99.31   0.00    0.00    0.00
+        0       4       3898    99.99   3900    3498    0.01
+        1       1       0       0.00    3883    3498    0.01    0.00    0.00    99.99
+        1       5       0       0.00    3898    3498    0.01
+        2       2       0       0.01    3889    3498    0.02    0.00    0.00    99.98
+        2       6       0       0.00    3889    3498    0.02
+        3       3       0       0.00    3856    3498    0.01    0.00    0.00    99.99
+        3       7       0       0.00    3897    3498    0.01
 .fi
-.SH DEBUG EXAMPLE
-The "--debug" option prints additional system information before measurements:
+This example also shows the use of the --hide option to skip columns that are not wanted.
+Note that cpu4 in this example is 99.99% busy, while the other CPUs are all under 1% busy.
+Notice that cpu4's HT sibling is cpu0, which is under 1% busy, but can get into CPU%c1 only,
+because its cpu4's activity on shared hardware keeps it from entering a deeper C-state.
 
-The first row of statistics is a summary for the entire system.
-For residency % columns, the summary is a weighted average.
-For Temperature columns, the summary is the column maximum.
-For Watts columns, the summary is a system total.
-Subsequent rows show per-CPU statistics.
+.SH SYSTEM CONFIGURATION INFORMATION EXAMPLE
+
+By default, turbostat always dumps system configuration information
+before taking measurements.  In the example above, "--quiet" is used
+to suppress that output.  Here is an example of the configuration information:
 .nf
-turbostat version 4.1 10-Feb, 2015 - Len Brown <lenb@kernel.org>
+turbostat version 2017.02.15 - Len Brown <lenb@kernel.org>
 CPUID(0): GenuineIntel 13 CPUID levels; family:model:stepping 0x6:3c:3 (6:60:3)
-CPUID(6): APERF, DTS, PTM, EPB
+CPUID(1): SSE3 MONITOR - EIST TM2 TSC MSR ACPI-TM TM
+CPUID(6): APERF, TURBO, DTS, PTM, No-HWP, No-HWPnotify, No-HWPwindow, No-HWPepp, No-HWPpkg, EPB
+cpu4: MSR_IA32_MISC_ENABLE: 0x00850089 (TCC EIST No-MWAIT PREFETCH TURBO)
+CPUID(7): No-SGX
+cpu4: MSR_MISC_PWR_MGMT: 0x00400000 (ENable-EIST_Coordination DISable-EPB DISable-OOB)
 RAPL: 3121 sec. Joule Counter Range, at 84 Watts
-cpu0: MSR_NHM_PLATFORM_INFO: 0x80838f3012300
-8 * 100 = 800 MHz max efficiency
-35 * 100 = 3500 MHz TSC frequency
-cpu0: MSR_IA32_POWER_CTL: 0x0004005d (C1E auto-promotion: DISabled)
-cpu0: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x1e000400 (UNdemote-C3, UNdemote-C1, demote-C3, demote-C1, UNlocked: pkg-cstate-limit=0: pc0)
-cpu0: MSR_TURBO_RATIO_LIMIT: 0x25262727
-37 * 100 = 3700 MHz max turbo 4 active cores
-38 * 100 = 3800 MHz max turbo 3 active cores
-39 * 100 = 3900 MHz max turbo 2 active cores
-39 * 100 = 3900 MHz max turbo 1 active cores
+cpu4: MSR_PLATFORM_INFO: 0x80838f3012300
+8 * 100.0 = 800.0 MHz max efficiency frequency
+35 * 100.0 = 3500.0 MHz base frequency
+cpu4: MSR_IA32_POWER_CTL: 0x0004005d (C1E auto-promotion: DISabled)
+cpu4: MSR_TURBO_RATIO_LIMIT: 0x25262727
+37 * 100.0 = 3700.0 MHz max turbo 4 active cores
+38 * 100.0 = 3800.0 MHz max turbo 3 active cores
+39 * 100.0 = 3900.0 MHz max turbo 2 active cores
+39 * 100.0 = 3900.0 MHz max turbo 1 active cores
+cpu4: MSR_CONFIG_TDP_NOMINAL: 0x00000023 (base_ratio=35)
+cpu4: MSR_CONFIG_TDP_LEVEL_1: 0x00000000 ()
+cpu4: MSR_CONFIG_TDP_LEVEL_2: 0x00000000 ()
+cpu4: MSR_CONFIG_TDP_CONTROL: 0x80000000 ( lock=1)
+cpu4: MSR_TURBO_ACTIVATION_RATIO: 0x00000000 (MAX_NON_TURBO_RATIO=0 lock=0)
+cpu4: MSR_PKG_CST_CONFIG_CONTROL: 0x1e000400 (UNdemote-C3, UNdemote-C1, demote-C3, demote-C1, UNlocked: pkg-cstate-limit=0: pc0)
+cpu4: POLL: CPUIDLE CORE POLL IDLE
+cpu4: C1: MWAIT 0x00
+cpu4: C1E: MWAIT 0x01
+cpu4: C3: MWAIT 0x10
+cpu4: C6: MWAIT 0x20
+cpu4: C7s: MWAIT 0x32
+cpu4: MSR_MISC_FEATURE_CONTROL: 0x00000000 (L2-Prefetch L2-Prefetch-pair L1-Prefetch L1-IP-Prefetch)
 cpu0: MSR_IA32_ENERGY_PERF_BIAS: 0x00000006 (balanced)
-cpu0: MSR_CORE_PERF_LIMIT_REASONS, 0x31200000 (Active: ) (Logged: Auto-HWP, Amps, MultiCoreTurbo, Transitions, )
+cpu0: MSR_CORE_PERF_LIMIT_REASONS, 0x31200000 (Active: ) (Logged: Transitions, MultiCoreTurbo, Amps, Auto-HWP, )
 cpu0: MSR_GFX_PERF_LIMIT_REASONS, 0x00000000 (Active: ) (Logged: )
 cpu0: MSR_RING_PERF_LIMIT_REASONS, 0x0d000000 (Active: ) (Logged: Amps, PkgPwrL1, PkgPwrL2, )
 cpu0: MSR_RAPL_POWER_UNIT: 0x000a0e03 (0.125000 Watts, 0.000061 Joules, 0.000977 sec.)
@@ -158,23 +226,14 @@ cpu0: MSR_PP1_POLICY: 0
 cpu0: MSR_PP1_POWER_LIMIT: 0x00000000 (UNlocked)
 cpu0: GFX Limit: DISabled (0.000000 Watts, 0.000977 sec, clamp DISabled)
 cpu0: MSR_IA32_TEMPERATURE_TARGET: 0x00641400 (100 C)
-cpu0: MSR_IA32_PACKAGE_THERM_STATUS: 0x88340800 (48 C)
-cpu0: MSR_IA32_THERM_STATUS: 0x88340000 (48 C +/- 1)
-cpu1: MSR_IA32_THERM_STATUS: 0x88440000 (32 C +/- 1)
-cpu2: MSR_IA32_THERM_STATUS: 0x88450000 (31 C +/- 1)
-cpu3: MSR_IA32_THERM_STATUS: 0x88490000 (27 C +/- 1)
-    Core     CPU Avg_MHz   Busy% Bzy_MHz TSC_MHz     SMI  CPU%c1  CPU%c3  CPU%c6  CPU%c7 CoreTmp  PkgTmp PkgWatt CorWatt GFXWatt
-       -       -     493   12.64    3898    3498       0   12.64    0.00    0.00   74.72      47      47   21.62   13.74    0.00
-       0       0       4    0.11    3894    3498       0   99.89    0.00    0.00    0.00      47      47   21.62   13.74    0.00
-       0       4    3897   99.98    3898    3498       0    0.02
-       1       1       7    0.17    3887    3498       0    0.04    0.00    0.00   99.79      32
-       1       5       0    0.00    3885    3498       0    0.21
-       2       2      29    0.76    3895    3498       0    0.10    0.01    0.01   99.13      32
-       2       6       2    0.06    3896    3498       0    0.80
-       3       3       1    0.02    3832    3498       0    0.03    0.00    0.00   99.95      28
-       3       7       0    0.00    3879    3498       0    0.04
-^C
-
+cpu0: MSR_IA32_PACKAGE_THERM_STATUS: 0x884c0800 (24 C)
+cpu0: MSR_IA32_THERM_STATUS: 0x884c0000 (24 C +/- 1)
+cpu1: MSR_IA32_THERM_STATUS: 0x88510000 (19 C +/- 1)
+cpu2: MSR_IA32_THERM_STATUS: 0x884e0000 (22 C +/- 1)
+cpu3: MSR_IA32_THERM_STATUS: 0x88510000 (19 C +/- 1)
+cpu4: MSR_PKGC3_IRTL: 0x00008842 (valid, 67584 ns)
+cpu4: MSR_PKGC6_IRTL: 0x00008873 (valid, 117760 ns)
+cpu4: MSR_PKGC7_IRTL: 0x00008891 (valid, 148480 ns)
 .fi
 The \fBmax efficiency\fP frequency, a.k.a. Low Frequency Mode, is the frequency
 available at the minimum package voltage.  The \fBTSC frequency\fP is the base
@@ -184,42 +243,22 @@ should be sustainable on all CPUs indefinitely, given nominal power and cooling.
 The remaining rows show what maximum turbo frequency is possible
 depending on the number of idle cores.  Note that not all information is
 available on all processors.
-.PP
-The --debug option adds additional columns to the measurement ouput, including CPU idle power-state residency processor temperature sensor readinds.
-See the field definitions above.
-.SH FORK EXAMPLE
-If turbostat is invoked with a command, it will fork that command
-and output the statistics gathered after the command exits.
-In this case, turbostat output goes to stderr, by default.
-Output can instead be saved to a file using the --out option.
-eg. Here a cycle soaker is run on 1 CPU (see %c0) for a few seconds
-until ^C while the other CPUs are mostly idle:
-
+.SH ADD COUNTER EXAMPLE
+Here we limit turbostat to showing just the CPU number for cpu0 - cpu3.
+We add a counter showing the 32-bit raw value of MSR 0x199 (MSR_IA32_PERF_CTL),
+labeling it with the column header, "PRF_CTRL", and display it only once,
+afte the conclusion of a 0.1 second sleep.
 .nf
-root@hsw: turbostat cat /dev/zero > /dev/null
-^C
-     CPU Avg_MHz   Busy% Bzy_MHz TSC_MHz
-       -     482   12.51    3854    3498
-       0       0    0.01    1960    3498
-       4       0    0.00    2128    3498
-       1       0    0.00    3003    3498
-       5    3854   99.98    3855    3498
-       2       0    0.01    3504    3498
-       6       3    0.08    3884    3498
-       3       0    0.00    2553    3498
-       7       0    0.00    2126    3498
-10.783983 sec
+sudo ./turbostat --quiet --cpu 0-3 --show CPU --add msr0x199,u32,raw,PRF_CTRL sleep .1
+0.101604 sec
+CPU       PRF_CTRL
+-       0x00000000
+0       0x00000c00
+1       0x00000800
+2       0x00000a00
+3       0x00000800
 
 .fi
-Above the cycle soaker drives cpu5 up its 3.9 GHz turbo limit.
-The first row shows the average MHz and Busy% across all the processors in the system.
-
-Note that the Avg_MHz column reflects the total number of cycles executed
-divided by the measurement interval.  If the Busy% column is 100%,
-then the processor was running at that speed the entire interval.
-The Avg_MHz multiplied by the Busy% results in the Bzy_MHz --
-which is the average frequency while the processor was executing --
-not including any non-busy idle time.
 
 .SH NOTES
 
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index f13f61b065c6..828dccd3f01e 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -49,17 +49,14 @@ FILE *outf;
 int *fd_percpu;
 struct timespec interval_ts = {5, 0};
 unsigned int debug;
+unsigned int quiet;
+unsigned int sums_need_wide_columns;
 unsigned int rapl_joules;
 unsigned int summary_only;
+unsigned int list_header_only;
 unsigned int dump_only;
-unsigned int do_nhm_cstates;
 unsigned int do_snb_cstates;
 unsigned int do_knl_cstates;
-unsigned int do_pc2;
-unsigned int do_pc3;
-unsigned int do_pc6;
-unsigned int do_pc7;
-unsigned int do_c8_c9_c10;
 unsigned int do_skl_residency;
 unsigned int do_slm_cstates;
 unsigned int use_c1_residency_msr;
@@ -71,25 +68,19 @@ unsigned int units = 1000000;	/* MHz etc */
 unsigned int genuine_intel;
 unsigned int has_invariant_tsc;
 unsigned int do_nhm_platform_info;
+unsigned int no_MSR_MISC_PWR_MGMT;
 unsigned int aperf_mperf_multiplier = 1;
-int do_irq = 1;
-int do_smi;
 double bclk;
 double base_hz;
 unsigned int has_base_hz;
 double tsc_tweak = 1.0;
-unsigned int show_pkg;
-unsigned int show_core;
-unsigned int show_cpu;
 unsigned int show_pkg_only;
 unsigned int show_core_only;
 char *output_buffer, *outp;
 unsigned int do_rapl;
 unsigned int do_dts;
 unsigned int do_ptm;
-unsigned int do_gfx_rc6_ms;
 unsigned long long  gfx_cur_rc6_ms;
-unsigned int do_gfx_mhz;
 unsigned int gfx_cur_mhz;
 unsigned int tcc_activation_temp;
 unsigned int tcc_activation_temp_override;
@@ -109,6 +100,7 @@ unsigned int has_hwp_notify;		/* IA32_HWP_INTERRUPT */
 unsigned int has_hwp_activity_window;   /* IA32_HWP_REQUEST[bits 41:32] */
 unsigned int has_hwp_epp;               /* IA32_HWP_REQUEST[bits 31:24] */
 unsigned int has_hwp_pkg;               /* IA32_HWP_REQUEST_PKG */
+unsigned int has_misc_feature_control;
 
 #define RAPL_PKG                (1 << 0)
                                         /* 0x610 MSR_PKG_POWER_LIMIT */
@@ -148,34 +140,38 @@ unsigned int has_hwp_pkg;		/* IA32_HWP_REQUEST_PKG */
  * Usually truncated to 7 characters, but also handles 18 columns for raw 64-bit counters
  */
 #define NAME_BYTES 20
+#define PATH_BYTES 128
 
 int backwards_count;
 char *progname;
 
-cpu_set_t *cpu_present_set, *cpu_affinity_set;
-size_t cpu_present_setsize, cpu_affinity_setsize;
+#define CPU_SUBSET_MAXCPUS      1024    /* need to use before probe... */
+cpu_set_t *cpu_present_set, *cpu_affinity_set, *cpu_subset;
+size_t cpu_present_setsize, cpu_affinity_setsize, cpu_subset_size;
+#define MAX_ADDED_COUNTERS 16
 
 struct thread_data {
         unsigned long long tsc;
         unsigned long long aperf;
         unsigned long long mperf;
         unsigned long long c1;
-        unsigned int irq_count;
+        unsigned long long  irq_count;
         unsigned int smi_count;
         unsigned int cpu_id;
         unsigned int flags;
 #define CPU_IS_FIRST_THREAD_IN_CORE     0x2
 #define CPU_IS_FIRST_CORE_IN_PACKAGE    0x4
-        unsigned long long counter[1];
+        unsigned long long counter[MAX_ADDED_COUNTERS];
 } *thread_even, *thread_odd;
 
 struct core_data {
         unsigned long long c3;
         unsigned long long c6;
         unsigned long long c7;
+        unsigned long long mc6_us;      /* duplicate as per-core for now, even though per module */
         unsigned int core_temp_c;
         unsigned int core_id;
-        unsigned long long counter[1];
+        unsigned long long counter[MAX_ADDED_COUNTERS];
 } *core_even, *core_odd;
 
 struct pkg_data {
@@ -200,7 +196,7 @@ struct pkg_data {
         unsigned int rapl_pkg_perf_status;      /* MSR_PKG_PERF_STATUS */
         unsigned int rapl_dram_perf_status;     /* MSR_DRAM_PERF_STATUS */
         unsigned int pkg_temp_c;
-        unsigned long long counter[1];
+        unsigned long long counter[MAX_ADDED_COUNTERS];
 } *package_even, *package_odd;
 
 #define ODD_COUNTERS thread_odd, core_odd, package_odd
@@ -215,22 +211,27 @@ struct pkg_data {
 #define GET_PKG(pkg_base, pkg_no) (pkg_base + pkg_no)
 
 enum counter_scope {SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE};
-enum counter_type {COUNTER_CYCLES, COUNTER_SECONDS};
+enum counter_type {COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC};
 enum counter_format {FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT};
 
 struct msr_counter {
         unsigned int msr_num;
         char name[NAME_BYTES];
+        char path[PATH_BYTES];
         unsigned int width;
         enum counter_type type;
         enum counter_format format;
         struct msr_counter *next;
+        unsigned int flags;
+#define FLAGS_HIDE      (1 << 0)
+#define FLAGS_SHOW      (1 << 1)
+#define SYSFS_PERCPU    (1 << 1)
 };
 
 struct sys_counters {
-        unsigned int thread_counter_bytes;
-        unsigned int core_counter_bytes;
-        unsigned int package_counter_bytes;
+        unsigned int added_thread_counters;
+        unsigned int added_core_counters;
+        unsigned int added_package_counters;
         struct msr_counter *tp;
         struct msr_counter *cp;
         struct msr_counter *pp;
@@ -334,147 +335,333 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
         retval = pread(get_msr_fd(cpu), msr, sizeof(*msr), offset);
 
         if (retval != sizeof *msr)
-                err(-1, "msr %d offset 0x%llx read failed", cpu, (unsigned long long)offset);
+                err(-1, "cpu%d: msr offset 0x%llx read failed", cpu, (unsigned long long)offset);
 
         return 0;
 }
 
 /*
- * Example Format w/ field column widths:
- *
- *  Package    Core     CPU Avg_MHz Bzy_MHz TSC_MHz     IRQ   SMI   Busy% CPU_%c1 CPU_%c3 CPU_%c6 CPU_%c7 ThreadC CoreTmp  CoreCnt PkgTmp  GFXMHz Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt PkgCnt
- * 12345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678
+ * Each string in this array is compared in --show and --hide cmdline.
+ * Thus, strings that are proper sub-sets must follow their more specific peers.
+ */
+struct msr_counter bic[] = {
+        { 0x0, "Package" },
+        { 0x0, "Avg_MHz" },
+        { 0x0, "Bzy_MHz" },
+        { 0x0, "TSC_MHz" },
+        { 0x0, "IRQ" },
+        { 0x0, "SMI", "", 32, 0, FORMAT_DELTA, NULL},
+        { 0x0, "Busy%" },
+        { 0x0, "CPU%c1" },
+        { 0x0, "CPU%c3" },
+        { 0x0, "CPU%c6" },
+        { 0x0, "CPU%c7" },
+        { 0x0, "ThreadC" },
+        { 0x0, "CoreTmp" },
+        { 0x0, "CoreCnt" },
+        { 0x0, "PkgTmp" },
+        { 0x0, "GFX%rc6" },
+        { 0x0, "GFXMHz" },
+        { 0x0, "Pkg%pc2" },
+        { 0x0, "Pkg%pc3" },
+        { 0x0, "Pkg%pc6" },
+        { 0x0, "Pkg%pc7" },
+        { 0x0, "Pkg%pc8" },
+        { 0x0, "Pkg%pc9" },
+        { 0x0, "Pkg%pc10" },
+        { 0x0, "PkgWatt" },
+        { 0x0, "CorWatt" },
+        { 0x0, "GFXWatt" },
+        { 0x0, "PkgCnt" },
+        { 0x0, "RAMWatt" },
+        { 0x0, "PKG_%" },
+        { 0x0, "RAM_%" },
+        { 0x0, "Pkg_J" },
+        { 0x0, "Cor_J" },
+        { 0x0, "GFX_J" },
+        { 0x0, "RAM_J" },
+        { 0x0, "Core" },
+        { 0x0, "CPU" },
+        { 0x0, "Mod%c6" },
+        { 0x0, "sysfs" },
+};
+
+#define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
+#define BIC_Package     (1ULL << 0)
+#define BIC_Avg_MHz     (1ULL << 1)
+#define BIC_Bzy_MHz     (1ULL << 2)
+#define BIC_TSC_MHz     (1ULL << 3)
+#define BIC_IRQ         (1ULL << 4)
+#define BIC_SMI         (1ULL << 5)
+#define BIC_Busy        (1ULL << 6)
+#define BIC_CPU_c1      (1ULL << 7)
+#define BIC_CPU_c3      (1ULL << 8)
+#define BIC_CPU_c6      (1ULL << 9)
+#define BIC_CPU_c7      (1ULL << 10)
+#define BIC_ThreadC     (1ULL << 11)
+#define BIC_CoreTmp     (1ULL << 12)
+#define BIC_CoreCnt     (1ULL << 13)
+#define BIC_PkgTmp      (1ULL << 14)
+#define BIC_GFX_rc6     (1ULL << 15)
+#define BIC_GFXMHz      (1ULL << 16)
+#define BIC_Pkgpc2      (1ULL << 17)
+#define BIC_Pkgpc3      (1ULL << 18)
+#define BIC_Pkgpc6      (1ULL << 19)
+#define BIC_Pkgpc7      (1ULL << 20)
+#define BIC_Pkgpc8      (1ULL << 21)
+#define BIC_Pkgpc9      (1ULL << 22)
+#define BIC_Pkgpc10     (1ULL << 23)
+#define BIC_PkgWatt     (1ULL << 24)
+#define BIC_CorWatt     (1ULL << 25)
+#define BIC_GFXWatt     (1ULL << 26)
+#define BIC_PkgCnt      (1ULL << 27)
+#define BIC_RAMWatt     (1ULL << 28)
+#define BIC_PKG__       (1ULL << 29)
+#define BIC_RAM__       (1ULL << 30)
+#define BIC_Pkg_J       (1ULL << 31)
+#define BIC_Cor_J       (1ULL << 32)
+#define BIC_GFX_J       (1ULL << 33)
+#define BIC_RAM_J       (1ULL << 34)
+#define BIC_Core        (1ULL << 35)
+#define BIC_CPU         (1ULL << 36)
+#define BIC_Mod_c6      (1ULL << 37)
+#define BIC_sysfs       (1ULL << 38)
+
+unsigned long long bic_enabled = 0xFFFFFFFFFFFFFFFFULL;
+unsigned long long bic_present = BIC_sysfs;
+
+#define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME)
+#define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT)
+#define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT)
+
+#define MAX_DEFERRED 16
+char *deferred_skip_names[MAX_DEFERRED];
+int deferred_skip_index;
+
+/*
+ * HIDE_LIST - hide this list of counters, show the rest [default]
+ * SHOW_LIST - show this list of counters, hide the rest
  */
+enum show_hide_mode { SHOW_LIST, HIDE_LIST } global_show_hide_mode = HIDE_LIST;
 
-void print_header(void)
+void help(void)
 {
-        struct msr_counter *mp;
+        fprintf(outf,
+        "Usage: turbostat [OPTIONS][(--interval seconds) | COMMAND ...]\n"
+        "\n"
+        "Turbostat forks the specified COMMAND and prints statistics\n"
+        "when COMMAND completes.\n"
+        "If no COMMAND is specified, turbostat wakes every 5-seconds\n"
+        "to print statistics, until interrupted.\n"
+        "--add          add a counter\n"
+        "               eg. --add msr0x10,u64,cpu,delta,MY_TSC\n"
+        "--cpu  cpu-set limit output to summary plus cpu-set:\n"
+        "               {core | package | j,k,l..m,n-p }\n"
+        "--quiet        skip decoding system configuration header\n"
+        "--interval sec Override default 5-second measurement interval\n"
+        "--help         print this help message\n"
+        "--list         list column headers only\n"
+        "--out file     create or truncate \"file\" for all output\n"
+        "--version      print version information\n"
+        "\n"
+        "For more help, run \"man turbostat\"\n");
+}
 
-        if (show_pkg)
-                outp += sprintf(outp, "\tPackage");
-        if (show_core)
-                outp += sprintf(outp, "\tCore");
-        if (show_cpu)
-                outp += sprintf(outp, "\tCPU");
-        if (has_aperf)
-                outp += sprintf(outp, "\tAvg_MHz");
-        if (has_aperf)
-                outp += sprintf(outp, "\tBusy%%");
-        if (has_aperf)
-                outp += sprintf(outp, "\tBzy_MHz");
-        outp += sprintf(outp, "\tTSC_MHz");
+/*
+ * bic_lookup
+ * for all the strings in comma separate name_list,
+ * set the approprate bit in return value.
+ */
+unsigned long long bic_lookup(char *name_list, enum show_hide_mode mode)
+{
+        int i;
+        unsigned long long retval = 0;
 
-        if (!debug)
-                goto done;
+        while (name_list) {
+                char *comma;
 
-        if (do_irq)
-                outp += sprintf(outp, "\tIRQ");
-        if (do_smi)
-                outp += sprintf(outp, "\tSMI");
-
-        if (do_nhm_cstates)
-                outp += sprintf(outp, "\tCPU%%c1");
-        if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates)
-                outp += sprintf(outp, "\tCPU%%c3");
-        if (do_nhm_cstates)
-                outp += sprintf(outp, "\tCPU%%c6");
-        if (do_snb_cstates)
-                outp += sprintf(outp, "\tCPU%%c7");
+                comma = strchr(name_list, ',');
+
+                if (comma)
+                        *comma = '\0';
+
+                for (i = 0; i < MAX_BIC; ++i) {
+                        if (!strcmp(name_list, bic[i].name)) {
+                                retval |= (1ULL << i);
+                                break;
+                        }
+                }
+                if (i == MAX_BIC) {
+                        if (mode == SHOW_LIST) {
+                                fprintf(stderr, "Invalid counter name: %s\n", name_list);
+                                exit(-1);
+                        }
+                        deferred_skip_names[deferred_skip_index++] = name_list;
+                        if (debug)
+                                fprintf(stderr, "deferred \"%s\"\n", name_list);
+                        if (deferred_skip_index >= MAX_DEFERRED) {
+                                fprintf(stderr, "More than max %d un-recognized --skip options '%s'\n",
+                                        MAX_DEFERRED, name_list);
+                                help();
+                                exit(1);
+                        }
+                }
+
+                name_list = comma;
+                if (name_list)
+                        name_list++;
+
+        }
+        return retval;
+}
+
+
+void print_header(char *delim)
+{
+        struct msr_counter *mp;
+        int printed = 0;
+
+        if (DO_BIC(BIC_Package))
+                outp += sprintf(outp, "%sPackage", (printed++ ? delim : ""));
+        if (DO_BIC(BIC_Core))
+                outp += sprintf(outp, "%sCore", (printed++ ? delim : ""));
+        if (DO_BIC(BIC_CPU))
+                outp += sprintf(outp, "%sCPU", (printed++ ? delim : ""));
+        if (DO_BIC(BIC_Avg_MHz))
+                outp += sprintf(outp, "%sAvg_MHz", (printed++ ? delim : ""));
+        if (DO_BIC(BIC_Busy))
+                outp += sprintf(outp, "%sBusy%%", (printed++ ? delim : ""));
+        if (DO_BIC(BIC_Bzy_MHz))
+                outp += sprintf(outp, "%sBzy_MHz", (printed++ ? delim : ""));
+        if (DO_BIC(BIC_TSC_MHz))
+                outp += sprintf(outp, "%sTSC_MHz", (printed++ ? delim : ""));
+
+        if (DO_BIC(BIC_IRQ)) {
+                if (sums_need_wide_columns)
+                        outp += sprintf(outp, "%s     IRQ", (printed++ ? delim : ""));
+                else
+                        outp += sprintf(outp, "%sIRQ", (printed++ ? delim : ""));
+        }
+
+        if (DO_BIC(BIC_SMI))
+                outp += sprintf(outp, "%sSMI", (printed++ ? delim : ""));
 
         for (mp = sys.tp; mp; mp = mp->next) {
+
                 if (mp->format == FORMAT_RAW) {
                         if (mp->width == 64)
-                                outp += sprintf(outp, "\t%18.18s", mp->name);
+                                outp += sprintf(outp, "%s%18.18s", (printed++ ? delim : ""), mp->name);
                         else
-                                outp += sprintf(outp, "\t%10.10s", mp->name);
+                                outp += sprintf(outp, "%s%10.10s", (printed++ ? delim : ""), mp->name);
                 } else {
-                        outp += sprintf(outp, "\t%-7.7s", mp->name);
+                        if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns)
+                                outp += sprintf(outp, "%s%8s", (printed++ ? delim : ""), mp->name);
+                        else
+                                outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), mp->name);
                 }
         }
 
-        if (do_dts)
-                outp += sprintf(outp, "\tCoreTmp");
+        if (DO_BIC(BIC_CPU_c1))
+                outp += sprintf(outp, "%sCPU%%c1", (printed++ ? delim : ""));
+        if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates)
+                outp += sprintf(outp, "%sCPU%%c3", (printed++ ? delim : ""));
+        if (DO_BIC(BIC_CPU_c6))
+                outp += sprintf(outp, "%sCPU%%c6", (printed++ ? delim : ""));
+        if (DO_BIC(BIC_CPU_c7))
+                outp += sprintf(outp, "%sCPU%%c7", (printed++ ? delim : ""));
+
+        if (DO_BIC(BIC_Mod_c6))
+                outp += sprintf(outp, "%sMod%%c6", (printed++ ? delim : ""));
+
+        if (DO_BIC(BIC_CoreTmp))
+                outp += sprintf(outp, "%sCoreTmp", (printed++ ? delim : ""));
 
         for (mp = sys.cp; mp; mp = mp->next) {
                 if (mp->format == FORMAT_RAW) {
                         if (mp->width == 64)
-                                outp += sprintf(outp, "\t%18.18s", mp->name);
+                                outp += sprintf(outp, "%s%18.18s", delim, mp->name);
                         else
-                                outp += sprintf(outp, "\t%10.10s", mp->name);
+                                outp += sprintf(outp, "%s%10.10s", delim, mp->name);
                 } else {
-                        outp += sprintf(outp, "\t%-7.7s", mp->name);
+                        if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns)
+                                outp += sprintf(outp, "%s%8s", delim, mp->name);
+                        else
+                                outp += sprintf(outp, "%s%s", delim, mp->name);
                 }
         }
 
-        if (do_ptm)
-                outp += sprintf(outp, "\tPkgTmp");
+        if (DO_BIC(BIC_PkgTmp))
+                outp += sprintf(outp, "%sPkgTmp", (printed++ ? delim : ""));
 
-        if (do_gfx_rc6_ms)
-                outp += sprintf(outp, "\tGFX%%rc6");
+        if (DO_BIC(BIC_GFX_rc6))
+                outp += sprintf(outp, "%sGFX%%rc6", (printed++ ? delim : ""));
 
-        if (do_gfx_mhz)
-                outp += sprintf(outp, "\tGFXMHz");
+        if (DO_BIC(BIC_GFXMHz))
+                outp += sprintf(outp, "%sGFXMHz", (printed++ ? delim : ""));
 
         if (do_skl_residency) {
-                outp += sprintf(outp, "\tTotl%%C0");
-                outp += sprintf(outp, "\tAny%%C0");
-                outp += sprintf(outp, "\tGFX%%C0");
-                outp += sprintf(outp, "\tCPUGFX%%");
-        }
-
-        if (do_pc2)
-                outp += sprintf(outp, "\tPkg%%pc2");
-        if (do_pc3)
-                outp += sprintf(outp, "\tPkg%%pc3");
-        if (do_pc6)
-                outp += sprintf(outp, "\tPkg%%pc6");
-        if (do_pc7)
-                outp += sprintf(outp, "\tPkg%%pc7");
-        if (do_c8_c9_c10) {
-                outp += sprintf(outp, "\tPkg%%pc8");
-                outp += sprintf(outp, "\tPkg%%pc9");
-                outp += sprintf(outp, "\tPk%%pc10");
+                outp += sprintf(outp, "%sTotl%%C0", (printed++ ? delim : ""));
+                outp += sprintf(outp, "%sAny%%C0", (printed++ ? delim : ""));
+                outp += sprintf(outp, "%sGFX%%C0", (printed++ ? delim : ""));
+                outp += sprintf(outp, "%sCPUGFX%%", (printed++ ? delim : ""));
         }
 
+        if (DO_BIC(BIC_Pkgpc2))
+                outp += sprintf(outp, "%sPkg%%pc2", (printed++ ? delim : ""));
+        if (DO_BIC(BIC_Pkgpc3))
+                outp += sprintf(outp, "%sPkg%%pc3", (printed++ ? delim : ""));
+        if (DO_BIC(BIC_Pkgpc6))
+                outp += sprintf(outp, "%sPkg%%pc6", (printed++ ? delim : ""));
+        if (DO_BIC(BIC_Pkgpc7))
+                outp += sprintf(outp, "%sPkg%%pc7", (printed++ ? delim : ""));
+        if (DO_BIC(BIC_Pkgpc8))
+                outp += sprintf(outp, "%sPkg%%pc8", (printed++ ? delim : ""));
+        if (DO_BIC(BIC_Pkgpc9))
+                outp += sprintf(outp, "%sPkg%%pc9", (printed++ ? delim : ""));
+        if (DO_BIC(BIC_Pkgpc10))
+                outp += sprintf(outp, "%sPk%%pc10", (printed++ ? delim : ""));
+
         if (do_rapl && !rapl_joules) {
-                if (do_rapl & RAPL_PKG)
-                        outp += sprintf(outp, "\tPkgWatt");
-                if (do_rapl & RAPL_CORES_ENERGY_STATUS)
-                        outp += sprintf(outp, "\tCorWatt");
-                if (do_rapl & RAPL_GFX)
-                        outp += sprintf(outp, "\tGFXWatt");
-                if (do_rapl & RAPL_DRAM)
-                        outp += sprintf(outp, "\tRAMWatt");
-                if (do_rapl & RAPL_PKG_PERF_STATUS)
-                        outp += sprintf(outp, "\tPKG_%%");
-                if (do_rapl & RAPL_DRAM_PERF_STATUS)
-                        outp += sprintf(outp, "\tRAM_%%");
+                if (DO_BIC(BIC_PkgWatt))
+                        outp += sprintf(outp, "%sPkgWatt", (printed++ ? delim : ""));
+                if (DO_BIC(BIC_CorWatt))
+                        outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : ""));
+                if (DO_BIC(BIC_GFXWatt))
+                        outp += sprintf(outp, "%sGFXWatt", (printed++ ? delim : ""));
+                if (DO_BIC(BIC_RAMWatt))
+                        outp += sprintf(outp, "%sRAMWatt", (printed++ ? delim : ""));
+                if (DO_BIC(BIC_PKG__))
+                        outp += sprintf(outp, "%sPKG_%%", (printed++ ? delim : ""));
+                if (DO_BIC(BIC_RAM__))
+                        outp += sprintf(outp, "%sRAM_%%", (printed++ ? delim : ""));
         } else if (do_rapl && rapl_joules) {
-                if (do_rapl & RAPL_PKG)
-                        outp += sprintf(outp, "\tPkg_J");
-                if (do_rapl & RAPL_CORES_ENERGY_STATUS)
-                        outp += sprintf(outp, "\tCor_J");
-                if (do_rapl & RAPL_GFX)
-                        outp += sprintf(outp, "\tGFX_J");
-                if (do_rapl & RAPL_DRAM)
-                        outp += sprintf(outp, "\tRAM_J");
-                if (do_rapl & RAPL_PKG_PERF_STATUS)
-                        outp += sprintf(outp, "\tPKG_%%");
-                if (do_rapl & RAPL_DRAM_PERF_STATUS)
-                        outp += sprintf(outp, "\tRAM_%%");
+                if (DO_BIC(BIC_Pkg_J))
+                        outp += sprintf(outp, "%sPkg_J", (printed++ ? delim : ""));
+                if (DO_BIC(BIC_Cor_J))
+                        outp += sprintf(outp, "%sCor_J", (printed++ ? delim : ""));
+                if (DO_BIC(BIC_GFX_J))
+                        outp += sprintf(outp, "%sGFX_J", (printed++ ? delim : ""));
+                if (DO_BIC(BIC_RAM_J))
+                        outp += sprintf(outp, "%sRAM_J", (printed++ ? delim : ""));
+                if (DO_BIC(BIC_PKG__))
+                        outp += sprintf(outp, "%sPKG_%%", (printed++ ? delim : ""));
+                if (DO_BIC(BIC_RAM__))
+                        outp += sprintf(outp, "%sRAM_%%", (printed++ ? delim : ""));
         }
         for (mp = sys.pp; mp; mp = mp->next) {
                 if (mp->format == FORMAT_RAW) {
                         if (mp->width == 64)
-                                outp += sprintf(outp, "\t%18.18s", mp->name);
+                                outp += sprintf(outp, "%s%18.18s", delim, mp->name);
                         else
-                                outp += sprintf(outp, "\t%10.10s", mp->name);
+                                outp += sprintf(outp, "%s%10.10s", delim, mp->name);
                 } else {
-                        outp += sprintf(outp, "\t%-7.7s", mp->name);
+                        if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns)
+                                outp += sprintf(outp, "%s%8s", delim, mp->name);
+                        else
+                                outp += sprintf(outp, "%s%s", delim, mp->name);
                 }
         }
 
-done:
         outp += sprintf(outp, "\n");
 }
 
@@ -494,10 +681,10 @@ int dump_counters(struct thread_data *t, struct core_data *c,
                 outp += sprintf(outp, "mperf: %016llX\n", t->mperf);
                 outp += sprintf(outp, "c1: %016llX\n", t->c1);
 
-                if (do_irq)
-                        outp += sprintf(outp, "IRQ: %08X\n", t->irq_count);
-                if (do_smi)
-                        outp += sprintf(outp, "SMI: %08X\n", t->smi_count);
+                if (DO_BIC(BIC_IRQ))
+                        outp += sprintf(outp, "IRQ: %lld\n", t->irq_count);
+                if (DO_BIC(BIC_SMI))
+                        outp += sprintf(outp, "SMI: %d\n", t->smi_count);
 
                 for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
                         outp += sprintf(outp, "tADDED [%d] msr0x%x: %08llX\n",
@@ -516,6 +703,7 @@ int dump_counters(struct thread_data *t, struct core_data *c,
                         outp += sprintf(outp, "cADDED [%d] msr0x%x: %08llX\n",
                                 i, mp->msr_num, c->counter[i]);
                 }
+                outp += sprintf(outp, "mc6_us: %016llX\n", c->mc6_us);
         }
 
         if (p) {
@@ -527,11 +715,11 @@ int dump_counters(struct thread_data *t, struct core_data *c,
                 outp += sprintf(outp, "CPU + GFX: %016llX\n", p->pkg_both_core_gfxe_c0);
 
                 outp += sprintf(outp, "pc2: %016llX\n", p->pc2);
-                if (do_pc3)
+                if (DO_BIC(BIC_Pkgpc3))
                         outp += sprintf(outp, "pc3: %016llX\n", p->pc3);
-                if (do_pc6)
+                if (DO_BIC(BIC_Pkgpc6))
                         outp += sprintf(outp, "pc6: %016llX\n", p->pc6);
-                if (do_pc7)
+                if (DO_BIC(BIC_Pkgpc7))
                         outp += sprintf(outp, "pc7: %016llX\n", p->pc7);
                 outp += sprintf(outp, "pc8: %016llX\n", p->pc8);
                 outp += sprintf(outp, "pc9: %016llX\n", p->pc9);
@@ -563,10 +751,12 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 int format_counters(struct thread_data *t, struct core_data *c,
         struct pkg_data *p)
 {
-        double interval_float;
+        double interval_float, tsc;
         char *fmt8;
         int i;
         struct msr_counter *mp;
+        char *delim = "\t";
+        int printed = 0;
 
          /* if showing only 1st thread in core and this isn't one, bail out */
         if (show_core_only && !(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
@@ -576,106 +766,126 @@ int format_counters(struct thread_data *t, struct core_data *c,
         if (show_pkg_only && !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
                 return 0;
 
+        /*if not summary line and --cpu is used */
+        if ((t != &average.threads) &&
+                (cpu_subset && !CPU_ISSET_S(t->cpu_id, cpu_subset_size, cpu_subset)))
+                return 0;
+
         interval_float = tv_delta.tv_sec + tv_delta.tv_usec/1000000.0;
 
+        tsc = t->tsc * tsc_tweak;
+
         /* topo columns, print blanks on 1st (average) line */
         if (t == &average.threads) {
-                if (show_pkg)
-                        outp += sprintf(outp, "\t-");
-                if (show_core)
-                        outp += sprintf(outp, "\t-");
-                if (show_cpu)
-                        outp += sprintf(outp, "\t-");
+                if (DO_BIC(BIC_Package))
+                        outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+                if (DO_BIC(BIC_Core))
+                        outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+                if (DO_BIC(BIC_CPU))
+                        outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
         } else {
-                if (show_pkg) {
+                if (DO_BIC(BIC_Package)) {
                         if (p)
-                                outp += sprintf(outp, "\t%d", p->package_id);
+                                outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->package_id);
                         else
-                                outp += sprintf(outp, "\t-");
+                                outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
                 }
-                if (show_core) {
+                if (DO_BIC(BIC_Core)) {
                         if (c)
-                                outp += sprintf(outp, "\t%d", c->core_id);
+                                outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), c->core_id);
                         else
-                                outp += sprintf(outp, "\t-");
+                                outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
                 }
-                if (show_cpu)
-                        outp += sprintf(outp, "\t%d", t->cpu_id);
+                if (DO_BIC(BIC_CPU))
+                        outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->cpu_id);
         }
 
-        /* Avg_MHz */
-        if (has_aperf)
-                outp += sprintf(outp, "\t%.0f",
+        if (DO_BIC(BIC_Avg_MHz))
+                outp += sprintf(outp, "%s%.0f", (printed++ ? delim : ""),
                         1.0 / units * t->aperf / interval_float);
 
-        /* Busy% */
-        if (has_aperf)
-                outp += sprintf(outp, "\t%.2f", 100.0 * t->mperf/t->tsc/tsc_tweak);
+        if (DO_BIC(BIC_Busy))
+                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * t->mperf/tsc);
 
-        /* Bzy_MHz */
-        if (has_aperf) {
+        if (DO_BIC(BIC_Bzy_MHz)) {
                 if (has_base_hz)
-                        outp += sprintf(outp, "\t%.0f", base_hz / units * t->aperf / t->mperf);
+                        outp += sprintf(outp, "%s%.0f", (printed++ ? delim : ""), base_hz / units * t->aperf / t->mperf);
                 else
-                        outp += sprintf(outp, "\t%.0f",
-                                1.0 * t->tsc / units * t->aperf / t->mperf / interval_float);
+                        outp += sprintf(outp, "%s%.0f", (printed++ ? delim : ""),
+                                tsc / units * t->aperf / t->mperf / interval_float);
         }
 
-        /* TSC_MHz */
-        outp += sprintf(outp, "\t%.0f", 1.0 * t->tsc/units/interval_float);
-
-        if (!debug)
-                goto done;
+        if (DO_BIC(BIC_TSC_MHz))
+                outp += sprintf(outp, "%s%.0f", (printed++ ? delim : ""), 1.0 * t->tsc/units/interval_float);
 
         /* IRQ */
-        if (do_irq)
-                outp += sprintf(outp, "\t%d", t->irq_count);
+        if (DO_BIC(BIC_IRQ)) {
+                if (sums_need_wide_columns)
+                        outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), t->irq_count);
+                else
+                        outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), t->irq_count);
+        }
 
         /* SMI */
-        if (do_smi)
-                outp += sprintf(outp, "\t%d", t->smi_count);
-
-        if (do_nhm_cstates)
-                outp += sprintf(outp, "\t%.2f", 100.0 * t->c1/t->tsc);
-
-        /* print per-core data only for 1st thread in core */
-        if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
-                goto done;
-
-        if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates)
-                outp += sprintf(outp, "\t%.2f", 100.0 * c->c3/t->tsc);
-        if (do_nhm_cstates)
-                outp += sprintf(outp, "\t%.2f", 100.0 * c->c6/t->tsc);
-        if (do_snb_cstates)
-                outp += sprintf(outp, "\t%.2f", 100.0 * c->c7/t->tsc);
+        if (DO_BIC(BIC_SMI))
+                outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->smi_count);
 
+        /* Added counters */
         for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
                 if (mp->format == FORMAT_RAW) {
                         if (mp->width == 32)
-                                outp += sprintf(outp, "\t0x%08lx", (unsigned long) t->counter[i]);
+                                outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), (unsigned int) t->counter[i]);
                         else
-                                outp += sprintf(outp, "\t0x%016llx", t->counter[i]);
+                                outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), t->counter[i]);
                 } else if (mp->format == FORMAT_DELTA) {
-                        outp += sprintf(outp, "\t%8lld", t->counter[i]);
+                        if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns)
+                                outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), t->counter[i]);
+                        else
+                                outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), t->counter[i]);
                 } else if (mp->format == FORMAT_PERCENT) {
-                        outp += sprintf(outp, "\t%.2f", 100.0 * t->counter[i]/t->tsc);
+                        if (mp->type == COUNTER_USEC)
+                                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), t->counter[i]/interval_float/10000);
+                        else
+                                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * t->counter[i]/tsc);
                 }
         }
 
+        /* C1 */
+        if (DO_BIC(BIC_CPU_c1))
+                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * t->c1/tsc);
 
-        if (do_dts)
-                outp += sprintf(outp, "\t%d", c->core_temp_c);
+
+        /* print per-core data only for 1st thread in core */
+        if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
+                goto done;
+
+        if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates)
+                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c3/tsc);
+        if (DO_BIC(BIC_CPU_c6))
+                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c6/tsc);
+        if (DO_BIC(BIC_CPU_c7))
+                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c7/tsc);
+
+        /* Mod%c6 */
+        if (DO_BIC(BIC_Mod_c6))
+                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->mc6_us / tsc);
+
+        if (DO_BIC(BIC_CoreTmp))
+                outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), c->core_temp_c);
 
         for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
                 if (mp->format == FORMAT_RAW) {
                         if (mp->width == 32)
-                                outp += sprintf(outp, "\t0x%08lx", (unsigned long) c->counter[i]);
+                                outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), (unsigned int) c->counter[i]);
                         else
-                                outp += sprintf(outp, "\t0x%016llx", c->counter[i]);
+                                outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), c->counter[i]);
                 } else if (mp->format == FORMAT_DELTA) {
-                        outp += sprintf(outp, "\t%8lld", c->counter[i]);
+                        if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns)
+                                outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), c->counter[i]);
+                        else
+                                outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), c->counter[i]);
                 } else if (mp->format == FORMAT_PERCENT) {
-                        outp += sprintf(outp, "\t%.2f", 100.0 * c->counter[i]/t->tsc);
+                        outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->counter[i]/tsc);
                 }
         }
 
@@ -684,95 +894,89 @@ int format_counters(struct thread_data *t, struct core_data *c,
                 goto done;
 
         /* PkgTmp */
-        if (do_ptm)
-                outp += sprintf(outp, "\t%d", p->pkg_temp_c);
+        if (DO_BIC(BIC_PkgTmp))
+                outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->pkg_temp_c);
 
         /* GFXrc6 */
-        if (do_gfx_rc6_ms) {
+        if (DO_BIC(BIC_GFX_rc6)) {
                 if (p->gfx_rc6_ms == -1) {      /* detect GFX counter reset */
-                        outp += sprintf(outp, "\t**.**");
+                        outp += sprintf(outp, "%s**.**", (printed++ ? delim : ""));
                 } else {
-                        outp += sprintf(outp, "\t%.2f",
+                        outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""),
                                 p->gfx_rc6_ms / 10.0 / interval_float);
                 }
         }
 
         /* GFXMHz */
-        if (do_gfx_mhz)
-                outp += sprintf(outp, "\t%d", p->gfx_mhz);
+        if (DO_BIC(BIC_GFXMHz))
+                outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_mhz);
 
         /* Totl%C0, Any%C0 GFX%C0 CPUGFX% */
         if (do_skl_residency) {
-                outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_wtd_core_c0/t->tsc);
-                outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_any_core_c0/t->tsc);
-                outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_any_gfxe_c0/t->tsc);
-                outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_both_core_gfxe_c0/t->tsc);
-        }
-
-        if (do_pc2)
-                outp += sprintf(outp, "\t%.2f", 100.0 * p->pc2/t->tsc);
-        if (do_pc3)
-                outp += sprintf(outp, "\t%.2f", 100.0 * p->pc3/t->tsc);
-        if (do_pc6)
-                outp += sprintf(outp, "\t%.2f", 100.0 * p->pc6/t->tsc);
-        if (do_pc7)
-                outp += sprintf(outp, "\t%.2f", 100.0 * p->pc7/t->tsc);
-        if (do_c8_c9_c10) {
-                outp += sprintf(outp, "\t%.2f", 100.0 * p->pc8/t->tsc);
-                outp += sprintf(outp, "\t%.2f", 100.0 * p->pc9/t->tsc);
-                outp += sprintf(outp, "\t%.2f", 100.0 * p->pc10/t->tsc);
+                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_wtd_core_c0/tsc);
+                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_any_core_c0/tsc);
+                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_any_gfxe_c0/tsc);
+                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_both_core_gfxe_c0/tsc);
         }
 
+        if (DO_BIC(BIC_Pkgpc2))
+                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc2/tsc);
+        if (DO_BIC(BIC_Pkgpc3))
+                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc3/tsc);
+        if (DO_BIC(BIC_Pkgpc6))
+                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc6/tsc);
+        if (DO_BIC(BIC_Pkgpc7))
+                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc7/tsc);
+        if (DO_BIC(BIC_Pkgpc8))
+                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc8/tsc);
+        if (DO_BIC(BIC_Pkgpc9))
+                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc9/tsc);
+        if (DO_BIC(BIC_Pkgpc10))
+                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc10/tsc);
+
         /*
          * If measurement interval exceeds minimum RAPL Joule Counter range,
          * indicate that results are suspect by printing "**" in fraction place.
          */
         if (interval_float < rapl_joule_counter_range)
-                fmt8 = "\t%.2f";
+                fmt8 = "%s%.2f";
         else
                 fmt8 = "%6.0f**";
 
-        if (do_rapl && !rapl_joules) {
-                if (do_rapl & RAPL_PKG)
-                        outp += sprintf(outp, fmt8, p->energy_pkg * rapl_energy_units / interval_float);
-                if (do_rapl & RAPL_CORES_ENERGY_STATUS)
-                        outp += sprintf(outp, fmt8, p->energy_cores * rapl_energy_units / interval_float);
-                if (do_rapl & RAPL_GFX)
-                        outp += sprintf(outp, fmt8, p->energy_gfx * rapl_energy_units / interval_float);
-                if (do_rapl & RAPL_DRAM)
-                        outp += sprintf(outp, fmt8, p->energy_dram * rapl_dram_energy_units / interval_float);
-                if (do_rapl & RAPL_PKG_PERF_STATUS)
-                        outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
-                if (do_rapl & RAPL_DRAM_PERF_STATUS)
-                        outp += sprintf(outp, fmt8, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
-        } else if (do_rapl && rapl_joules) {
-                if (do_rapl & RAPL_PKG)
-                        outp += sprintf(outp, fmt8,
-                                        p->energy_pkg * rapl_energy_units);
-                if (do_rapl & RAPL_CORES)
-                        outp += sprintf(outp, fmt8,
-                                        p->energy_cores * rapl_energy_units);
-                if (do_rapl & RAPL_GFX)
-                        outp += sprintf(outp, fmt8,
-                                        p->energy_gfx * rapl_energy_units);
-                if (do_rapl & RAPL_DRAM)
-                        outp += sprintf(outp, fmt8,
-                                        p->energy_dram * rapl_dram_energy_units);
-                if (do_rapl & RAPL_PKG_PERF_STATUS)
-                        outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
-                if (do_rapl & RAPL_DRAM_PERF_STATUS)
-                        outp += sprintf(outp, fmt8, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
-        }
+        if (DO_BIC(BIC_PkgWatt))
+                outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float);
+        if (DO_BIC(BIC_CorWatt))
+                outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float);
+        if (DO_BIC(BIC_GFXWatt))
+                outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units / interval_float);
+        if (DO_BIC(BIC_RAMWatt))
+                outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_dram * rapl_dram_energy_units / interval_float);
+        if (DO_BIC(BIC_Pkg_J))
+                outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units);
+        if (DO_BIC(BIC_Cor_J))
+                outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units);
+        if (DO_BIC(BIC_GFX_J))
+                outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units);
+        if (DO_BIC(BIC_RAM_J))
+                outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_dram * rapl_dram_energy_units);
+        if (DO_BIC(BIC_PKG__))
+                outp += sprintf(outp, fmt8, (printed++ ? delim : ""), 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
+        if (DO_BIC(BIC_RAM__))
+                outp += sprintf(outp, fmt8, (printed++ ? delim : ""), 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
+
         for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
                 if (mp->format == FORMAT_RAW) {
                         if (mp->width == 32)
-                                outp += sprintf(outp, "\t0x%08lx", (unsigned long) p->counter[i]);
+                                outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), (unsigned int) p->counter[i]);
                         else
-                                outp += sprintf(outp, "\t0x%016llx", p->counter[i]);
+                                outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), p->counter[i]);
                 } else if (mp->format == FORMAT_DELTA) {
-                        outp += sprintf(outp, "\t%8lld", p->counter[i]);
+                        if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns)
+                                outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), p->counter[i]);
+                        else
+                                outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), p->counter[i]);
                 } else if (mp->format == FORMAT_PERCENT) {
-                        outp += sprintf(outp, "\t%.2f", 100.0 * p->counter[i]/t->tsc);
+                        outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->counter[i]/tsc);
                 }
         }
 
@@ -807,7 +1011,7 @@ void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_
         static int printed;
 
         if (!printed || !summary_only)
-                print_header();
+                print_header("\t");
 
         if (topo.num_cpus > 1)
                 format_counters(&average.threads, &average.cores,
@@ -841,11 +1045,11 @@ delta_package(struct pkg_data *new, struct pkg_data *old)
                 old->pkg_both_core_gfxe_c0 = new->pkg_both_core_gfxe_c0 - old->pkg_both_core_gfxe_c0;
         }
         old->pc2 = new->pc2 - old->pc2;
-        if (do_pc3)
+        if (DO_BIC(BIC_Pkgpc3))
                 old->pc3 = new->pc3 - old->pc3;
-        if (do_pc6)
+        if (DO_BIC(BIC_Pkgpc6))
                 old->pc6 = new->pc6 - old->pc6;
-        if (do_pc7)
+        if (DO_BIC(BIC_Pkgpc7))
                 old->pc7 = new->pc7 - old->pc7;
         old->pc8 = new->pc8 - old->pc8;
         old->pc9 = new->pc9 - old->pc9;
@@ -887,6 +1091,7 @@ delta_core(struct core_data *new, struct core_data *old)
         old->c6 = new->c6 - old->c6;
         old->c7 = new->c7 - old->c7;
         old->core_temp_c = new->core_temp_c;
+        old->mc6_us = new->mc6_us - old->mc6_us;
 
         for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
                 if (mp->format == FORMAT_RAW)
@@ -916,7 +1121,7 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 
         old->c1 = new->c1 - old->c1;
 
-        if (has_aperf) {
+        if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz)) {
                 if ((new->aperf > old->aperf) && (new->mperf > old->mperf)) {
                         old->aperf = new->aperf - old->aperf;
                         old->mperf = new->mperf - old->mperf;
@@ -941,7 +1146,7 @@ delta_thread(struct thread_data *new, struct thread_data *old,
                         old->c1 = 0;
                 else {
                         /* normal case, derive c1 */
-                        old->c1 = old->tsc - old->mperf - core_delta->c3
+                        old->c1 = (old->tsc * tsc_tweak) - old->mperf - core_delta->c3
                                 - core_delta->c6 - core_delta->c7;
                 }
         }
@@ -952,10 +1157,10 @@ delta_thread(struct thread_data *new, struct thread_data *old,
                 old->mperf = 1; /* divide by 0 protection */
         }
 
-        if (do_irq)
+        if (DO_BIC(BIC_IRQ))
                 old->irq_count = new->irq_count - old->irq_count;
 
-        if (do_smi)
+        if (DO_BIC(BIC_SMI))
                 old->smi_count = new->smi_count - old->smi_count;
 
         for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
@@ -1008,6 +1213,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
         c->c3 = 0;
         c->c6 = 0;
         c->c7 = 0;
+        c->mc6_us = 0;
         c->core_temp_c = 0;
 
         p->pkg_wtd_core_c0 = 0;
@@ -1016,11 +1222,11 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
         p->pkg_both_core_gfxe_c0 = 0;
 
         p->pc2 = 0;
-        if (do_pc3)
+        if (DO_BIC(BIC_Pkgpc3))
                 p->pc3 = 0;
-        if (do_pc6)
+        if (DO_BIC(BIC_Pkgpc6))
                 p->pc6 = 0;
-        if (do_pc7)
+        if (DO_BIC(BIC_Pkgpc7))
                 p->pc7 = 0;
         p->pc8 = 0;
         p->pc9 = 0;
@@ -1036,7 +1242,6 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 
         p->gfx_rc6_ms = 0;
         p->gfx_mhz = 0;
-
         for (i = 0, mp = sys.tp; mp; i++, mp = mp->next)
                 t->counter[i] = 0;
 
@@ -1073,6 +1278,7 @@ int sum_counters(struct thread_data *t, struct core_data *c,
         average.cores.c3 += c->c3;
         average.cores.c6 += c->c6;
         average.cores.c7 += c->c7;
+        average.cores.mc6_us += c->mc6_us;
 
         average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c);
 
@@ -1094,11 +1300,11 @@ int sum_counters(struct thread_data *t, struct core_data *c,
         }
 
         average.packages.pc2 += p->pc2;
-        if (do_pc3)
+        if (DO_BIC(BIC_Pkgpc3))
                 average.packages.pc3 += p->pc3;
-        if (do_pc6)
+        if (DO_BIC(BIC_Pkgpc6))
                 average.packages.pc6 += p->pc6;
-        if (do_pc7)
+        if (DO_BIC(BIC_Pkgpc7))
                 average.packages.pc7 += p->pc7;
         average.packages.pc8 += p->pc8;
         average.packages.pc9 += p->pc9;
@@ -1143,9 +1349,13 @@ void compute_average(struct thread_data *t, struct core_data *c,
         average.threads.mperf /= topo.num_cpus;
         average.threads.c1 /= topo.num_cpus;
 
+        if (average.threads.irq_count > 9999999)
+                sums_need_wide_columns = 1;
+
         average.cores.c3 /= topo.num_cores;
         average.cores.c6 /= topo.num_cores;
         average.cores.c7 /= topo.num_cores;
+        average.cores.mc6_us /= topo.num_cores;
 
         if (do_skl_residency) {
                 average.packages.pkg_wtd_core_c0 /= topo.num_packages;
@@ -1155,11 +1365,11 @@ void compute_average(struct thread_data *t, struct core_data *c,
         }
 
         average.packages.pc2 /= topo.num_packages;
-        if (do_pc3)
+        if (DO_BIC(BIC_Pkgpc3))
                 average.packages.pc3 /= topo.num_packages;
-        if (do_pc6)
+        if (DO_BIC(BIC_Pkgpc6))
                 average.packages.pc6 /= topo.num_packages;
-        if (do_pc7)
+        if (DO_BIC(BIC_Pkgpc7))
                 average.packages.pc7 /= topo.num_packages;
 
         average.packages.pc8 /= topo.num_packages;
@@ -1169,16 +1379,29 @@ void compute_average(struct thread_data *t, struct core_data *c,
         for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
                 if (mp->format == FORMAT_RAW)
                         continue;
+                if (mp->type == COUNTER_ITEMS) {
+                        if (average.threads.counter[i] > 9999999)
+                                sums_need_wide_columns = 1;
+                        continue;
+                }
                 average.threads.counter[i] /= topo.num_cpus;
         }
         for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
                 if (mp->format == FORMAT_RAW)
                         continue;
+                if (mp->type == COUNTER_ITEMS) {
+                        if (average.cores.counter[i] > 9999999)
+                                sums_need_wide_columns = 1;
+                }
                 average.cores.counter[i] /= topo.num_cores;
         }
         for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
                 if (mp->format == FORMAT_RAW)
                         continue;
+                if (mp->type == COUNTER_ITEMS) {
+                        if (average.packages.counter[i] > 9999999)
+                                sums_need_wide_columns = 1;
+                }
                 average.packages.counter[i] /= topo.num_packages;
         }
 }
@@ -1193,6 +1416,60 @@ static unsigned long long rdtsc(void)
 }
 
 /*
+ * Open a file, and exit on failure
+ */
+FILE *fopen_or_die(const char *path, const char *mode)
+{
+        FILE *filep = fopen(path, mode);
+
+        if (!filep)
+                err(1, "%s: open failed", path);
+        return filep;
+}
+/*
+ * snapshot_sysfs_counter()
+ *
+ * return snapshot of given counter
+ */
+unsigned long long snapshot_sysfs_counter(char *path)
+{
+        FILE *fp;
+        int retval;
+        unsigned long long counter;
+
+        fp = fopen_or_die(path, "r");
+
+        retval = fscanf(fp, "%lld", &counter);
+        if (retval != 1)
+                err(1, "snapshot_sysfs_counter(%s)", path);
+
+        fclose(fp);
+
+        return counter;
+}
+
+int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp)
+{
+        if (mp->msr_num != 0) {
+                if (get_msr(cpu, mp->msr_num, counterp))
+                        return -1;
+        } else {
+                char path[128];
+
+                if (mp->flags & SYSFS_PERCPU) {
+                        sprintf(path, "/sys/devices/system/cpu/cpu%d/%s",
+                                 cpu, mp->path);
+
+                        *counterp = snapshot_sysfs_counter(path);
+                } else {
+                        *counterp = snapshot_sysfs_counter(mp->path);
+                }
+        }
+
+        return 0;
+}
+
+/*
  * get_counters(...)
  * migrate to cpu
  * acquire and record local counters for that cpu
@@ -1213,7 +1490,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 retry:
         t->tsc = rdtsc();       /* we are running on local CPU of interest */
 
-        if (has_aperf) {
+        if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz)) {
                 unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time;
 
                 /*
@@ -1269,35 +1546,33 @@ retry:
                 t->mperf = t->mperf * aperf_mperf_multiplier;
         }
 
-        if (do_irq)
+        if (DO_BIC(BIC_IRQ))
                 t->irq_count = irqs_per_cpu[cpu];
-        if (do_smi) {
+        if (DO_BIC(BIC_SMI)) {
                 if (get_msr(cpu, MSR_SMI_COUNT, &msr))
                         return -5;
                 t->smi_count = msr & 0xFFFFFFFF;
         }
-
-        if (use_c1_residency_msr) {
+        if (DO_BIC(BIC_CPU_c1) && use_c1_residency_msr) {
                 if (get_msr(cpu, MSR_CORE_C1_RES, &t->c1))
                         return -6;
         }
 
         for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
-                if (get_msr(cpu, mp->msr_num, &t->counter[i]))
+                if (get_mp(cpu, mp, &t->counter[i]))
                         return -10;
         }
 
-
         /* collect core counters only for 1st thread in core */
         if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
                 return 0;
 
-        if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates) {
+        if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates) {
                 if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3))
                         return -6;
         }
 
-        if (do_nhm_cstates && !do_knl_cstates) {
+        if (DO_BIC(BIC_CPU_c6) && !do_knl_cstates) {
                 if (get_msr(cpu, MSR_CORE_C6_RESIDENCY, &c->c6))
                         return -7;
         } else if (do_knl_cstates) {
@@ -1305,18 +1580,22 @@ retry:
                         return -7;
         }
 
-        if (do_snb_cstates)
+        if (DO_BIC(BIC_CPU_c7))
                 if (get_msr(cpu, MSR_CORE_C7_RESIDENCY, &c->c7))
                         return -8;
 
-        if (do_dts) {
+        if (DO_BIC(BIC_Mod_c6))
+                if (get_msr(cpu, MSR_MODULE_C6_RES_MS, &c->mc6_us))
+                        return -8;
+
+        if (DO_BIC(BIC_CoreTmp)) {
                 if (get_msr(cpu, MSR_IA32_THERM_STATUS, &msr))
                         return -9;
                 c->core_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F);
         }
 
         for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
-                if (get_msr(cpu, mp->msr_num, &c->counter[i]))
+                if (get_mp(cpu, mp, &c->counter[i]))
                         return -10;
         }
 
@@ -1334,26 +1613,35 @@ retry:
                 if (get_msr(cpu, MSR_PKG_BOTH_CORE_GFXE_C0_RES, &p->pkg_both_core_gfxe_c0))
                         return -13;
         }
-        if (do_pc3)
+        if (DO_BIC(BIC_Pkgpc3))
                 if (get_msr(cpu, MSR_PKG_C3_RESIDENCY, &p->pc3))
                         return -9;
-        if (do_pc6)
-                if (get_msr(cpu, MSR_PKG_C6_RESIDENCY, &p->pc6))
-                        return -10;
-        if (do_pc2)
+        if (DO_BIC(BIC_Pkgpc6)) {
+                if (do_slm_cstates) {
+                        if (get_msr(cpu, MSR_ATOM_PKG_C6_RESIDENCY, &p->pc6))
+                                return -10;
+                } else {
+                        if (get_msr(cpu, MSR_PKG_C6_RESIDENCY, &p->pc6))
+                                return -10;
+                }
+        }
+
+        if (DO_BIC(BIC_Pkgpc2))
                 if (get_msr(cpu, MSR_PKG_C2_RESIDENCY, &p->pc2))
                         return -11;
-        if (do_pc7)
+        if (DO_BIC(BIC_Pkgpc7))
                 if (get_msr(cpu, MSR_PKG_C7_RESIDENCY, &p->pc7))
                         return -12;
-        if (do_c8_c9_c10) {
+        if (DO_BIC(BIC_Pkgpc8))
                 if (get_msr(cpu, MSR_PKG_C8_RESIDENCY, &p->pc8))
                         return -13;
+        if (DO_BIC(BIC_Pkgpc9))
                 if (get_msr(cpu, MSR_PKG_C9_RESIDENCY, &p->pc9))
                         return -13;
+        if (DO_BIC(BIC_Pkgpc10))
                 if (get_msr(cpu, MSR_PKG_C10_RESIDENCY, &p->pc10))
                         return -13;
-        }
+
         if (do_rapl & RAPL_PKG) {
                 if (get_msr(cpu, MSR_PKG_ENERGY_STATUS, &msr))
                         return -13;
@@ -1384,20 +1672,20 @@ retry:
                         return -16;
                 p->rapl_dram_perf_status = msr & 0xFFFFFFFF;
         }
-        if (do_ptm) {
+        if (DO_BIC(BIC_PkgTmp)) {
                 if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr))
                         return -17;
                 p->pkg_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F);
         }
 
-        if (do_gfx_rc6_ms)
+        if (DO_BIC(BIC_GFX_rc6))
                 p->gfx_rc6_ms = gfx_cur_rc6_ms;
 
-        if (do_gfx_mhz)
+        if (DO_BIC(BIC_GFXMHz))
                 p->gfx_mhz = gfx_cur_mhz;
 
         for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
-                if (get_msr(cpu, mp->msr_num, &p->counter[i]))
+                if (get_mp(cpu, mp, &p->counter[i]))
                         return -10;
         }
 
@@ -1433,8 +1721,8 @@ char *pkg_cstate_limit_strings[] = { "reserved", "unknown", "pc0", "pc1", "pc2",
 int nhm_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__3, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int snb_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCL__7, PCL_7S, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int hsw_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL__3, PCL__6, PCL__7, PCL_7S, PCL__8, PCL__9, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
-int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
-int amt_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
+int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7};
+int amt_pkg_cstate_limits[16] = {PCLUNL, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int bxt_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int skx_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
@@ -1457,11 +1745,11 @@ dump_nhm_platform_info(void)
         fprintf(outf, "cpu%d: MSR_PLATFORM_INFO: 0x%08llx\n", base_cpu, msr);
 
         ratio = (msr >> 40) & 0xFF;
-        fprintf(outf, "%d * %.0f = %.0f MHz max efficiency frequency\n",
+        fprintf(outf, "%d * %.1f = %.1f MHz max efficiency frequency\n",
                 ratio, bclk, ratio * bclk);
 
         ratio = (msr >> 8) & 0xFF;
-        fprintf(outf, "%d * %.0f = %.0f MHz base frequency\n",
+        fprintf(outf, "%d * %.1f = %.1f MHz base frequency\n",
                 ratio, bclk, ratio * bclk);
 
         get_msr(base_cpu, MSR_IA32_POWER_CTL, &msr);
@@ -1483,12 +1771,12 @@ dump_hsw_turbo_ratio_limits(void)
 
         ratio = (msr >> 8) & 0xFF;
         if (ratio)
-                fprintf(outf, "%d * %.0f = %.0f MHz max turbo 18 active cores\n",
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo 18 active cores\n",
                         ratio, bclk, ratio * bclk);
 
         ratio = (msr >> 0) & 0xFF;
         if (ratio)
-                fprintf(outf, "%d * %.0f = %.0f MHz max turbo 17 active cores\n",
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo 17 active cores\n",
                         ratio, bclk, ratio * bclk);
         return;
 }
@@ -1505,99 +1793,175 @@ dump_ivt_turbo_ratio_limits(void)
 
         ratio = (msr >> 56) & 0xFF;
         if (ratio)
-                fprintf(outf, "%d * %.0f = %.0f MHz max turbo 16 active cores\n",
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo 16 active cores\n",
                         ratio, bclk, ratio * bclk);
 
         ratio = (msr >> 48) & 0xFF;
         if (ratio)
-                fprintf(outf, "%d * %.0f = %.0f MHz max turbo 15 active cores\n",
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo 15 active cores\n",
                         ratio, bclk, ratio * bclk);
 
         ratio = (msr >> 40) & 0xFF;
         if (ratio)
-                fprintf(outf, "%d * %.0f = %.0f MHz max turbo 14 active cores\n",
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo 14 active cores\n",
                         ratio, bclk, ratio * bclk);
 
         ratio = (msr >> 32) & 0xFF;
         if (ratio)
-                fprintf(outf, "%d * %.0f = %.0f MHz max turbo 13 active cores\n",
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo 13 active cores\n",
                         ratio, bclk, ratio * bclk);
 
         ratio = (msr >> 24) & 0xFF;
         if (ratio)
-                fprintf(outf, "%d * %.0f = %.0f MHz max turbo 12 active cores\n",
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo 12 active cores\n",
                         ratio, bclk, ratio * bclk);
 
         ratio = (msr >> 16) & 0xFF;
         if (ratio)
-                fprintf(outf, "%d * %.0f = %.0f MHz max turbo 11 active cores\n",
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo 11 active cores\n",
                         ratio, bclk, ratio * bclk);
 
         ratio = (msr >> 8) & 0xFF;
         if (ratio)
-                fprintf(outf, "%d * %.0f = %.0f MHz max turbo 10 active cores\n",
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo 10 active cores\n",
                         ratio, bclk, ratio * bclk);
 
         ratio = (msr >> 0) & 0xFF;
         if (ratio)
-                fprintf(outf, "%d * %.0f = %.0f MHz max turbo 9 active cores\n",
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo 9 active cores\n",
                         ratio, bclk, ratio * bclk);
         return;
 }
+int has_turbo_ratio_group_limits(int family, int model)
+{
+
+        if (!genuine_intel)
+                return 0;
+
+        switch (model) {
+        case INTEL_FAM6_ATOM_GOLDMONT:
+        case INTEL_FAM6_SKYLAKE_X:
+        case INTEL_FAM6_ATOM_DENVERTON:
+                return 1;
+        }
+        return 0;
+}
 
 static void
-dump_nhm_turbo_ratio_limits(void)
+dump_turbo_ratio_limits(int family, int model)
 {
-        unsigned long long msr;
-        unsigned int ratio;
+        unsigned long long msr, core_counts;
+        unsigned int ratio, group_size;
 
         get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT, &msr);
-
         fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT: 0x%08llx\n", base_cpu, msr);
 
+        if (has_turbo_ratio_group_limits(family, model)) {
+                get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT1, &core_counts);
+                fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT1: 0x%08llx\n", base_cpu, core_counts);
+        } else {
+                core_counts = 0x0807060504030201;
+        }
+
         ratio = (msr >> 56) & 0xFF;
+        group_size = (core_counts >> 56) & 0xFF;
         if (ratio)
-                fprintf(outf, "%d * %.0f = %.0f MHz max turbo 8 active cores\n",
-                        ratio, bclk, ratio * bclk);
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n",
+                        ratio, bclk, ratio * bclk, group_size);
 
         ratio = (msr >> 48) & 0xFF;
+        group_size = (core_counts >> 48) & 0xFF;
         if (ratio)
-                fprintf(outf, "%d * %.0f = %.0f MHz max turbo 7 active cores\n",
-                        ratio, bclk, ratio * bclk);
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n",
+                        ratio, bclk, ratio * bclk, group_size);
 
         ratio = (msr >> 40) & 0xFF;
+        group_size = (core_counts >> 40) & 0xFF;
         if (ratio)
-                fprintf(outf, "%d * %.0f = %.0f MHz max turbo 6 active cores\n",
-                        ratio, bclk, ratio * bclk);
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n",
+                        ratio, bclk, ratio * bclk, group_size);
 
         ratio = (msr >> 32) & 0xFF;
+        group_size = (core_counts >> 32) & 0xFF;
         if (ratio)
-                fprintf(outf, "%d * %.0f = %.0f MHz max turbo 5 active cores\n",
-                        ratio, bclk, ratio * bclk);
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n",
+                        ratio, bclk, ratio * bclk, group_size);
 
         ratio = (msr >> 24) & 0xFF;
+        group_size = (core_counts >> 24) & 0xFF;
         if (ratio)
-                fprintf(outf, "%d * %.0f = %.0f MHz max turbo 4 active cores\n",
-                        ratio, bclk, ratio * bclk);
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n",
+                        ratio, bclk, ratio * bclk, group_size);
 
         ratio = (msr >> 16) & 0xFF;
+        group_size = (core_counts >> 16) & 0xFF;
         if (ratio)
-                fprintf(outf, "%d * %.0f = %.0f MHz max turbo 3 active cores\n",
-                        ratio, bclk, ratio * bclk);
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n",
+                        ratio, bclk, ratio * bclk, group_size);
 
         ratio = (msr >> 8) & 0xFF;
+        group_size = (core_counts >> 8) & 0xFF;
         if (ratio)
-                fprintf(outf, "%d * %.0f = %.0f MHz max turbo 2 active cores\n",
-                        ratio, bclk, ratio * bclk);
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n",
+                        ratio, bclk, ratio * bclk, group_size);
 
         ratio = (msr >> 0) & 0xFF;
+        group_size = (core_counts >> 0) & 0xFF;
         if (ratio)
-                fprintf(outf, "%d * %.0f = %.0f MHz max turbo 1 active cores\n",
-                        ratio, bclk, ratio * bclk);
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n",
+                        ratio, bclk, ratio * bclk, group_size);
         return;
 }
 
 static void
+dump_atom_turbo_ratio_limits(void)
+{
+        unsigned long long msr;
+        unsigned int ratio;
+
+        get_msr(base_cpu, MSR_ATOM_CORE_RATIOS, &msr);
+        fprintf(outf, "cpu%d: MSR_ATOM_CORE_RATIOS: 0x%08llx\n", base_cpu, msr & 0xFFFFFFFF);
+
+        ratio = (msr >> 0) & 0x3F;
+        if (ratio)
+                fprintf(outf, "%d * %.1f = %.1f MHz minimum operating frequency\n",
+                        ratio, bclk, ratio * bclk);
+
+        ratio = (msr >> 8) & 0x3F;
+        if (ratio)
+                fprintf(outf, "%d * %.1f = %.1f MHz low frequency mode (LFM)\n",
+                        ratio, bclk, ratio * bclk);
+
+        ratio = (msr >> 16) & 0x3F;
+        if (ratio)
+                fprintf(outf, "%d * %.1f = %.1f MHz base frequency\n",
+                        ratio, bclk, ratio * bclk);
+
+        get_msr(base_cpu, MSR_ATOM_CORE_TURBO_RATIOS, &msr);
+        fprintf(outf, "cpu%d: MSR_ATOM_CORE_TURBO_RATIOS: 0x%08llx\n", base_cpu, msr & 0xFFFFFFFF);
+
+        ratio = (msr >> 24) & 0x3F;
+        if (ratio)
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo 4 active cores\n",
+                        ratio, bclk, ratio * bclk);
+
+        ratio = (msr >> 16) & 0x3F;
+        if (ratio)
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo 3 active cores\n",
+                        ratio, bclk, ratio * bclk);
+
+        ratio = (msr >> 8) & 0x3F;
+        if (ratio)
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo 2 active cores\n",
+                        ratio, bclk, ratio * bclk);
+
+        ratio = (msr >> 0) & 0x3F;
+        if (ratio)
+                fprintf(outf, "%d * %.1f = %.1f MHz max turbo 1 active core\n",
+                        ratio, bclk, ratio * bclk);
+}
+
+static void
 dump_knl_turbo_ratio_limits(void)
 {
         const unsigned int buckets_no = 7;
@@ -1652,7 +2016,7 @@ dump_knl_turbo_ratio_limits(void)
         for (i = buckets_no - 1; i >= 0; i--)
                 if (i > 0 ? ratio[i] != ratio[i - 1] : 1)
                         fprintf(outf,
-                                "%d * %.0f = %.0f MHz max turbo %d active cores\n",
+                                "%d * %.1f = %.1f MHz max turbo %d active cores\n",
                                 ratio[i], bclk, ratio[i] * bclk, cores[i]);
 }
 
@@ -1661,12 +2025,12 @@ dump_nhm_cst_cfg(void)
 {
         unsigned long long msr;
 
-        get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
+        get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr);
 
 #define SNB_C1_AUTO_UNDEMOTE              (1UL << 27)
 #define SNB_C3_AUTO_UNDEMOTE              (1UL << 28)
 
-        fprintf(outf, "cpu%d: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x%08llx", base_cpu, msr);
+        fprintf(outf, "cpu%d: MSR_PKG_CST_CONFIG_CONTROL: 0x%08llx", base_cpu, msr);
 
         fprintf(outf, " (%s%s%s%s%slocked: pkg-cstate-limit=%d: %s)\n",
                 (msr & SNB_C3_AUTO_UNDEMOTE) ? "UNdemote-C3, " : "",
@@ -1810,16 +2174,6 @@ void free_all_buffers(void)
         free(irqs_per_cpu);
 }
 
-/*
- * Open a file, and exit on failure
- */
-FILE *fopen_or_die(const char *path, const char *mode)
-{
-        FILE *filep = fopen(path, mode);
-        if (!filep)
-                err(1, "%s: open failed", path);
-        return filep;
-}
 
 /*
  * Parse a file containing a single int.
@@ -2148,13 +2502,14 @@ int snapshot_gfx_mhz(void)
  */
 int snapshot_proc_sysfs_files(void)
 {
-        if (snapshot_proc_interrupts())
-                return 1;
+        if (DO_BIC(BIC_IRQ))
+                if (snapshot_proc_interrupts())
+                        return 1;
 
-        if (do_gfx_rc6_ms)
+        if (DO_BIC(BIC_GFX_rc6))
                 snapshot_gfx_rc6_ms();
 
-        if (do_gfx_mhz)
+        if (DO_BIC(BIC_GFXMHz))
                 snapshot_gfx_mhz();
 
         return 0;
@@ -2283,7 +2638,9 @@ void check_permissions()
  * MSR_SMI_COUNT                   0x00000034
  *
  * MSR_PLATFORM_INFO               0x000000ce
- * MSR_NHM_SNB_PKG_CST_CFG_CTL     0x000000e2
+ * MSR_PKG_CST_CONFIG_CONTROL     0x000000e2
+ *
+ * MSR_MISC_PWR_MGMT               0x000001aa
  *
  * MSR_PKG_C3_RESIDENCY            0x000003f8
  * MSR_PKG_C6_RESIDENCY            0x000003f9
@@ -2291,7 +2648,8 @@ void check_permissions()
  * MSR_CORE_C6_RESIDENCY           0x000003fd
  *
  * Side effect:
- * sets global pkg_cstate_limit to decode MSR_NHM_SNB_PKG_CST_CFG_CTL
+ * sets global pkg_cstate_limit to decode MSR_PKG_CST_CONFIG_CONTROL
+ * sets has_misc_feature_control
  */
 int probe_nhm_msrs(unsigned int family, unsigned int model)
 {
@@ -2322,6 +2680,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
         case INTEL_FAM6_IVYBRIDGE:      /* IVB */
         case INTEL_FAM6_IVYBRIDGE_X:    /* IVB Xeon */
                 pkg_cstate_limits = snb_pkg_cstate_limits;
+                has_misc_feature_control = 1;
                 break;
         case INTEL_FAM6_HASWELL_CORE:   /* HSW */
         case INTEL_FAM6_HASWELL_X:      /* HSX */
@@ -2336,29 +2695,34 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
         case INTEL_FAM6_KABYLAKE_MOBILE:        /* KBL */
         case INTEL_FAM6_KABYLAKE_DESKTOP:       /* KBL */
                 pkg_cstate_limits = hsw_pkg_cstate_limits;
+                has_misc_feature_control = 1;
                 break;
         case INTEL_FAM6_SKYLAKE_X:      /* SKX */
                 pkg_cstate_limits = skx_pkg_cstate_limits;
+                has_misc_feature_control = 1;
                 break;
         case INTEL_FAM6_ATOM_SILVERMONT1:       /* BYT */
+                no_MSR_MISC_PWR_MGMT = 1;
         case INTEL_FAM6_ATOM_SILVERMONT2:       /* AVN */
                 pkg_cstate_limits = slv_pkg_cstate_limits;
                 break;
         case INTEL_FAM6_ATOM_AIRMONT:   /* AMT */
                 pkg_cstate_limits = amt_pkg_cstate_limits;
+                no_MSR_MISC_PWR_MGMT = 1;
                 break;
         case INTEL_FAM6_XEON_PHI_KNL:   /* PHI */
         case INTEL_FAM6_XEON_PHI_KNM:
                 pkg_cstate_limits = phi_pkg_cstate_limits;
                 break;
         case INTEL_FAM6_ATOM_GOLDMONT:  /* BXT */
+        case INTEL_FAM6_ATOM_GEMINI_LAKE:
         case INTEL_FAM6_ATOM_DENVERTON: /* DNV */
                 pkg_cstate_limits = bxt_pkg_cstate_limits;
                 break;
         default:
                 return 0;
         }
-        get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
+        get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr);
         pkg_cstate_limit = pkg_cstate_limits[msr & 0xF];
 
         get_msr(base_cpu, MSR_PLATFORM_INFO, &msr);
@@ -2368,8 +2732,69 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
         has_base_hz = 1;
         return 1;
 }
-int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model)
+/*
+ * SLV client has support for unique MSRs:
+ *
+ * MSR_CC6_DEMOTION_POLICY_CONFIG
+ * MSR_MC6_DEMOTION_POLICY_CONFIG
+ */
+
+int has_slv_msrs(unsigned int family, unsigned int model)
 {
+        if (!genuine_intel)
+                return 0;
+
+        switch (model) {
+        case INTEL_FAM6_ATOM_SILVERMONT1:
+        case INTEL_FAM6_ATOM_MERRIFIELD:
+        case INTEL_FAM6_ATOM_MOOREFIELD:
+                return 1;
+        }
+        return 0;
+}
+int is_dnv(unsigned int family, unsigned int model)
+{
+
+        if (!genuine_intel)
+                return 0;
+
+        switch (model) {
+        case INTEL_FAM6_ATOM_DENVERTON:
+                return 1;
+        }
+        return 0;
+}
+int is_bdx(unsigned int family, unsigned int model)
+{
+
+        if (!genuine_intel)
+                return 0;
+
+        switch (model) {
+        case INTEL_FAM6_BROADWELL_X:
+        case INTEL_FAM6_BROADWELL_XEON_D:
+                return 1;
+        }
+        return 0;
+}
+int is_skx(unsigned int family, unsigned int model)
+{
+
+        if (!genuine_intel)
+                return 0;
+
+        switch (model) {
+        case INTEL_FAM6_SKYLAKE_X:
+                return 1;
+        }
+        return 0;
+}
+
+int has_turbo_ratio_limit(unsigned int family, unsigned int model)
+{
+        if (has_slv_msrs(family, model))
+                return 0;
+
         switch (model) {
         /* Nehalem compatible, but do not include turbo-ratio limit support */
         case INTEL_FAM6_NEHALEM_EX:     /* Nehalem-EX Xeon - Beckton */
@@ -2381,6 +2806,13 @@ int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model)
                 return 1;
         }
 }
+int has_atom_turbo_ratio_limit(unsigned int family, unsigned int model)
+{
+        if (has_slv_msrs(family, model))
+                return 1;
+
+        return 0;
+}
 int has_ivt_turbo_ratio_limit(unsigned int family, unsigned int model)
 {
         if (!genuine_intel)
@@ -2429,6 +2861,22 @@ int has_knl_turbo_ratio_limit(unsigned int family, unsigned int model)
                 return 0;
         }
 }
+int has_glm_turbo_ratio_limit(unsigned int family, unsigned int model)
+{
+        if (!genuine_intel)
+                return 0;
+
+        if (family != 6)
+                return 0;
+
+        switch (model) {
+        case INTEL_FAM6_ATOM_GOLDMONT:
+        case INTEL_FAM6_SKYLAKE_X:
+                return 1;
+        default:
+                return 0;
+        }
+}
 int has_config_tdp(unsigned int family, unsigned int model)
 {
         if (!genuine_intel)
@@ -2475,8 +2923,11 @@ dump_cstate_pstate_config_info(unsigned int family, unsigned int model)
         if (has_ivt_turbo_ratio_limit(family, model))
                 dump_ivt_turbo_ratio_limits();
 
-        if (has_nhm_turbo_ratio_limit(family, model))
-                dump_nhm_turbo_ratio_limits();
+        if (has_turbo_ratio_limit(family, model))
+                dump_turbo_ratio_limits(family, model);
+
+        if (has_atom_turbo_ratio_limit(family, model))
+                dump_atom_turbo_ratio_limits();
 
         if (has_knl_turbo_ratio_limit(family, model))
                 dump_knl_turbo_ratio_limits();
@@ -2487,6 +2938,96 @@ dump_cstate_pstate_config_info(unsigned int family, unsigned int model)
         dump_nhm_cst_cfg();
 }
 
+static void
+dump_sysfs_cstate_config(void)
+{
+        char path[64];
+        char name_buf[16];
+        char desc[64];
+        FILE *input;
+        int state;
+        char *sp;
+
+        if (!DO_BIC(BIC_sysfs))
+                return;
+
+        for (state = 0; state < 10; ++state) {
+
+                sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name",
+                        base_cpu, state);
+                input = fopen(path, "r");
+                if (input == NULL)
+                        continue;
+                fgets(name_buf, sizeof(name_buf), input);
+
+                 /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
+                sp = strchr(name_buf, '-');
+                if (!sp)
+                        sp = strchrnul(name_buf, '\n');
+                *sp = '\0';
+
+                fclose(input);
+
+                sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/desc",
+                        base_cpu, state);
+                input = fopen(path, "r");
+                if (input == NULL)
+                        continue;
+                fgets(desc, sizeof(desc), input);
+
+                fprintf(outf, "cpu%d: %s: %s", base_cpu, name_buf, desc);
+                fclose(input);
+        }
+}
+static void
+dump_sysfs_pstate_config(void)
+{
+        char path[64];
+        char driver_buf[64];
+        char governor_buf[64];
+        FILE *input;
+        int turbo;
+
+        sprintf(path, "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_driver",
+                        base_cpu);
+        input = fopen(path, "r");
+        if (input == NULL) {
+                fprintf(stderr, "NSFOD %s\n", path);
+                return;
+        }
+        fgets(driver_buf, sizeof(driver_buf), input);
+        fclose(input);
+
+        sprintf(path, "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_governor",
+                        base_cpu);
+        input = fopen(path, "r");
+        if (input == NULL) {
+                fprintf(stderr, "NSFOD %s\n", path);
+                return;
+        }
+        fgets(governor_buf, sizeof(governor_buf), input);
+        fclose(input);
+
+        fprintf(outf, "cpu%d: cpufreq driver: %s", base_cpu, driver_buf);
+        fprintf(outf, "cpu%d: cpufreq governor: %s", base_cpu, governor_buf);
+
+        sprintf(path, "/sys/devices/system/cpu/cpufreq/boost");
+        input = fopen(path, "r");
+        if (input != NULL) {
+                fscanf(input, "%d", &turbo);
+                fprintf(outf, "cpufreq boost: %d\n", turbo);
+                fclose(input);
+        }
+
+        sprintf(path, "/sys/devices/system/cpu/intel_pstate/no_turbo");
+        input = fopen(path, "r");
+        if (input != NULL) {
+                fscanf(input, "%d", &turbo);
+                fprintf(outf, "cpufreq intel_pstate no_turbo: %d\n", turbo);
+                fclose(input);
+        }
+}
+
 
 /*
  * print_epb()
@@ -2790,15 +3331,40 @@ void rapl_probe(unsigned int family, unsigned int model)
         case INTEL_FAM6_BROADWELL_CORE: /* BDW */
         case INTEL_FAM6_BROADWELL_GT3E: /* BDW */
                 do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_GFX | RAPL_PKG_POWER_INFO;
+                if (rapl_joules) {
+                        BIC_PRESENT(BIC_Pkg_J);
+                        BIC_PRESENT(BIC_Cor_J);
+                        BIC_PRESENT(BIC_GFX_J);
+                } else {
+                        BIC_PRESENT(BIC_PkgWatt);
+                        BIC_PRESENT(BIC_CorWatt);
+                        BIC_PRESENT(BIC_GFXWatt);
+                }
                 break;
         case INTEL_FAM6_ATOM_GOLDMONT:  /* BXT */
+        case INTEL_FAM6_ATOM_GEMINI_LAKE:
                 do_rapl = RAPL_PKG | RAPL_PKG_POWER_INFO;
+                if (rapl_joules)
+                        BIC_PRESENT(BIC_Pkg_J);
+                else
+                        BIC_PRESENT(BIC_PkgWatt);
                 break;
         case INTEL_FAM6_SKYLAKE_MOBILE: /* SKL */
         case INTEL_FAM6_SKYLAKE_DESKTOP:        /* SKL */
         case INTEL_FAM6_KABYLAKE_MOBILE:        /* KBL */
         case INTEL_FAM6_KABYLAKE_DESKTOP:       /* KBL */
                 do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
+                BIC_PRESENT(BIC_PKG__);
+                BIC_PRESENT(BIC_RAM__);
+                if (rapl_joules) {
+                        BIC_PRESENT(BIC_Pkg_J);
+                        BIC_PRESENT(BIC_Cor_J);
+                        BIC_PRESENT(BIC_RAM_J);
+                } else {
+                        BIC_PRESENT(BIC_PkgWatt);
+                        BIC_PRESENT(BIC_CorWatt);
+                        BIC_PRESENT(BIC_RAMWatt);
+                }
                 break;
         case INTEL_FAM6_HASWELL_X:      /* HSX */
         case INTEL_FAM6_BROADWELL_X:    /* BDX */
@@ -2807,17 +3373,55 @@ void rapl_probe(unsigned int family, unsigned int model)
         case INTEL_FAM6_XEON_PHI_KNL:   /* KNL */
         case INTEL_FAM6_XEON_PHI_KNM:
                 do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
+                BIC_PRESENT(BIC_PKG__);
+                BIC_PRESENT(BIC_RAM__);
+                if (rapl_joules) {
+                        BIC_PRESENT(BIC_Pkg_J);
+                        BIC_PRESENT(BIC_RAM_J);
+                } else {
+                        BIC_PRESENT(BIC_PkgWatt);
+                        BIC_PRESENT(BIC_RAMWatt);
+                }
                 break;
         case INTEL_FAM6_SANDYBRIDGE_X:
         case INTEL_FAM6_IVYBRIDGE_X:
                 do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_PKG_PERF_STATUS | RAPL_DRAM_PERF_STATUS | RAPL_PKG_POWER_INFO;
+                BIC_PRESENT(BIC_PKG__);
+                BIC_PRESENT(BIC_RAM__);
+                if (rapl_joules) {
+                        BIC_PRESENT(BIC_Pkg_J);
+                        BIC_PRESENT(BIC_Cor_J);
+                        BIC_PRESENT(BIC_RAM_J);
+                } else {
+                        BIC_PRESENT(BIC_PkgWatt);
+                        BIC_PRESENT(BIC_CorWatt);
+                        BIC_PRESENT(BIC_RAMWatt);
+                }
                 break;
         case INTEL_FAM6_ATOM_SILVERMONT1:       /* BYT */
         case INTEL_FAM6_ATOM_SILVERMONT2:       /* AVN */
                 do_rapl = RAPL_PKG | RAPL_CORES;
+                if (rapl_joules) {
+                        BIC_PRESENT(BIC_Pkg_J);
+                        BIC_PRESENT(BIC_Cor_J);
+                } else {
+                        BIC_PRESENT(BIC_PkgWatt);
+                        BIC_PRESENT(BIC_CorWatt);
+                }
                 break;
         case INTEL_FAM6_ATOM_DENVERTON: /* DNV */
                 do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO | RAPL_CORES_ENERGY_STATUS;
+                BIC_PRESENT(BIC_PKG__);
+                BIC_PRESENT(BIC_RAM__);
+                if (rapl_joules) {
+                        BIC_PRESENT(BIC_Pkg_J);
+                        BIC_PRESENT(BIC_Cor_J);
+                        BIC_PRESENT(BIC_RAM_J);
+                } else {
+                        BIC_PRESENT(BIC_PkgWatt);
+                        BIC_PRESENT(BIC_CorWatt);
+                        BIC_PRESENT(BIC_RAMWatt);
+                }
                 break;
         default:
                 return;
@@ -2844,7 +3448,7 @@ void rapl_probe(unsigned int family, unsigned int model)
         tdp = get_tdp(model);
 
         rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
-        if (debug)
+        if (!quiet)
                 fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
 
         return;
@@ -2969,11 +3573,9 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
         if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr))
                 return -1;
 
-        if (debug) {
-                fprintf(outf, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx "
-                        "(%f Watts, %f Joules, %f sec.)\n", cpu, msr,
-                        rapl_power_units, rapl_energy_units, rapl_time_units);
-        }
+        fprintf(outf, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr,
+                rapl_power_units, rapl_energy_units, rapl_time_units);
+
         if (do_rapl & RAPL_PKG_POWER_INFO) {
 
                 if (get_msr(cpu, MSR_PKG_POWER_INFO, &msr))
@@ -2994,7 +3596,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
                         return -9;
 
                 fprintf(outf, "cpu%d: MSR_PKG_POWER_LIMIT: 0x%08llx (%slocked)\n",
-                        cpu, msr, (msr >> 63) & 1 ? "": "UN");
+                        cpu, msr, (msr >> 63) & 1 ? "" : "UN");
 
                 print_power_limit_msr(cpu, msr, "PKG Limit #1");
                 fprintf(outf, "cpu%d: PKG Limit #2: %sabled (%f Watts, %f* sec, clamp %sabled)\n",
@@ -3020,40 +3622,34 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
                 if (get_msr(cpu, MSR_DRAM_POWER_LIMIT, &msr))
                         return -9;
                 fprintf(outf, "cpu%d: MSR_DRAM_POWER_LIMIT: 0x%08llx (%slocked)\n",
-                                cpu, msr, (msr >> 31) & 1 ? "": "UN");
+                                cpu, msr, (msr >> 31) & 1 ? "" : "UN");
 
                 print_power_limit_msr(cpu, msr, "DRAM Limit");
         }
         if (do_rapl & RAPL_CORE_POLICY) {
-                if (debug) {
-                        if (get_msr(cpu, MSR_PP0_POLICY, &msr))
-                                return -7;
+                if (get_msr(cpu, MSR_PP0_POLICY, &msr))
+                        return -7;
 
-                        fprintf(outf, "cpu%d: MSR_PP0_POLICY: %lld\n", cpu, msr & 0xF);
-                }
+                fprintf(outf, "cpu%d: MSR_PP0_POLICY: %lld\n", cpu, msr & 0xF);
         }
         if (do_rapl & RAPL_CORES_POWER_LIMIT) {
-                if (debug) {
-                        if (get_msr(cpu, MSR_PP0_POWER_LIMIT, &msr))
-                                return -9;
-                        fprintf(outf, "cpu%d: MSR_PP0_POWER_LIMIT: 0x%08llx (%slocked)\n",
-                                        cpu, msr, (msr >> 31) & 1 ? "": "UN");
-                        print_power_limit_msr(cpu, msr, "Cores Limit");
-                }
+                if (get_msr(cpu, MSR_PP0_POWER_LIMIT, &msr))
+                        return -9;
+                fprintf(outf, "cpu%d: MSR_PP0_POWER_LIMIT: 0x%08llx (%slocked)\n",
+                                cpu, msr, (msr >> 31) & 1 ? "" : "UN");
+                print_power_limit_msr(cpu, msr, "Cores Limit");
         }
         if (do_rapl & RAPL_GFX) {
-                if (debug) {
-                        if (get_msr(cpu, MSR_PP1_POLICY, &msr))
-                                return -8;
+                if (get_msr(cpu, MSR_PP1_POLICY, &msr))
+                        return -8;
 
-                        fprintf(outf, "cpu%d: MSR_PP1_POLICY: %lld\n", cpu, msr & 0xF);
+                fprintf(outf, "cpu%d: MSR_PP1_POLICY: %lld\n", cpu, msr & 0xF);
 
-                        if (get_msr(cpu, MSR_PP1_POWER_LIMIT, &msr))
-                                return -9;
-                        fprintf(outf, "cpu%d: MSR_PP1_POWER_LIMIT: 0x%08llx (%slocked)\n",
-                                        cpu, msr, (msr >> 31) & 1 ? "": "UN");
-                        print_power_limit_msr(cpu, msr, "GFX Limit");
-                }
+                if (get_msr(cpu, MSR_PP1_POWER_LIMIT, &msr))
+                        return -9;
+                fprintf(outf, "cpu%d: MSR_PP1_POWER_LIMIT: 0x%08llx (%slocked)\n",
+                                cpu, msr, (msr >> 31) & 1 ? "" : "UN");
+                print_power_limit_msr(cpu, msr, "GFX Limit");
         }
         return 0;
 }
@@ -3090,6 +3686,7 @@ int has_snb_msrs(unsigned int family, unsigned int model)
         case INTEL_FAM6_KABYLAKE_DESKTOP:       /* KBL */
         case INTEL_FAM6_SKYLAKE_X:      /* SKX */
         case INTEL_FAM6_ATOM_GOLDMONT:  /* BXT */
+        case INTEL_FAM6_ATOM_GEMINI_LAKE:
         case INTEL_FAM6_ATOM_DENVERTON: /* DNV */
                 return 1;
         }
@@ -3121,6 +3718,7 @@ int has_hsw_msrs(unsigned int family, unsigned int model)
         case INTEL_FAM6_KABYLAKE_MOBILE:        /* KBL */
         case INTEL_FAM6_KABYLAKE_DESKTOP:       /* KBL */
         case INTEL_FAM6_ATOM_GOLDMONT:  /* BXT */
+        case INTEL_FAM6_ATOM_GEMINI_LAKE:
                 return 1;
         }
         return 0;
@@ -3149,8 +3747,6 @@ int has_skl_msrs(unsigned int family, unsigned int model)
         return 0;
 }
 
-
-
 int is_slm(unsigned int family, unsigned int model)
 {
         if (!genuine_intel)
@@ -3201,7 +3797,8 @@ double slm_bclk(void)
         }
         freq = slm_freq_table[i];
 
-        fprintf(outf, "SLM BCLK: %.1f Mhz\n", freq);
+        if (!quiet)
+                fprintf(outf, "SLM BCLK: %.1f Mhz\n", freq);
 
         return freq;
 }
@@ -3264,7 +3861,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk
 
         target_c_local = (msr >> 16) & 0xFF;
 
-        if (debug)
+        if (!quiet)
                 fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n",
                         cpu, msr, target_c_local);
 
@@ -3299,13 +3896,30 @@ void decode_misc_enable_msr(void)
         unsigned long long msr;
 
         if (!get_msr(base_cpu, MSR_IA32_MISC_ENABLE, &msr))
-                fprintf(outf, "cpu%d: MSR_IA32_MISC_ENABLE: 0x%08llx (%s %s %s)\n",
+                fprintf(outf, "cpu%d: MSR_IA32_MISC_ENABLE: 0x%08llx (%sTCC %sEIST %sMWAIT %sPREFETCH %sTURBO)\n",
                         base_cpu, msr,
-                        msr & (1 << 3) ? "TCC" : "",
-                        msr & (1 << 16) ? "EIST" : "",
-                        msr & (1 << 18) ? "MONITOR" : "");
+                        msr & MSR_IA32_MISC_ENABLE_TM1 ? "" : "No-",
+                        msr & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP ? "" : "No-",
+                        msr & MSR_IA32_MISC_ENABLE_MWAIT ? "No-" : "",
+                        msr & MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE ? "No-" : "",
+                        msr & MSR_IA32_MISC_ENABLE_TURBO_DISABLE ? "No-" : "");
 }
 
+void decode_misc_feature_control(void)
+{
+        unsigned long long msr;
+
+        if (!has_misc_feature_control)
+                return;
+
+        if (!get_msr(base_cpu, MSR_MISC_FEATURE_CONTROL, &msr))
+                fprintf(outf, "cpu%d: MSR_MISC_FEATURE_CONTROL: 0x%08llx (%sL2-Prefetch %sL2-Prefetch-pair %sL1-Prefetch %sL1-IP-Prefetch)\n",
+                        base_cpu, msr,
+                        msr & (0 << 0) ? "No-" : "",
+                        msr & (1 << 0) ? "No-" : "",
+                        msr & (2 << 0) ? "No-" : "",
+                        msr & (3 << 0) ? "No-" : "");
+}
 /*
  * Decode MSR_MISC_PWR_MGMT
  *
@@ -3320,6 +3934,9 @@ void decode_misc_pwr_mgmt_msr(void)
         if (!do_nhm_platform_info)
                 return;
 
+        if (no_MSR_MISC_PWR_MGMT)
+                return;
+
         if (!get_msr(base_cpu, MSR_MISC_PWR_MGMT, &msr))
                 fprintf(outf, "cpu%d: MSR_MISC_PWR_MGMT: 0x%08llx (%sable-EIST_Coordination %sable-EPB %sable-OOB)\n",
                         base_cpu, msr,
@@ -3327,11 +3944,30 @@ void decode_misc_pwr_mgmt_msr(void)
                         msr & (1 << 1) ? "EN" : "DIS",
                         msr & (1 << 8) ? "EN" : "DIS");
 }
+/*
+ * Decode MSR_CC6_DEMOTION_POLICY_CONFIG, MSR_MC6_DEMOTION_POLICY_CONFIG
+ *
+ * This MSRs are present on Silvermont processors,
+ * Intel Atom processor E3000 series (Baytrail), and friends.
+ */
+void decode_c6_demotion_policy_msr(void)
+{
+        unsigned long long msr;
+
+        if (!get_msr(base_cpu, MSR_CC6_DEMOTION_POLICY_CONFIG, &msr))
+                fprintf(outf, "cpu%d: MSR_CC6_DEMOTION_POLICY_CONFIG: 0x%08llx (%sable-CC6-Demotion)\n",
+                        base_cpu, msr, msr & (1 << 0) ? "EN" : "DIS");
+
+        if (!get_msr(base_cpu, MSR_MC6_DEMOTION_POLICY_CONFIG, &msr))
+                fprintf(outf, "cpu%d: MSR_MC6_DEMOTION_POLICY_CONFIG: 0x%08llx (%sable-MC6-Demotion)\n",
+                        base_cpu, msr, msr & (1 << 0) ? "EN" : "DIS");
+}
 
 void process_cpuid()
 {
         unsigned int eax, ebx, ecx, edx, max_level, max_extended_level;
         unsigned int fms, family, model, stepping;
+        unsigned int has_turbo;
 
         eax = ebx = ecx = edx = 0;
 
@@ -3340,7 +3976,7 @@ void process_cpuid()
         if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e)
                 genuine_intel = 1;
 
-        if (debug)
+        if (!quiet)
                 fprintf(outf, "CPUID(0): %.4s%.4s%.4s ",
                         (char *)&ebx, (char *)&edx, (char *)&ecx);
 
@@ -3351,7 +3987,7 @@ void process_cpuid()
         if (family == 6 || family == 0xf)
                 model += ((fms >> 16) & 0xf) << 4;
 
-        if (debug) {
+        if (!quiet) {
                 fprintf(outf, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n",
                         max_level, family, model, stepping, family, model, stepping);
                 fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s\n",
@@ -3394,8 +4030,18 @@ void process_cpuid()
 
         __cpuid(0x6, eax, ebx, ecx, edx);
         has_aperf = ecx & (1 << 0);
+        if (has_aperf) {
+                BIC_PRESENT(BIC_Avg_MHz);
+                BIC_PRESENT(BIC_Busy);
+                BIC_PRESENT(BIC_Bzy_MHz);
+        }
         do_dts = eax & (1 << 0);
+        if (do_dts)
+                BIC_PRESENT(BIC_CoreTmp);
+        has_turbo = eax & (1 << 1);
         do_ptm = eax & (1 << 6);
+        if (do_ptm)
+                BIC_PRESENT(BIC_PkgTmp);
         has_hwp = eax & (1 << 7);
         has_hwp_notify = eax & (1 << 8);
         has_hwp_activity_window = eax & (1 << 9);
@@ -3403,10 +4049,11 @@ void process_cpuid()
         has_hwp_pkg = eax & (1 << 11);
         has_epb = ecx & (1 << 3);
 
-        if (debug)
-                fprintf(outf, "CPUID(6): %sAPERF, %sDTS, %sPTM, %sHWP, "
+        if (!quiet)
+                fprintf(outf, "CPUID(6): %sAPERF, %sTURBO, %sDTS, %sPTM, %sHWP, "
                         "%sHWPnotify, %sHWPwindow, %sHWPepp, %sHWPpkg, %sEPB\n",
                         has_aperf ? "" : "No-",
+                        has_turbo ? "" : "No-",
                         do_dts ? "" : "No-",
                         do_ptm ? "" : "No-",
                         has_hwp ? "" : "No-",
@@ -3416,10 +4063,11 @@ void process_cpuid()
                         has_hwp_pkg ? "" : "No-",
                         has_epb ? "" : "No-");
 
-        if (debug)
+        if (!quiet)
                 decode_misc_enable_msr();
 
-        if (max_level >= 0x7 && debug) {
+
+        if (max_level >= 0x7 && !quiet) {
                 int has_sgx;
 
                 ecx = 0;
@@ -3445,7 +4093,7 @@ void process_cpuid()
 
                 if (ebx_tsc != 0) {
 
-                        if (debug && (ebx != 0))
+                        if (!quiet && (ebx != 0))
                                 fprintf(outf, "CPUID(0x15): eax_crystal: %d ebx_tsc: %d ecx_crystal_hz: %d\n",
                                         eax_crystal, ebx_tsc, crystal_hz);
 
@@ -3462,6 +4110,7 @@ void process_cpuid()
                                         crystal_hz = 25000000;  /* 25.0 MHz */
                                         break;
                                 case INTEL_FAM6_ATOM_GOLDMONT:  /* BXT */
+                                case INTEL_FAM6_ATOM_GEMINI_LAKE:
                                         crystal_hz = 19200000;  /* 19.2 MHz */
                                         break;
                                 default:
@@ -3470,7 +4119,7 @@ void process_cpuid()
 
                         if (crystal_hz) {
                                 tsc_hz =  (unsigned long long) crystal_hz * ebx_tsc / eax_crystal;
-                                if (debug)
+                                if (!quiet)
                                         fprintf(outf, "TSC: %lld MHz (%d Hz * %d / %d / 1000000)\n",
                                                 tsc_hz / 1000000, crystal_hz, ebx_tsc,  eax_crystal);
                         }
@@ -3485,7 +4134,7 @@ void process_cpuid()
                 base_mhz = max_mhz = bus_mhz = edx = 0;
 
                 __cpuid(0x16, base_mhz, max_mhz, bus_mhz, edx);
-                if (debug)
+                if (!quiet)
                         fprintf(outf, "CPUID(0x16): base_mhz: %d max_mhz: %d bus_mhz: %d\n",
                                 base_mhz, max_mhz, bus_mhz);
         }
@@ -3493,56 +4142,96 @@ void process_cpuid()
         if (has_aperf)
                 aperf_mperf_multiplier = get_aperf_mperf_multiplier(family, model);
 
-        do_nhm_platform_info = do_nhm_cstates = do_smi = probe_nhm_msrs(family, model);
+        BIC_PRESENT(BIC_IRQ);
+        BIC_PRESENT(BIC_TSC_MHz);
+
+        if (probe_nhm_msrs(family, model)) {
+                do_nhm_platform_info = 1;
+                BIC_PRESENT(BIC_CPU_c1);
+                BIC_PRESENT(BIC_CPU_c3);
+                BIC_PRESENT(BIC_CPU_c6);
+                BIC_PRESENT(BIC_SMI);
+        }
         do_snb_cstates = has_snb_msrs(family, model);
+
+        if (do_snb_cstates)
+                BIC_PRESENT(BIC_CPU_c7);
+
         do_irtl_snb = has_snb_msrs(family, model);
-        do_pc2 = do_snb_cstates && (pkg_cstate_limit >= PCL__2);
-        do_pc3 = (pkg_cstate_limit >= PCL__3);
-        do_pc6 = (pkg_cstate_limit >= PCL__6);
-        do_pc7 = do_snb_cstates && (pkg_cstate_limit >= PCL__7);
-        do_c8_c9_c10 = has_hsw_msrs(family, model);
+        if (do_snb_cstates && (pkg_cstate_limit >= PCL__2))
+                BIC_PRESENT(BIC_Pkgpc2);
+        if (pkg_cstate_limit >= PCL__3)
+                BIC_PRESENT(BIC_Pkgpc3);
+        if (pkg_cstate_limit >= PCL__6)
+                BIC_PRESENT(BIC_Pkgpc6);
+        if (do_snb_cstates && (pkg_cstate_limit >= PCL__7))
+                BIC_PRESENT(BIC_Pkgpc7);
+        if (has_slv_msrs(family, model)) {
+                BIC_NOT_PRESENT(BIC_Pkgpc2);
+                BIC_NOT_PRESENT(BIC_Pkgpc3);
+                BIC_PRESENT(BIC_Pkgpc6);
+                BIC_NOT_PRESENT(BIC_Pkgpc7);
+                BIC_PRESENT(BIC_Mod_c6);
+                use_c1_residency_msr = 1;
+        }
+        if (is_dnv(family, model)) {
+                BIC_PRESENT(BIC_CPU_c1);
+                BIC_NOT_PRESENT(BIC_CPU_c3);
+                BIC_NOT_PRESENT(BIC_Pkgpc3);
+                BIC_NOT_PRESENT(BIC_CPU_c7);
+                BIC_NOT_PRESENT(BIC_Pkgpc7);
+                use_c1_residency_msr = 1;
+        }
+        if (is_skx(family, model)) {
+                BIC_NOT_PRESENT(BIC_CPU_c3);
+                BIC_NOT_PRESENT(BIC_Pkgpc3);
+                BIC_NOT_PRESENT(BIC_CPU_c7);
+                BIC_NOT_PRESENT(BIC_Pkgpc7);
+        }
+        if (is_bdx(family, model)) {
+                BIC_NOT_PRESENT(BIC_CPU_c7);
+                BIC_NOT_PRESENT(BIC_Pkgpc7);
+        }
+        if (has_hsw_msrs(family, model)) {
+                BIC_PRESENT(BIC_Pkgpc8);
+                BIC_PRESENT(BIC_Pkgpc9);
+                BIC_PRESENT(BIC_Pkgpc10);
+        }
         do_irtl_hsw = has_hsw_msrs(family, model);
         do_skl_residency = has_skl_msrs(family, model);
         do_slm_cstates = is_slm(family, model);
         do_knl_cstates  = is_knl(family, model);
 
-        if (debug)
+        if (!quiet)
                 decode_misc_pwr_mgmt_msr();
 
+        if (!quiet && has_slv_msrs(family, model))
+                decode_c6_demotion_policy_msr();
+
         rapl_probe(family, model);
         perf_limit_reasons_probe(family, model);
 
-        if (debug)
+        if (!quiet)
                 dump_cstate_pstate_config_info(family, model);
 
+        if (!quiet)
+                dump_sysfs_cstate_config();
+        if (!quiet)
+                dump_sysfs_pstate_config();
+
         if (has_skl_msrs(family, model))
                 calculate_tsc_tweak();
 
-        do_gfx_rc6_ms = !access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK);
+        if (!access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK))
+                BIC_PRESENT(BIC_GFX_rc6);
 
-        do_gfx_mhz = !access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK);
+        if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK))
+                BIC_PRESENT(BIC_GFXMHz);
 
-        return;
-}
+        if (!quiet)
+                decode_misc_feature_control();
 
-void help()
-{
-        fprintf(outf,
-        "Usage: turbostat [OPTIONS][(--interval seconds) | COMMAND ...]\n"
-        "\n"
-        "Turbostat forks the specified COMMAND and prints statistics\n"
-        "when COMMAND completes.\n"
-        "If no COMMAND is specified, turbostat wakes every 5-seconds\n"
-        "to print statistics, until interrupted.\n"
-        "--add          add a counter\n"
-        "               eg. --add msr0x10,u64,cpu,delta,MY_TSC\n"
-        "--debug        run in \"debug\" mode\n"
-        "--interval sec Override default 5-second measurement interval\n"
-        "--help         print this help message\n"
-        "--out file     create or truncate \"file\" for all output\n"
-        "--version      print version information\n"
-        "\n"
-        "For more help, run \"man turbostat\"\n");
+        return;
 }
 
 
@@ -3579,7 +4268,7 @@ void topology_probe()
         topo.max_cpu_num = 0;
         for_all_proc_cpus(count_cpus);
         if (!summary_only && topo.num_cpus > 1)
-                show_cpu = 1;
+                BIC_PRESENT(BIC_CPU);
 
         if (debug > 1)
                 fprintf(outf, "num_cpus %d max_cpu_num %d\n", topo.num_cpus, topo.max_cpu_num);
@@ -3599,6 +4288,15 @@ void topology_probe()
         for_all_proc_cpus(mark_cpu_present);
 
         /*
+         * Validate that all cpus in cpu_subset are also in cpu_present_set
+         */
+        for (i = 0; i < CPU_SUBSET_MAXCPUS; ++i) {
+                if (CPU_ISSET_S(i, cpu_subset_size, cpu_subset))
+                        if (!CPU_ISSET_S(i, cpu_present_setsize, cpu_present_set))
+                                err(1, "cpu%d not present", i);
+        }
+
+        /*
          * Allocate and initialize cpu_affinity_set
          */
         cpu_affinity_set = CPU_ALLOC((topo.max_cpu_num + 1));
@@ -3639,15 +4337,15 @@ void topology_probe()
         if (debug > 1)
                 fprintf(outf, "max_core_id %d, sizing for %d cores per package\n",
                         max_core_id, topo.num_cores_per_pkg);
-        if (debug && !summary_only && topo.num_cores_per_pkg > 1)
-                show_core = 1;
+        if (!summary_only && topo.num_cores_per_pkg > 1)
+                BIC_PRESENT(BIC_Core);
 
         topo.num_packages = max_package_id + 1;
         if (debug > 1)
                 fprintf(outf, "max_package_id %d, sizing for %d packages\n",
                         max_package_id, topo.num_packages);
-        if (debug && !summary_only && topo.num_packages > 1)
-                show_pkg = 1;
+        if (!summary_only && topo.num_packages > 1)
+                BIC_PRESENT(BIC_Package);
 
         topo.num_threads_per_core = max_siblings;
         if (debug > 1)
@@ -3662,7 +4360,7 @@ allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_data
         int i;
 
         *t = calloc(topo.num_threads_per_core * topo.num_cores_per_pkg *
-                topo.num_packages, sizeof(struct thread_data) + sys.thread_counter_bytes);
+                topo.num_packages, sizeof(struct thread_data));
         if (*t == NULL)
                 goto error;
 
@@ -3671,14 +4369,14 @@ allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_data
                 (*t)[i].cpu_id = -1;
 
         *c = calloc(topo.num_cores_per_pkg * topo.num_packages,
-                sizeof(struct core_data) + sys.core_counter_bytes);
+                sizeof(struct core_data));
         if (*c == NULL)
                 goto error;
 
         for (i = 0; i < topo.num_cores_per_pkg * topo.num_packages; i++)
                 (*c)[i].core_id = -1;
 
-        *p = calloc(topo.num_packages, sizeof(struct pkg_data) + sys.package_counter_bytes);
+        *p = calloc(topo.num_packages, sizeof(struct pkg_data));
         if (*p == NULL)
                 goto error;
 
@@ -3789,24 +4487,24 @@ void turbostat_init()
         process_cpuid();
 
 
-        if (debug)
+        if (!quiet)
                 for_all_cpus(print_hwp, ODD_COUNTERS);
 
-        if (debug)
+        if (!quiet)
                 for_all_cpus(print_epb, ODD_COUNTERS);
 
-        if (debug)
+        if (!quiet)
                 for_all_cpus(print_perf_limit, ODD_COUNTERS);
 
-        if (debug)
+        if (!quiet)
                 for_all_cpus(print_rapl, ODD_COUNTERS);
 
         for_all_cpus(set_temperature_target, ODD_COUNTERS);
 
-        if (debug)
+        if (!quiet)
                 for_all_cpus(print_thermal, ODD_COUNTERS);
 
-        if (debug && do_irtl_snb)
+        if (!quiet && do_irtl_snb)
                 print_irtl();
 }
 
@@ -3815,6 +4513,7 @@ int fork_it(char **argv)
         pid_t child_pid;
         int status;
 
+        snapshot_proc_sysfs_files();
         status = for_all_cpus(get_counters, EVEN_COUNTERS);
         if (status)
                 exit(status);
@@ -3826,6 +4525,7 @@ int fork_it(char **argv)
         if (!child_pid) {
                 /* child */
                 execvp(argv[0], argv);
+                err(errno, "exec %s", argv[0]);
         } else {
 
                 /* parent */
@@ -3841,6 +4541,7 @@ int fork_it(char **argv)
          * n.b. fork_it() does not check for errors from for_all_cpus()
          * because re-starting is problematic when forking
          */
+        snapshot_proc_sysfs_files();
         for_all_cpus(get_counters, ODD_COUNTERS);
         gettimeofday(&tv_odd, (struct timezone *)NULL);
         timersub(&tv_odd, &tv_even, &tv_delta);
@@ -3862,6 +4563,7 @@ int get_and_dump_counters(void)
 {
         int status;
 
+        snapshot_proc_sysfs_files();
         status = for_all_cpus(get_counters, ODD_COUNTERS);
         if (status)
                 return status;
@@ -3876,13 +4578,13 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-        fprintf(outf, "turbostat version 4.16 24 Dec 2016"
+        fprintf(outf, "turbostat version 17.02.24"
                 " - Len Brown <lenb@kernel.org>\n");
 }
 
-int add_counter(unsigned int msr_num, char *name, unsigned int width,
-        enum counter_scope scope, enum counter_type type,
-        enum counter_format format)
+int add_counter(unsigned int msr_num, char *path, char *name,
+        unsigned int width, enum counter_scope scope,
+        enum counter_type type, enum counter_format format, int flags)
 {
         struct msr_counter *msrp;
 
@@ -3894,31 +4596,46 @@ int add_counter(unsigned int msr_num, char *name, unsigned int width,
 
         msrp->msr_num = msr_num;
         strncpy(msrp->name, name, NAME_BYTES);
+        if (path)
+                strncpy(msrp->path, path, PATH_BYTES);
         msrp->width = width;
         msrp->type = type;
         msrp->format = format;
+        msrp->flags = flags;
 
         switch (scope) {
 
         case SCOPE_CPU:
-                sys.thread_counter_bytes += 64;
                 msrp->next = sys.tp;
                 sys.tp = msrp;
-                sys.thread_counter_bytes += sizeof(unsigned long long);
+                sys.added_thread_counters++;
+                if (sys.added_thread_counters > MAX_ADDED_COUNTERS) {
+                        fprintf(stderr, "exceeded max %d added thread counters\n",
+                                MAX_ADDED_COUNTERS);
+                        exit(-1);
+                }
                 break;
 
         case SCOPE_CORE:
-                sys.core_counter_bytes += 64;
                 msrp->next = sys.cp;
                 sys.cp = msrp;
-                sys.core_counter_bytes += sizeof(unsigned long long);
+                sys.added_core_counters++;
+                if (sys.added_core_counters > MAX_ADDED_COUNTERS) {
+                        fprintf(stderr, "exceeded max %d added core counters\n",
+                                MAX_ADDED_COUNTERS);
+                        exit(-1);
+                }
                 break;
 
         case SCOPE_PACKAGE:
-                sys.package_counter_bytes += 64;
                 msrp->next = sys.pp;
                 sys.pp = msrp;
-                sys.package_counter_bytes += sizeof(unsigned long long);
+                sys.added_package_counters++;
+                if (sys.added_package_counters > MAX_ADDED_COUNTERS) {
+                        fprintf(stderr, "exceeded max %d added package counters\n",
+                                MAX_ADDED_COUNTERS);
+                        exit(-1);
+                }
                 break;
         }
 
@@ -3928,7 +4645,8 @@ int add_counter(unsigned int msr_num, char *name, unsigned int width,
 void parse_add_command(char *add_command)
 {
         int msr_num = 0;
-        char name_buffer[NAME_BYTES];
+        char *path = NULL;
+        char name_buffer[NAME_BYTES] = "";
         int width = 64;
         int fail = 0;
         enum counter_scope scope = SCOPE_CPU;
@@ -3943,6 +4661,11 @@ void parse_add_command(char *add_command)
                 if (sscanf(add_command, "msr%d", &msr_num) == 1)
                         goto next;
 
+                if (*add_command == '/') {
+                        path = add_command;
+                        goto next;
+                }
+
                 if (sscanf(add_command, "u%d", &width) == 1) {
                         if ((width == 32) || (width == 64))
                                 goto next;
@@ -3968,6 +4691,10 @@ void parse_add_command(char *add_command)
                         type = COUNTER_SECONDS;
                         goto next;
                 }
+                if (!strncmp(add_command, "usec", strlen("usec"))) {
+                        type = COUNTER_USEC;
+                        goto next;
+                }
                 if (!strncmp(add_command, "raw", strlen("raw"))) {
                         format = FORMAT_RAW;
                         goto next;
@@ -3992,36 +4719,26 @@ void parse_add_command(char *add_command)
 
 next:
                 add_command = strchr(add_command, ',');
-                if (add_command)
+                if (add_command) {
+                        *add_command = '\0';
                         add_command++;
+                }
 
         }
-        if (msr_num == 0) {
-                fprintf(stderr, "--add: (msrDDD | msr0xXXX) required\n");
+        if ((msr_num == 0) && (path == NULL)) {
+                fprintf(stderr, "--add: (msrDDD | msr0xXXX | /path_to_counter ) required\n");
                 fail++;
         }
 
         /* generate default column header */
         if (*name_buffer == '\0') {
-                if (format == FORMAT_RAW) {
-                        if (width == 32)
-                                sprintf(name_buffer, "msr%d", msr_num);
-                        else
-                                sprintf(name_buffer, "MSR%d", msr_num);
-                } else if (format == FORMAT_DELTA) {
-                        if (width == 32)
-                                sprintf(name_buffer, "cnt%d", msr_num);
-                        else
-                                sprintf(name_buffer, "CNT%d", msr_num);
-                } else if (format == FORMAT_PERCENT) {
-                        if (width == 32)
-                                sprintf(name_buffer, "msr%d%%", msr_num);
-                        else
-                                sprintf(name_buffer, "MSR%d%%", msr_num);
-                }
+                if (width == 32)
+                        sprintf(name_buffer, "M0x%x%s", msr_num, format == FORMAT_PERCENT ? "%" : "");
+                else
+                        sprintf(name_buffer, "M0X%x%s", msr_num, format == FORMAT_PERCENT ? "%" : "");
         }
 
-        if (add_counter(msr_num, name_buffer, width, scope, type, format))
+        if (add_counter(msr_num, path, name_buffer, width, scope, type, format, 0))
                 fail++;
 
         if (fail) {
@@ -4029,20 +4746,214 @@ next:
                 exit(1);
         }
 }
+
+int is_deferred_skip(char *name)
+{
+        int i;
+
+        for (i = 0; i < deferred_skip_index; ++i)
+                if (!strcmp(name, deferred_skip_names[i]))
+                        return 1;
+        return 0;
+}
+
+void probe_sysfs(void)
+{
+        char path[64];
+        char name_buf[16];
+        FILE *input;
+        int state;
+        char *sp;
+
+        if (!DO_BIC(BIC_sysfs))
+                return;
+
+        for (state = 10; state > 0; --state) {
+
+                sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name",
+                        base_cpu, state);
+                input = fopen(path, "r");
+                if (input == NULL)
+                        continue;
+                fgets(name_buf, sizeof(name_buf), input);
+
+                 /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
+                sp = strchr(name_buf, '-');
+                if (!sp)
+                        sp = strchrnul(name_buf, '\n');
+                *sp = '%';
+                *(sp + 1) = '\0';
+
+                fclose(input);
+
+                sprintf(path, "cpuidle/state%d/time", state);
+
+                if (is_deferred_skip(name_buf))
+                        continue;
+
+                add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_USEC,
+                                FORMAT_PERCENT, SYSFS_PERCPU);
+        }
+
+        for (state = 10; state > 0; --state) {
+
+                sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name",
+                        base_cpu, state);
+                input = fopen(path, "r");
+                if (input == NULL)
+                        continue;
+                fgets(name_buf, sizeof(name_buf), input);
+                 /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
+                sp = strchr(name_buf, '-');
+                if (!sp)
+                        sp = strchrnul(name_buf, '\n');
+                *sp = '\0';
+                fclose(input);
+
+                sprintf(path, "cpuidle/state%d/usage", state);
+
+                if (is_deferred_skip(name_buf))
+                        continue;
+
+                add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS,
+                                FORMAT_DELTA, SYSFS_PERCPU);
+        }
+
+}
+
+
+/*
+ * parse cpuset with following syntax
+ * 1,2,4..6,8-10 and set bits in cpu_subset
+ */
+void parse_cpu_command(char *optarg)
+{
+        unsigned int start, end;
+        char *next;
+
+        if (!strcmp(optarg, "core")) {
+                if (cpu_subset)
+                        goto error;
+                show_core_only++;
+                return;
+        }
+        if (!strcmp(optarg, "package")) {
+                if (cpu_subset)
+                        goto error;
+                show_pkg_only++;
+                return;
+        }
+        if (show_core_only || show_pkg_only)
+                goto error;
+
+        cpu_subset = CPU_ALLOC(CPU_SUBSET_MAXCPUS);
+        if (cpu_subset == NULL)
+                err(3, "CPU_ALLOC");
+        cpu_subset_size = CPU_ALLOC_SIZE(CPU_SUBSET_MAXCPUS);
+
+        CPU_ZERO_S(cpu_subset_size, cpu_subset);
+
+        next = optarg;
+
+        while (next && *next) {
+
+                if (*next == '-')       /* no negative cpu numbers */
+                        goto error;
+
+                start = strtoul(next, &next, 10);
+
+                if (start >= CPU_SUBSET_MAXCPUS)
+                        goto error;
+                CPU_SET_S(start, cpu_subset_size, cpu_subset);
+
+                if (*next == '\0')
+                        break;
+
+                if (*next == ',') {
+                        next += 1;
+                        continue;
+                }
+
+                if (*next == '-') {
+                        next += 1;      /* start range */
+                } else if (*next == '.') {
+                        next += 1;
+                        if (*next == '.')
+                                next += 1;      /* start range */
+                        else
+                                goto error;
+                }
+
+                end = strtoul(next, &next, 10);
+                if (end <= start)
+                        goto error;
+
+                while (++start <= end) {
+                        if (start >= CPU_SUBSET_MAXCPUS)
+                                goto error;
+                        CPU_SET_S(start, cpu_subset_size, cpu_subset);
+                }
+
+                if (*next == ',')
+                        next += 1;
+                else if (*next != '\0')
+                        goto error;
+        }
+
+        return;
+
+error:
+        fprintf(stderr, "\"--cpu %s\" malformed\n", optarg);
+        help();
+        exit(-1);
+}
+
+int shown;
+/*
+ * parse_show_hide() - process cmdline to set default counter action
+ */
+void parse_show_hide(char *optarg, enum show_hide_mode new_mode)
+{
+        /*
+         * --show: show only those specified
+         *  The 1st invocation will clear and replace the enabled mask
+         *  subsequent invocations can add to it.
+         */
+        if (new_mode == SHOW_LIST) {
+                if (shown == 0)
+                        bic_enabled = bic_lookup(optarg, new_mode);
+                else
+                        bic_enabled |= bic_lookup(optarg, new_mode);
+                shown = 1;
+
+                return;
+        }
+
+        /*
+         * --hide: do not show those specified
+         *  multiple invocations simply clear more bits in enabled mask
+         */
+        bic_enabled &= ~bic_lookup(optarg, new_mode);
+
+}
+
 void cmdline(int argc, char **argv)
 {
         int opt;
         int option_index = 0;
         static struct option long_options[] = {
                 {"add",         required_argument,      0, 'a'},
+                {"cpu",         required_argument,      0, 'c'},
                 {"Dump",        no_argument,            0, 'D'},
-                {"debug",       no_argument,            0, 'd'},
+                {"debug",       no_argument,            0, 'd'},        /* internal, not documented */
                 {"interval",    required_argument,      0, 'i'},
                 {"help",        no_argument,            0, 'h'},
+                {"hide",        required_argument,      0, 'H'},        // meh, -h taken by --help
                 {"Joules",      no_argument,            0, 'J'},
+                {"list",        no_argument,            0, 'l'},
                 {"out",         required_argument,      0, 'o'},
-                {"Package",     no_argument,            0, 'p'},
-                {"processor",   no_argument,            0, 'p'},
+                {"quiet",       no_argument,            0, 'q'},
+                {"show",        required_argument,      0, 's'},
                 {"Summary",     no_argument,            0, 'S'},
                 {"TCC",         required_argument,      0, 'T'},
                 {"version",     no_argument,            0, 'v' },
@@ -4051,18 +4962,24 @@ void cmdline(int argc, char **argv)
 
         progname = argv[0];
 
-        while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:PpST:v",
+        while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:qST:v",
                                 long_options, &option_index)) != -1) {
                 switch (opt) {
                 case 'a':
                         parse_add_command(optarg);
                         break;
+                case 'c':
+                        parse_cpu_command(optarg);
+                        break;
                 case 'D':
                         dump_only++;
                         break;
                 case 'd':
                         debug++;
                         break;
+                case 'H':
+                        parse_show_hide(optarg, HIDE_LIST);
+                        break;
                 case 'h':
                 default:
                         help();
@@ -4084,14 +5001,18 @@ void cmdline(int argc, char **argv)
                 case 'J':
                         rapl_joules++;
                         break;
+                case 'l':
+                        list_header_only++;
+                        quiet++;
+                        break;
                 case 'o':
                         outf = fopen_or_die(optarg, "w");
                         break;
-                case 'P':
-                        show_pkg_only++;
+                case 'q':
+                        quiet = 1;
                         break;
-                case 'p':
-                        show_core_only++;
+                case 's':
+                        parse_show_hide(optarg, SHOW_LIST);
                         break;
                 case 'S':
                         summary_only++;
@@ -4113,15 +5034,24 @@ int main(int argc, char **argv)
 
         cmdline(argc, argv);
 
-        if (debug)
+        if (!quiet)
                 print_version();
 
+        probe_sysfs();
+
         turbostat_init();
 
         /* dump counters and exit */
         if (dump_only)
                 return get_and_dump_counters();
 
+        /* list header and exit */
+        if (list_header_only) {
+                print_header(",");
+                flush_output_stdout();
+                return 0;
+        }
+
         /*
          * if any params left, it must be a command to fork
          */
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index be93ab02b490..0c8b61f8398e 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -179,6 +179,7 @@ my $localversion;
 my $iteration = 0;
 my $successes = 0;
 my $stty_orig;
+my $run_command_status = 0;
 
 my $bisect_good;
 my $bisect_bad;
@@ -1325,26 +1326,44 @@ sub wait_for_monitor;
 
 sub reboot {
     my ($time) = @_;
+    my $powercycle = 0;
 
-    # Make sure everything has been written to disk
-    run_ssh("sync");
+    # test if the machine can be connected to within 5 seconds
+    my $stat = run_ssh("echo check machine status", 5);
+    if (!$stat) {
+        doprint("power cycle\n");
+        $powercycle = 1;
+    }
+
+    if ($powercycle) {
+        run_command "$power_cycle";
 
-    if (defined($time)) {
         start_monitor;
         # flush out current monitor
         # May contain the reboot success line
         wait_for_monitor 1;
-    }
 
-    # try to reboot normally
-    if (run_command $reboot) {
-        if (defined($powercycle_after_reboot)) {
-            sleep $powercycle_after_reboot;
+    } else {
+        # Make sure everything has been written to disk
+        run_ssh("sync");
+
+        if (defined($time)) {
+            start_monitor;
+            # flush out current monitor
+            # May contain the reboot success line
+            wait_for_monitor 1;
+        }
+
+        # try to reboot normally
+        if (run_command $reboot) {
+            if (defined($powercycle_after_reboot)) {
+                sleep $powercycle_after_reboot;
+                run_command "$power_cycle";
+            }
+        } else {
+            # nope? power cycle it.
             run_command "$power_cycle";
         }
-    } else {
-        # nope? power cycle it.
-        run_command "$power_cycle";
     }
 
     if (defined($time)) {
@@ -1412,6 +1431,10 @@ sub dodie {
             system("stty $stty_orig");
     }
 
+    if (defined($post_test)) {
+        run_command $post_test;
+    }
+
     die @_, "\n";
 }
 
@@ -1624,10 +1647,6 @@ sub save_logs {
 
 sub fail {
 
-        if (defined($post_test)) {
-                run_command $post_test;
-        }
-
         if ($die_on_failure) {
                 dodie @_;
         }
@@ -1660,23 +1679,26 @@ sub fail {
             save_logs "fail", $store_failures;
         }
 
+        if (defined($post_test)) {
+                run_command $post_test;
+        }
+
         return 1;
 }
 
 sub run_command {
-    my ($command, $redirect) = @_;
+    my ($command, $redirect, $timeout) = @_;
     my $start_time;
     my $end_time;
     my $dolog = 0;
     my $dord = 0;
     my $pid;
 
-    $start_time = time;
-
     $command =~ s/\$SSH_USER/$ssh_user/g;
     $command =~ s/\$MACHINE/$machine/g;
 
     doprint("$command ... ");
+    $start_time = time;
 
     $pid = open(CMD, "$command 2>&1 |") or
         (fail "unable to exec $command" and return 0);
@@ -1693,13 +1715,30 @@ sub run_command {
         $dord = 1;
     }
 
-    while (<CMD>) {
-        print LOG if ($dolog);
-        print RD  if ($dord);
+    my $hit_timeout = 0;
+
+    while (1) {
+        my $fp = \*CMD;
+        if (defined($timeout)) {
+            doprint "timeout = $timeout\n";
+        }
+        my $line = wait_for_input($fp, $timeout);
+        if (!defined($line)) {
+            my $now = time;
+            if (defined($timeout) && (($now - $start_time) >= $timeout)) {
+                doprint "Hit timeout of $timeout, killing process\n";
+                $hit_timeout = 1;
+                kill 9, $pid;
+            }
+            last;
+        }
+        print LOG $line if ($dolog);
+        print RD $line if ($dord);
     }
 
     waitpid($pid, 0);
-    my $failed = $?;
+    # shift 8 for real exit status
+    $run_command_status = $? >> 8;
 
     close(CMD);
     close(LOG) if ($dolog);
@@ -1714,21 +1753,25 @@ sub run_command {
         doprint "[$delta seconds] ";
     }
 
-    if ($failed) {
+    if ($hit_timeout) {
+        $run_command_status = 1;
+    }
+
+    if ($run_command_status) {
         doprint "FAILED!\n";
     } else {
         doprint "SUCCESS\n";
     }
 
-    return !$failed;
+    return !$run_command_status;
 }
 
 sub run_ssh {
-    my ($cmd) = @_;
+    my ($cmd, $timeout) = @_;
     my $cp_exec = $ssh_exec;
 
     $cp_exec =~ s/\$SSH_COMMAND/$cmd/g;
-    return run_command "$cp_exec";
+    return run_command "$cp_exec", undef , $timeout;
 }
 
 sub run_scp {
@@ -1837,6 +1880,7 @@ sub get_grub_index {
 sub wait_for_input
 {
     my ($fp, $time) = @_;
+    my $start_time;
     my $rin;
     my $rout;
     my $nr;
@@ -1852,17 +1896,22 @@ sub wait_for_input
     vec($rin, fileno($fp), 1) = 1;
     vec($rin, fileno(\*STDIN), 1) = 1;
 
+    $start_time = time;
+
     while (1) {
         $nr = select($rout=$rin, undef, undef, $time);
 
-        if ($nr <= 0) {
-            return undef;
-        }
+        last if ($nr <= 0);
 
         # copy data from stdin to the console
         if (vec($rout, fileno(\*STDIN), 1) == 1) {
-            sysread(\*STDIN, $buf, 1000);
-            syswrite($fp, $buf, 1000);
+            $nr = sysread(\*STDIN, $buf, 1000);
+            syswrite($fp, $buf, $nr) if ($nr > 0);
+        }
+
+        # The timeout is based on time waiting for the fp data
+        if (vec($rout, fileno($fp), 1) != 1) {
+            last if (defined($time) && (time - $start_time > $time));
             next;
         }
 
@@ -1874,12 +1923,11 @@ sub wait_for_input
             last if ($ch eq "\n");
         }
 
-        if (!length($line)) {
-            return undef;
-        }
+        last if (!length($line));
 
         return $line;
     }
+    return undef;
 }
 
 sub reboot_to {
@@ -2489,10 +2537,6 @@ sub halt {
 sub success {
     my ($i) = @_;
 
-    if (defined($post_test)) {
-        run_command $post_test;
-    }
-
     $successes++;
 
     my $name = "";
@@ -2517,6 +2561,10 @@ sub success {
         doprint "Reboot and wait $sleep_time seconds\n";
         reboot_to_good $sleep_time;
     }
+
+    if (defined($post_test)) {
+        run_command $post_test;
+    }
 }
 
 sub answer_bisect {
@@ -2537,16 +2585,15 @@ sub answer_bisect {
 }
 
 sub child_run_test {
-    my $failed = 0;
 
     # child should have no power
     $reboot_on_error = 0;
     $poweroff_on_error = 0;
     $die_on_failure = 1;
 
-    run_command $run_test, $testlog or $failed = 1;
+    run_command $run_test, $testlog;
 
-    exit $failed;
+    exit $run_command_status;
 }
 
 my $child_done;
@@ -2629,7 +2676,7 @@ sub do_run_test {
     }
 
     waitpid $child_pid, 0;
-    $child_exit = $?;
+    $child_exit = $? >> 8;
 
     my $end_time = time;
     $test_time = $end_time - $start_time;
@@ -3330,7 +3377,6 @@ sub config_bisect {
     save_config \%good_configs, $good_config;
     save_config \%bad_configs, $bad_config;
 
-
     if (defined($config_bisect_check) && $config_bisect_check ne "0") {
         if ($config_bisect_check ne "good") {
             doprint "Testing bad config\n";
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 45be8b55a663..798f17655433 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -887,7 +887,7 @@ static void nfit_test0_setup(struct nfit_test *t)
         memdev->range_index = 0+1;
         memdev->region_index = 4+1;
         memdev->region_size = SPA0_SIZE/2;
-        memdev->region_offset = t->spa_set_dma[0];
+        memdev->region_offset = 1;
         memdev->address = 0;
         memdev->interleave_index = 0;
         memdev->interleave_ways = 2;
@@ -902,7 +902,7 @@ static void nfit_test0_setup(struct nfit_test *t)
         memdev->range_index = 0+1;
         memdev->region_index = 5+1;
         memdev->region_size = SPA0_SIZE/2;
-        memdev->region_offset = t->spa_set_dma[0] + SPA0_SIZE/2;
+        memdev->region_offset = (1 << 8);
         memdev->address = 0;
         memdev->interleave_index = 0;
         memdev->interleave_ways = 2;
@@ -917,7 +917,7 @@ static void nfit_test0_setup(struct nfit_test *t)
         memdev->range_index = 1+1;
         memdev->region_index = 4+1;
         memdev->region_size = SPA1_SIZE/4;
-        memdev->region_offset = t->spa_set_dma[1];
+        memdev->region_offset = (1 << 16);
         memdev->address = SPA0_SIZE/2;
         memdev->interleave_index = 0;
         memdev->interleave_ways = 4;
@@ -932,7 +932,7 @@ static void nfit_test0_setup(struct nfit_test *t)
         memdev->range_index = 1+1;
         memdev->region_index = 5+1;
         memdev->region_size = SPA1_SIZE/4;
-        memdev->region_offset = t->spa_set_dma[1] + SPA1_SIZE/4;
+        memdev->region_offset = (1 << 24);
         memdev->address = SPA0_SIZE/2;
         memdev->interleave_index = 0;
         memdev->interleave_ways = 4;
@@ -947,7 +947,7 @@ static void nfit_test0_setup(struct nfit_test *t)
         memdev->range_index = 1+1;
         memdev->region_index = 6+1;
         memdev->region_size = SPA1_SIZE/4;
-        memdev->region_offset = t->spa_set_dma[1] + 2*SPA1_SIZE/4;
+        memdev->region_offset = (1ULL << 32);
         memdev->address = SPA0_SIZE/2;
         memdev->interleave_index = 0;
         memdev->interleave_ways = 4;
@@ -962,7 +962,7 @@ static void nfit_test0_setup(struct nfit_test *t)
         memdev->range_index = 1+1;
         memdev->region_index = 7+1;
         memdev->region_size = SPA1_SIZE/4;
-        memdev->region_offset = t->spa_set_dma[1] + 3*SPA1_SIZE/4;
+        memdev->region_offset = (1ULL << 40);
         memdev->address = SPA0_SIZE/2;
         memdev->interleave_index = 0;
         memdev->interleave_ways = 4;
@@ -1380,7 +1380,7 @@ static void nfit_test0_setup(struct nfit_test *t)
                 memdev->range_index = 11+1;
                 memdev->region_index = 9+1;
                 memdev->region_size = SPA0_SIZE;
-                memdev->region_offset = t->spa_set_dma[2];
+                memdev->region_offset = (1ULL << 48);
                 memdev->address = 0;
                 memdev->interleave_index = 0;
                 memdev->interleave_ways = 1;
diff --git a/tools/testing/radix-tree/.gitignore b/tools/testing/radix-tree/.gitignore
index 11d888ca6a92..d4706c0ffceb 100644
--- a/tools/testing/radix-tree/.gitignore
+++ b/tools/testing/radix-tree/.gitignore
@@ -1,2 +1,6 @@
+generated/map-shift.h
+idr.c
+idr-test
 main
+multiorder
 radix-tree.c
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index 3635e4d3eca7..6a9480c03cbd 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -1,29 +1,50 @@
 
-CFLAGS += -I. -I../../include -g -O2 -Wall -D_LGPL_SOURCE
-LDFLAGS += -lpthread -lurcu
-TARGETS = main
-OFILES = main.o radix-tree.o linux.o test.o tag_check.o find_next_bit.o \
-         regression1.o regression2.o regression3.o multiorder.o \
-         iteration_check.o benchmark.o
-
-ifdef BENCHMARK
-        CFLAGS += -DBENCHMARK=1
+CFLAGS += -I. -I../../include -g -O2 -Wall -D_LGPL_SOURCE -fsanitize=address
+LDFLAGS += -fsanitize=address
+LDLIBS+= -lpthread -lurcu
+TARGETS = main idr-test multiorder
+CORE_OFILES := radix-tree.o idr.o linux.o test.o find_bit.o
+OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \
+         tag_check.o multiorder.o idr-test.o iteration_check.o benchmark.o
+
+ifndef SHIFT
+        SHIFT=3
 endif
 
-targets: $(TARGETS)
+ifeq ($(BUILD), 32)
+        CFLAGS += -m32
+        LDFLAGS += -m32
+endif
+
+targets: mapshift $(TARGETS)
 
 main:   $(OFILES)
-        $(CC) $(CFLAGS) $(LDFLAGS) $(OFILES) -o main
+
+idr-test: idr-test.o $(CORE_OFILES)
+
+multiorder: multiorder.o $(CORE_OFILES)
 
 clean:
-        $(RM) -f $(TARGETS) *.o radix-tree.c
+        $(RM) $(TARGETS) *.o radix-tree.c idr.c generated/map-shift.h
 
-find_next_bit.o: ../../lib/find_bit.c
-        $(CC) $(CFLAGS) -c -o $@ $<
+vpath %.c ../../lib
 
-$(OFILES): *.h */*.h \
+$(OFILES): Makefile *.h */*.h generated/map-shift.h \
         ../../include/linux/*.h \
-        ../../../include/linux/radix-tree.h
+        ../../include/asm/*.h \
+        ../../../include/linux/radix-tree.h \
+        ../../../include/linux/idr.h
 
 radix-tree.c: ../../../lib/radix-tree.c
         sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@
+
+idr.c: ../../../lib/idr.c
+        sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@
+
+.PHONY: mapshift
+
+mapshift:
+        @if ! grep -qws $(SHIFT) generated/map-shift.h; then            \
+                echo "#define RADIX_TREE_MAP_SHIFT $(SHIFT)" >          \
+                                generated/map-shift.h;                  \
+        fi
diff --git a/tools/testing/radix-tree/benchmark.c b/tools/testing/radix-tree/benchmark.c
index 215ca86c7605..99c40f3ed133 100644
--- a/tools/testing/radix-tree/benchmark.c
+++ b/tools/testing/radix-tree/benchmark.c
@@ -17,6 +17,9 @@
 #include <time.h>
 #include "test.h"
 
+#define for_each_index(i, base, order) \
+                for (i = base; i < base + (1 << order); i++)
+
 #define NSEC_PER_SEC    1000000000L
 
 static long long benchmark_iter(struct radix_tree_root *root, bool tagged)
@@ -57,27 +60,176 @@ again:
         return nsec;
 }
 
+static void benchmark_insert(struct radix_tree_root *root,
+                             unsigned long size, unsigned long step, int order)
+{
+        struct timespec start, finish;
+        unsigned long index;
+        long long nsec;
+
+        clock_gettime(CLOCK_MONOTONIC, &start);
+
+        for (index = 0 ; index < size ; index += step)
+                item_insert_order(root, index, order);
+
+        clock_gettime(CLOCK_MONOTONIC, &finish);
+
+        nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+               (finish.tv_nsec - start.tv_nsec);
+
+        printv(2, "Size: %8ld, step: %8ld, order: %d, insertion: %15lld ns\n",
+                size, step, order, nsec);
+}
+
+static void benchmark_tagging(struct radix_tree_root *root,
+                             unsigned long size, unsigned long step, int order)
+{
+        struct timespec start, finish;
+        unsigned long index;
+        long long nsec;
+
+        clock_gettime(CLOCK_MONOTONIC, &start);
+
+        for (index = 0 ; index < size ; index += step)
+                radix_tree_tag_set(root, index, 0);
+
+        clock_gettime(CLOCK_MONOTONIC, &finish);
+
+        nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+               (finish.tv_nsec - start.tv_nsec);
+
+        printv(2, "Size: %8ld, step: %8ld, order: %d, tagging: %17lld ns\n",
+                size, step, order, nsec);
+}
+
+static void benchmark_delete(struct radix_tree_root *root,
+                             unsigned long size, unsigned long step, int order)
+{
+        struct timespec start, finish;
+        unsigned long index, i;
+        long long nsec;
+
+        clock_gettime(CLOCK_MONOTONIC, &start);
+
+        for (index = 0 ; index < size ; index += step)
+                for_each_index(i, index, order)
+                        item_delete(root, i);
+
+        clock_gettime(CLOCK_MONOTONIC, &finish);
+
+        nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+               (finish.tv_nsec - start.tv_nsec);
+
+        printv(2, "Size: %8ld, step: %8ld, order: %d, deletion: %16lld ns\n",
+                size, step, order, nsec);
+}
+
 static void benchmark_size(unsigned long size, unsigned long step, int order)
 {
         RADIX_TREE(tree, GFP_KERNEL);
         long long normal, tagged;
-        unsigned long index;
 
-        for (index = 0 ; index < size ; index += step) {
-                item_insert_order(&tree, index, order);
-                radix_tree_tag_set(&tree, index, 0);
-        }
+        benchmark_insert(&tree, size, step, order);
+        benchmark_tagging(&tree, size, step, order);
 
         tagged = benchmark_iter(&tree, true);
         normal = benchmark_iter(&tree, false);
 
-        printf("Size %ld, step %6ld, order %d tagged %10lld ns, normal %10lld ns\n",
-                size, step, order, tagged, normal);
+        printv(2, "Size: %8ld, step: %8ld, order: %d, tagged iteration: %8lld ns\n",
+                size, step, order, tagged);
+        printv(2, "Size: %8ld, step: %8ld, order: %d, normal iteration: %8lld ns\n",
+                size, step, order, normal);
+
+        benchmark_delete(&tree, size, step, order);
 
         item_kill_tree(&tree);
         rcu_barrier();
 }
 
+static long long  __benchmark_split(unsigned long index,
+                                    int old_order, int new_order)
+{
+        struct timespec start, finish;
+        long long nsec;
+        RADIX_TREE(tree, GFP_ATOMIC);
+
+        item_insert_order(&tree, index, old_order);
+
+        clock_gettime(CLOCK_MONOTONIC, &start);
+        radix_tree_split(&tree, index, new_order);
+        clock_gettime(CLOCK_MONOTONIC, &finish);
+        nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+               (finish.tv_nsec - start.tv_nsec);
+
+        item_kill_tree(&tree);
+
+        return nsec;
+
+}
+
+static void benchmark_split(unsigned long size, unsigned long step)
+{
+        int i, j, idx;
+        long long nsec = 0;
+
+
+        for (idx = 0; idx < size; idx += step) {
+                for (i = 3; i < 11; i++) {
+                        for (j = 0; j < i; j++) {
+                                nsec += __benchmark_split(idx, i, j);
+                        }
+                }
+        }
+
+        printv(2, "Size %8ld, step %8ld, split time %10lld ns\n",
+                        size, step, nsec);
+
+}
+
+static long long  __benchmark_join(unsigned long index,
+                             unsigned order1, unsigned order2)
+{
+        unsigned long loc;
+        struct timespec start, finish;
+        long long nsec;
+        void *item, *item2 = item_create(index + 1, order1);
+        RADIX_TREE(tree, GFP_KERNEL);
+
+        item_insert_order(&tree, index, order2);
+        item = radix_tree_lookup(&tree, index);
+
+        clock_gettime(CLOCK_MONOTONIC, &start);
+        radix_tree_join(&tree, index + 1, order1, item2);
+        clock_gettime(CLOCK_MONOTONIC, &finish);
+        nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+                (finish.tv_nsec - start.tv_nsec);
+
+        loc = find_item(&tree, item);
+        if (loc == -1)
+                free(item);
+
+        item_kill_tree(&tree);
+
+        return nsec;
+}
+
+static void benchmark_join(unsigned long step)
+{
+        int i, j, idx;
+        long long nsec = 0;
+
+        for (idx = 0; idx < 1 << 10; idx += step) {
+                for (i = 1; i < 15; i++) {
+                        for (j = 0; j < i; j++) {
+                                nsec += __benchmark_join(idx, i, j);
+                        }
+                }
+        }
+
+        printv(2, "Size %8d, step %8ld, join time %10lld ns\n",
+                        1 << 10, step, nsec);
+}
+
 void benchmark(void)
 {
         unsigned long size[] = {1 << 10, 1 << 20, 0};
@@ -85,8 +237,8 @@ void benchmark(void)
                                 128, 256, 512, 12345, 0};
         int c, s;
 
-        printf("starting benchmarks\n");
-        printf("RADIX_TREE_MAP_SHIFT = %d\n", RADIX_TREE_MAP_SHIFT);
+        printv(1, "starting benchmarks\n");
+        printv(1, "RADIX_TREE_MAP_SHIFT = %d\n", RADIX_TREE_MAP_SHIFT);
 
         for (c = 0; size[c]; c++)
                 for (s = 0; step[s]; s++)
@@ -95,4 +247,11 @@ void benchmark(void)
         for (c = 0; size[c]; c++)
                 for (s = 0; step[s]; s++)
                         benchmark_size(size[c], step[s] << 9, 9);
+
+        for (c = 0; size[c]; c++)
+                for (s = 0; step[s]; s++)
+                        benchmark_split(size[c], step[s]);
+
+        for (s = 0; step[s]; s++)
+                benchmark_join(step[s]);
 }
diff --git a/tools/testing/radix-tree/generated/autoconf.h b/tools/testing/radix-tree/generated/autoconf.h
index ad18cf5a2a3a..cf88dc5b8832 100644
--- a/tools/testing/radix-tree/generated/autoconf.h
+++ b/tools/testing/radix-tree/generated/autoconf.h
@@ -1,3 +1 @@
 #define CONFIG_RADIX_TREE_MULTIORDER 1
-#define CONFIG_SHMEM 1
-#define CONFIG_SWAP 1
diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
new file mode 100644
index 000000000000..30cd0b296f1a
--- /dev/null
+++ b/tools/testing/radix-tree/idr-test.c
@@ -0,0 +1,516 @@
+/*
+ * idr-test.c: Test the IDR API
+ * Copyright (c) 2016 Matthew Wilcox <willy@infradead.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#include <linux/bitmap.h>
+#include <linux/idr.h>
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+
+#include "test.h"
+
+#define DUMMY_PTR       ((void *)0x12)
+
+int item_idr_free(int id, void *p, void *data)
+{
+        struct item *item = p;
+        assert(item->index == id);
+        free(p);
+
+        return 0;
+}
+
+void item_idr_remove(struct idr *idr, int id)
+{
+        struct item *item = idr_find(idr, id);
+        assert(item->index == id);
+        idr_remove(idr, id);
+        free(item);
+}
+
+void idr_alloc_test(void)
+{
+        unsigned long i;
+        DEFINE_IDR(idr);
+
+        assert(idr_alloc_cyclic(&idr, DUMMY_PTR, 0, 0x4000, GFP_KERNEL) == 0);
+        assert(idr_alloc_cyclic(&idr, DUMMY_PTR, 0x3ffd, 0x4000, GFP_KERNEL) == 0x3ffd);
+        idr_remove(&idr, 0x3ffd);
+        idr_remove(&idr, 0);
+
+        for (i = 0x3ffe; i < 0x4003; i++) {
+                int id;
+                struct item *item;
+
+                if (i < 0x4000)
+                        item = item_create(i, 0);
+                else
+                        item = item_create(i - 0x3fff, 0);
+
+                id = idr_alloc_cyclic(&idr, item, 1, 0x4000, GFP_KERNEL);
+                assert(id == item->index);
+        }
+
+        idr_for_each(&idr, item_idr_free, &idr);
+        idr_destroy(&idr);
+}
+
+void idr_replace_test(void)
+{
+        DEFINE_IDR(idr);
+
+        idr_alloc(&idr, (void *)-1, 10, 11, GFP_KERNEL);
+        idr_replace(&idr, &idr, 10);
+
+        idr_destroy(&idr);
+}
+
+/*
+ * Unlike the radix tree, you can put a NULL pointer -- with care -- into
+ * the IDR.  Some interfaces, like idr_find() do not distinguish between
+ * "present, value is NULL" and "not present", but that's exactly what some
+ * users want.
+ */
+void idr_null_test(void)
+{
+        int i;
+        DEFINE_IDR(idr);
+
+        assert(idr_is_empty(&idr));
+
+        assert(idr_alloc(&idr, NULL, 0, 0, GFP_KERNEL) == 0);
+        assert(!idr_is_empty(&idr));
+        idr_remove(&idr, 0);
+        assert(idr_is_empty(&idr));
+
+        assert(idr_alloc(&idr, NULL, 0, 0, GFP_KERNEL) == 0);
+        assert(!idr_is_empty(&idr));
+        idr_destroy(&idr);
+        assert(idr_is_empty(&idr));
+
+        for (i = 0; i < 10; i++) {
+                assert(idr_alloc(&idr, NULL, 0, 0, GFP_KERNEL) == i);
+        }
+
+        assert(idr_replace(&idr, DUMMY_PTR, 3) == NULL);
+        assert(idr_replace(&idr, DUMMY_PTR, 4) == NULL);
+        assert(idr_replace(&idr, NULL, 4) == DUMMY_PTR);
+        assert(idr_replace(&idr, DUMMY_PTR, 11) == ERR_PTR(-ENOENT));
+        idr_remove(&idr, 5);
+        assert(idr_alloc(&idr, NULL, 0, 0, GFP_KERNEL) == 5);
+        idr_remove(&idr, 5);
+
+        for (i = 0; i < 9; i++) {
+                idr_remove(&idr, i);
+                assert(!idr_is_empty(&idr));
+        }
+        idr_remove(&idr, 8);
+        assert(!idr_is_empty(&idr));
+        idr_remove(&idr, 9);
+        assert(idr_is_empty(&idr));
+
+        assert(idr_alloc(&idr, NULL, 0, 0, GFP_KERNEL) == 0);
+        assert(idr_replace(&idr, DUMMY_PTR, 3) == ERR_PTR(-ENOENT));
+        assert(idr_replace(&idr, DUMMY_PTR, 0) == NULL);
+        assert(idr_replace(&idr, NULL, 0) == DUMMY_PTR);
+
+        idr_destroy(&idr);
+        assert(idr_is_empty(&idr));
+
+        for (i = 1; i < 10; i++) {
+                assert(idr_alloc(&idr, NULL, 1, 0, GFP_KERNEL) == i);
+        }
+
+        idr_destroy(&idr);
+        assert(idr_is_empty(&idr));
+}
+
+void idr_nowait_test(void)
+{
+        unsigned int i;
+        DEFINE_IDR(idr);
+
+        idr_preload(GFP_KERNEL);
+
+        for (i = 0; i < 3; i++) {
+                struct item *item = item_create(i, 0);
+                assert(idr_alloc(&idr, item, i, i + 1, GFP_NOWAIT) == i);
+        }
+
+        idr_preload_end();
+
+        idr_for_each(&idr, item_idr_free, &idr);
+        idr_destroy(&idr);
+}
+
+void idr_get_next_test(void)
+{
+        unsigned long i;
+        int nextid;
+        DEFINE_IDR(idr);
+
+        int indices[] = {4, 7, 9, 15, 65, 128, 1000, 99999, 0};
+
+        for(i = 0; indices[i]; i++) {
+                struct item *item = item_create(indices[i], 0);
+                assert(idr_alloc(&idr, item, indices[i], indices[i+1],
+                                 GFP_KERNEL) == indices[i]);
+        }
+
+        for(i = 0, nextid = 0; indices[i]; i++) {
+                idr_get_next(&idr, &nextid);
+                assert(nextid == indices[i]);
+                nextid++;
+        }
+
+        idr_for_each(&idr, item_idr_free, &idr);
+        idr_destroy(&idr);
+}
+
+void idr_checks(void)
+{
+        unsigned long i;
+        DEFINE_IDR(idr);
+
+        for (i = 0; i < 10000; i++) {
+                struct item *item = item_create(i, 0);
+                assert(idr_alloc(&idr, item, 0, 20000, GFP_KERNEL) == i);
+        }
+
+        assert(idr_alloc(&idr, DUMMY_PTR, 5, 30, GFP_KERNEL) < 0);
+
+        for (i = 0; i < 5000; i++)
+                item_idr_remove(&idr, i);
+
+        idr_remove(&idr, 3);
+
+        idr_for_each(&idr, item_idr_free, &idr);
+        idr_destroy(&idr);
+
+        assert(idr_is_empty(&idr));
+
+        idr_remove(&idr, 3);
+        idr_remove(&idr, 0);
+
+        for (i = INT_MAX - 3UL; i < INT_MAX + 1UL; i++) {
+                struct item *item = item_create(i, 0);
+                assert(idr_alloc(&idr, item, i, i + 10, GFP_KERNEL) == i);
+        }
+        assert(idr_alloc(&idr, DUMMY_PTR, i - 2, i, GFP_KERNEL) == -ENOSPC);
+
+        idr_for_each(&idr, item_idr_free, &idr);
+        idr_destroy(&idr);
+        idr_destroy(&idr);
+
+        assert(idr_is_empty(&idr));
+
+        for (i = 1; i < 10000; i++) {
+                struct item *item = item_create(i, 0);
+                assert(idr_alloc(&idr, item, 1, 20000, GFP_KERNEL) == i);
+        }
+
+        idr_for_each(&idr, item_idr_free, &idr);
+        idr_destroy(&idr);
+
+        idr_replace_test();
+        idr_alloc_test();
+        idr_null_test();
+        idr_nowait_test();
+        idr_get_next_test();
+}
+
+/*
+ * Check that we get the correct error when we run out of memory doing
+ * allocations.  To ensure we run out of memory, just "forget" to preload.
+ * The first test is for not having a bitmap available, and the second test
+ * is for not being able to allocate a level of the radix tree.
+ */
+void ida_check_nomem(void)
+{
+        DEFINE_IDA(ida);
+        int id, err;
+
+        err = ida_get_new_above(&ida, 256, &id);
+        assert(err == -EAGAIN);
+        err = ida_get_new_above(&ida, 1UL << 30, &id);
+        assert(err == -EAGAIN);
+}
+
+/*
+ * Check what happens when we fill a leaf and then delete it.  This may
+ * discover mishandling of IDR_FREE.
+ */
+void ida_check_leaf(void)
+{
+        DEFINE_IDA(ida);
+        int id;
+        unsigned long i;
+
+        for (i = 0; i < IDA_BITMAP_BITS; i++) {
+                assert(ida_pre_get(&ida, GFP_KERNEL));
+                assert(!ida_get_new(&ida, &id));
+                assert(id == i);
+        }
+
+        ida_destroy(&ida);
+        assert(ida_is_empty(&ida));
+
+        assert(ida_pre_get(&ida, GFP_KERNEL));
+        assert(!ida_get_new(&ida, &id));
+        assert(id == 0);
+        ida_destroy(&ida);
+        assert(ida_is_empty(&ida));
+}
+
+/*
+ * Check handling of conversions between exceptional entries and full bitmaps.
+ */
+void ida_check_conv(void)
+{
+        DEFINE_IDA(ida);
+        int id;
+        unsigned long i;
+
+        for (i = 0; i < IDA_BITMAP_BITS * 2; i += IDA_BITMAP_BITS) {
+                assert(ida_pre_get(&ida, GFP_KERNEL));
+                assert(!ida_get_new_above(&ida, i + 1, &id));
+                assert(id == i + 1);
+                assert(!ida_get_new_above(&ida, i + BITS_PER_LONG, &id));
+                assert(id == i + BITS_PER_LONG);
+                ida_remove(&ida, i + 1);
+                ida_remove(&ida, i + BITS_PER_LONG);
+                assert(ida_is_empty(&ida));
+        }
+
+        assert(ida_pre_get(&ida, GFP_KERNEL));
+
+        for (i = 0; i < IDA_BITMAP_BITS * 2; i++) {
+                assert(ida_pre_get(&ida, GFP_KERNEL));
+                assert(!ida_get_new(&ida, &id));
+                assert(id == i);
+        }
+
+        for (i = IDA_BITMAP_BITS * 2; i > 0; i--) {
+                ida_remove(&ida, i - 1);
+        }
+        assert(ida_is_empty(&ida));
+
+        for (i = 0; i < IDA_BITMAP_BITS + BITS_PER_LONG - 4; i++) {
+                assert(ida_pre_get(&ida, GFP_KERNEL));
+                assert(!ida_get_new(&ida, &id));
+                assert(id == i);
+        }
+
+        for (i = IDA_BITMAP_BITS + BITS_PER_LONG - 4; i > 0; i--) {
+                ida_remove(&ida, i - 1);
+        }
+        assert(ida_is_empty(&ida));
+
+        radix_tree_cpu_dead(1);
+        for (i = 0; i < 1000000; i++) {
+                int err = ida_get_new(&ida, &id);
+                if (err == -EAGAIN) {
+                        assert((i % IDA_BITMAP_BITS) == (BITS_PER_LONG - 2));
+                        assert(ida_pre_get(&ida, GFP_KERNEL));
+                        err = ida_get_new(&ida, &id);
+                } else {
+                        assert((i % IDA_BITMAP_BITS) != (BITS_PER_LONG - 2));
+                }
+                assert(!err);
+                assert(id == i);
+        }
+        ida_destroy(&ida);
+}
+
+/*
+ * Check allocations up to and slightly above the maximum allowed (2^31-1) ID.
+ * Allocating up to 2^31-1 should succeed, and then allocating the next one
+ * should fail.
+ */
+void ida_check_max(void)
+{
+        DEFINE_IDA(ida);
+        int id, err;
+        unsigned long i, j;
+
+        for (j = 1; j < 65537; j *= 2) {
+                unsigned long base = (1UL << 31) - j;
+                for (i = 0; i < j; i++) {
+                        assert(ida_pre_get(&ida, GFP_KERNEL));
+                        assert(!ida_get_new_above(&ida, base, &id));
+                        assert(id == base + i);
+                }
+                assert(ida_pre_get(&ida, GFP_KERNEL));
+                err = ida_get_new_above(&ida, base, &id);
+                assert(err == -ENOSPC);
+                ida_destroy(&ida);
+                assert(ida_is_empty(&ida));
+                rcu_barrier();
+        }
+}
+
+void ida_check_random(void)
+{
+        DEFINE_IDA(ida);
+        DECLARE_BITMAP(bitmap, 2048);
+        int id, err;
+        unsigned int i;
+        time_t s = time(NULL);
+
+ repeat:
+        memset(bitmap, 0, sizeof(bitmap));
+        for (i = 0; i < 100000; i++) {
+                int i = rand();
+                int bit = i & 2047;
+                if (test_bit(bit, bitmap)) {
+                        __clear_bit(bit, bitmap);
+                        ida_remove(&ida, bit);
+                } else {
+                        __set_bit(bit, bitmap);
+                        do {
+                                ida_pre_get(&ida, GFP_KERNEL);
+                                err = ida_get_new_above(&ida, bit, &id);
+                        } while (err == -ENOMEM);
+                        assert(!err);
+                        assert(id == bit);
+                }
+        }
+        ida_destroy(&ida);
+        if (time(NULL) < s + 10)
+                goto repeat;
+}
+
+void ida_simple_get_remove_test(void)
+{
+        DEFINE_IDA(ida);
+        unsigned long i;
+
+        for (i = 0; i < 10000; i++) {
+                assert(ida_simple_get(&ida, 0, 20000, GFP_KERNEL) == i);
+        }
+        assert(ida_simple_get(&ida, 5, 30, GFP_KERNEL) < 0);
+
+        for (i = 0; i < 10000; i++) {
+                ida_simple_remove(&ida, i);
+        }
+        assert(ida_is_empty(&ida));
+
+        ida_destroy(&ida);
+}
+
+void ida_checks(void)
+{
+        DEFINE_IDA(ida);
+        int id;
+        unsigned long i;
+
+        radix_tree_cpu_dead(1);
+        ida_check_nomem();
+
+        for (i = 0; i < 10000; i++) {
+                assert(ida_pre_get(&ida, GFP_KERNEL));
+                assert(!ida_get_new(&ida, &id));
+                assert(id == i);
+        }
+
+        ida_remove(&ida, 20);
+        ida_remove(&ida, 21);
+        for (i = 0; i < 3; i++) {
+                assert(ida_pre_get(&ida, GFP_KERNEL));
+                assert(!ida_get_new(&ida, &id));
+                if (i == 2)
+                        assert(id == 10000);
+        }
+
+        for (i = 0; i < 5000; i++)
+                ida_remove(&ida, i);
+
+        assert(ida_pre_get(&ida, GFP_KERNEL));
+        assert(!ida_get_new_above(&ida, 5000, &id));
+        assert(id == 10001);
+
+        ida_destroy(&ida);
+
+        assert(ida_is_empty(&ida));
+
+        assert(ida_pre_get(&ida, GFP_KERNEL));
+        assert(!ida_get_new_above(&ida, 1, &id));
+        assert(id == 1);
+
+        ida_remove(&ida, id);
+        assert(ida_is_empty(&ida));
+        ida_destroy(&ida);
+        assert(ida_is_empty(&ida));
+
+        assert(ida_pre_get(&ida, GFP_KERNEL));
+        assert(!ida_get_new_above(&ida, 1, &id));
+        ida_destroy(&ida);
+        assert(ida_is_empty(&ida));
+
+        assert(ida_pre_get(&ida, GFP_KERNEL));
+        assert(!ida_get_new_above(&ida, 1, &id));
+        assert(id == 1);
+        assert(ida_pre_get(&ida, GFP_KERNEL));
+        assert(!ida_get_new_above(&ida, 1025, &id));
+        assert(id == 1025);
+        assert(ida_pre_get(&ida, GFP_KERNEL));
+        assert(!ida_get_new_above(&ida, 10000, &id));
+        assert(id == 10000);
+        ida_remove(&ida, 1025);
+        ida_destroy(&ida);
+        assert(ida_is_empty(&ida));
+
+        ida_check_leaf();
+        ida_check_max();
+        ida_check_conv();
+        ida_check_random();
+        ida_simple_get_remove_test();
+
+        radix_tree_cpu_dead(1);
+}
+
+static void *ida_random_fn(void *arg)
+{
+        rcu_register_thread();
+        ida_check_random();
+        rcu_unregister_thread();
+        return NULL;
+}
+
+void ida_thread_tests(void)
+{
+        pthread_t threads[10];
+        int i;
+
+        for (i = 0; i < ARRAY_SIZE(threads); i++)
+                if (pthread_create(&threads[i], NULL, ida_random_fn, NULL)) {
+                        perror("creating ida thread");
+                        exit(1);
+                }
+
+        while (i--)
+                pthread_join(threads[i], NULL);
+}
+
+int __weak main(void)
+{
+        radix_tree_init();
+        idr_checks();
+        ida_checks();
+        ida_thread_tests();
+        radix_tree_cpu_dead(1);
+        rcu_barrier();
+        if (nr_allocated)
+                printf("nr_allocated = %d\n", nr_allocated);
+        return 0;
+}
diff --git a/tools/testing/radix-tree/iteration_check.c b/tools/testing/radix-tree/iteration_check.c
index 7572b7ed930e..a92bab513701 100644
--- a/tools/testing/radix-tree/iteration_check.c
+++ b/tools/testing/radix-tree/iteration_check.c
@@ -177,7 +177,7 @@ void iteration_test(unsigned order, unsigned test_duration)
 {
         int i;
 
-        printf("Running %siteration tests for %d seconds\n",
+        printv(1, "Running %siteration tests for %d seconds\n",
                         order > 0 ? "multiorder " : "", test_duration);
 
         max_order = order;
diff --git a/tools/testing/radix-tree/linux.c b/tools/testing/radix-tree/linux.c
index d31ea7c9abec..cf48c8473f48 100644
--- a/tools/testing/radix-tree/linux.c
+++ b/tools/testing/radix-tree/linux.c
@@ -5,7 +5,7 @@
 #include <unistd.h>
 #include <assert.h>
 
-#include <linux/mempool.h>
+#include <linux/gfp.h>
 #include <linux/poison.h>
 #include <linux/slab.h>
 #include <linux/radix-tree.h>
@@ -13,6 +13,8 @@
 
 int nr_allocated;
 int preempt_count;
+int kmalloc_verbose;
+int test_verbose;
 
 struct kmem_cache {
         pthread_mutex_t lock;
@@ -22,27 +24,6 @@ struct kmem_cache {
         void (*ctor)(void *);
 };
 
-void *mempool_alloc(mempool_t *pool, int gfp_mask)
-{
-        return pool->alloc(gfp_mask, pool->data);
-}
-
-void mempool_free(void *element, mempool_t *pool)
-{
-        pool->free(element, pool->data);
-}
-
-mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn,
-                        mempool_free_t *free_fn, void *pool_data)
-{
-        mempool_t *ret = malloc(sizeof(*ret));
-
-        ret->alloc = alloc_fn;
-        ret->free = free_fn;
-        ret->data = pool_data;
-        return ret;
-}
-
 void *kmem_cache_alloc(struct kmem_cache *cachep, int flags)
 {
         struct radix_tree_node *node;
@@ -54,9 +35,9 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, int flags)
         if (cachep->nr_objs) {
                 cachep->nr_objs--;
                 node = cachep->objs;
-                cachep->objs = node->private_data;
+                cachep->objs = node->parent;
                 pthread_mutex_unlock(&cachep->lock);
-                node->private_data = NULL;
+                node->parent = NULL;
         } else {
                 pthread_mutex_unlock(&cachep->lock);
                 node = malloc(cachep->size);
@@ -65,6 +46,8 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, int flags)
         }
 
         uatomic_inc(&nr_allocated);
+        if (kmalloc_verbose)
+                printf("Allocating %p from slab\n", node);
         return node;
 }
 
@@ -72,6 +55,8 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp)
 {
         assert(objp);
         uatomic_dec(&nr_allocated);
+        if (kmalloc_verbose)
+                printf("Freeing %p to slab\n", objp);
         pthread_mutex_lock(&cachep->lock);
         if (cachep->nr_objs > 10) {
                 memset(objp, POISON_FREE, cachep->size);
@@ -79,7 +64,7 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp)
         } else {
                 struct radix_tree_node *node = objp;
                 cachep->nr_objs++;
-                node->private_data = cachep->objs;
+                node->parent = cachep->objs;
                 cachep->objs = node;
         }
         pthread_mutex_unlock(&cachep->lock);
@@ -89,6 +74,8 @@ void *kmalloc(size_t size, gfp_t gfp)
 {
         void *ret = malloc(size);
         uatomic_inc(&nr_allocated);
+        if (kmalloc_verbose)
+                printf("Allocating %p from malloc\n", ret);
         return ret;
 }
 
@@ -97,6 +84,8 @@ void kfree(void *p)
         if (!p)
                 return;
         uatomic_dec(&nr_allocated);
+        if (kmalloc_verbose)
+                printf("Freeing %p to malloc\n", p);
         free(p);
 }
 
diff --git a/tools/testing/radix-tree/linux/bitops.h b/tools/testing/radix-tree/linux/bitops.h
deleted file mode 100644
index a13e9bc76eec..000000000000
--- a/tools/testing/radix-tree/linux/bitops.h
+++ /dev/null
@@ -1,160 +0,0 @@
-#ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
-#define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
-
-#include <linux/types.h>
-#include <linux/bitops/find.h>
-#include <linux/bitops/hweight.h>
-#include <linux/kernel.h>
-
-#define BIT_MASK(nr)            (1UL << ((nr) % BITS_PER_LONG))
-#define BIT_WORD(nr)            ((nr) / BITS_PER_LONG)
-#define BITS_PER_BYTE           8
-#define BITS_TO_LONGS(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
-
-/**
- * __set_bit - Set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * Unlike set_bit(), this function is non-atomic and may be reordered.
- * If it's called on the same region of memory simultaneously, the effect
- * may be that only one operation succeeds.
- */
-static inline void __set_bit(int nr, volatile unsigned long *addr)
-{
-        unsigned long mask = BIT_MASK(nr);
-        unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-
-        *p  |= mask;
-}
-
-static inline void __clear_bit(int nr, volatile unsigned long *addr)
-{
-        unsigned long mask = BIT_MASK(nr);
-        unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-
-        *p &= ~mask;
-}
-
-/**
- * __change_bit - Toggle a bit in memory
- * @nr: the bit to change
- * @addr: the address to start counting from
- *
- * Unlike change_bit(), this function is non-atomic and may be reordered.
- * If it's called on the same region of memory simultaneously, the effect
- * may be that only one operation succeeds.
- */
-static inline void __change_bit(int nr, volatile unsigned long *addr)
-{
-        unsigned long mask = BIT_MASK(nr);
-        unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-
-        *p ^= mask;
-}
-
-/**
- * __test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.
- * If two examples of this operation race, one can appear to succeed
- * but actually fail.  You must protect multiple accesses with a lock.
- */
-static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
-{
-        unsigned long mask = BIT_MASK(nr);
-        unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-        unsigned long old = *p;
-
-        *p = old | mask;
-        return (old & mask) != 0;
-}
-
-/**
- * __test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.
- * If two examples of this operation race, one can appear to succeed
- * but actually fail.  You must protect multiple accesses with a lock.
- */
-static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
-{
-        unsigned long mask = BIT_MASK(nr);
-        unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-        unsigned long old = *p;
-
-        *p = old & ~mask;
-        return (old & mask) != 0;
-}
-
-/* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(int nr,
-                                            volatile unsigned long *addr)
-{
-        unsigned long mask = BIT_MASK(nr);
-        unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-        unsigned long old = *p;
-
-        *p = old ^ mask;
-        return (old & mask) != 0;
-}
-
-/**
- * test_bit - Determine whether a bit is set
- * @nr: bit number to test
- * @addr: Address to start counting from
- */
-static inline int test_bit(int nr, const volatile unsigned long *addr)
-{
-        return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
-}
-
-/**
- * __ffs - find first bit in word.
- * @word: The word to search
- *
- * Undefined if no bit exists, so code should check against 0 first.
- */
-static inline unsigned long __ffs(unsigned long word)
-{
-        int num = 0;
-
-        if ((word & 0xffffffff) == 0) {
-                num += 32;
-                word >>= 32;
-        }
-        if ((word & 0xffff) == 0) {
-                num += 16;
-                word >>= 16;
-        }
-        if ((word & 0xff) == 0) {
-                num += 8;
-                word >>= 8;
-        }
-        if ((word & 0xf) == 0) {
-                num += 4;
-                word >>= 4;
-        }
-        if ((word & 0x3) == 0) {
-                num += 2;
-                word >>= 2;
-        }
-        if ((word & 0x1) == 0)
-                num += 1;
-        return num;
-}
-
-unsigned long find_next_bit(const unsigned long *addr,
-                            unsigned long size,
-                            unsigned long offset);
-
-static inline unsigned long hweight_long(unsigned long w)
-{
-        return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
-}
-
-#endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
diff --git a/tools/testing/radix-tree/linux/bitops/__ffs.h b/tools/testing/radix-tree/linux/bitops/__ffs.h
deleted file mode 100644
index 9a3274aecf83..000000000000
--- a/tools/testing/radix-tree/linux/bitops/__ffs.h
+++ /dev/null
@@ -1,43 +0,0 @@
-#ifndef _ASM_GENERIC_BITOPS___FFS_H_
-#define _ASM_GENERIC_BITOPS___FFS_H_
-
-#include <asm/types.h>
-
-/**
- * __ffs - find first bit in word.
- * @word: The word to search
- *
- * Undefined if no bit exists, so code should check against 0 first.
- */
-static inline unsigned long __ffs(unsigned long word)
-{
-        int num = 0;
-
-#if BITS_PER_LONG == 64
-        if ((word & 0xffffffff) == 0) {
-                num += 32;
-                word >>= 32;
-        }
-#endif
-        if ((word & 0xffff) == 0) {
-                num += 16;
-                word >>= 16;
-        }
-        if ((word & 0xff) == 0) {
-                num += 8;
-                word >>= 8;
-        }
-        if ((word & 0xf) == 0) {
-                num += 4;
-                word >>= 4;
-        }
-        if ((word & 0x3) == 0) {
-                num += 2;
-                word >>= 2;
-        }
-        if ((word & 0x1) == 0)
-                num += 1;
-        return num;
-}
-
-#endif /* _ASM_GENERIC_BITOPS___FFS_H_ */
diff --git a/tools/testing/radix-tree/linux/bitops/ffs.h b/tools/testing/radix-tree/linux/bitops/ffs.h
deleted file mode 100644
index fbbb43af7dc0..000000000000
--- a/tools/testing/radix-tree/linux/bitops/ffs.h
+++ /dev/null
@@ -1,41 +0,0 @@
-#ifndef _ASM_GENERIC_BITOPS_FFS_H_
-#define _ASM_GENERIC_BITOPS_FFS_H_
-
-/**
- * ffs - find first bit set
- * @x: the word to search
- *
- * This is defined the same way as
- * the libc and compiler builtin ffs routines, therefore
- * differs in spirit from the above ffz (man ffs).
- */
-static inline int ffs(int x)
-{
-        int r = 1;
-
-        if (!x)
-                return 0;
-        if (!(x & 0xffff)) {
-                x >>= 16;
-                r += 16;
-        }
-        if (!(x & 0xff)) {
-                x >>= 8;
-                r += 8;
-        }
-        if (!(x & 0xf)) {
-                x >>= 4;
-                r += 4;
-        }
-        if (!(x & 3)) {
-                x >>= 2;
-                r += 2;
-        }
-        if (!(x & 1)) {
-                x >>= 1;
-                r += 1;
-        }
-        return r;
-}
-
-#endif /* _ASM_GENERIC_BITOPS_FFS_H_ */
diff --git a/tools/testing/radix-tree/linux/bitops/ffz.h b/tools/testing/radix-tree/linux/bitops/ffz.h
deleted file mode 100644
index 6744bd4cdf46..000000000000
--- a/tools/testing/radix-tree/linux/bitops/ffz.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _ASM_GENERIC_BITOPS_FFZ_H_
-#define _ASM_GENERIC_BITOPS_FFZ_H_
-
-/*
- * ffz - find first zero in word.
- * @word: The word to search
- *
- * Undefined if no zero exists, so code should check against ~0UL first.
- */
-#define ffz(x)  __ffs(~(x))
-
-#endif /* _ASM_GENERIC_BITOPS_FFZ_H_ */
diff --git a/tools/testing/radix-tree/linux/bitops/find.h b/tools/testing/radix-tree/linux/bitops/find.h
deleted file mode 100644
index 72a51e5a12ef..000000000000
--- a/tools/testing/radix-tree/linux/bitops/find.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef _ASM_GENERIC_BITOPS_FIND_H_
-#define _ASM_GENERIC_BITOPS_FIND_H_
-
-extern unsigned long find_next_bit(const unsigned long *addr, unsigned long
-                size, unsigned long offset);
-
-extern unsigned long find_next_zero_bit(const unsigned long *addr, unsigned
-                long size, unsigned long offset);
-
-#define find_first_bit(addr, size) find_next_bit((addr), (size), 0)
-#define find_first_zero_bit(addr, size) find_next_zero_bit((addr), (size), 0)
-
-#endif /*_ASM_GENERIC_BITOPS_FIND_H_ */
diff --git a/tools/testing/radix-tree/linux/bitops/fls.h b/tools/testing/radix-tree/linux/bitops/fls.h
deleted file mode 100644
index 850859bc5069..000000000000
--- a/tools/testing/radix-tree/linux/bitops/fls.h
+++ /dev/null
@@ -1,41 +0,0 @@
-#ifndef _ASM_GENERIC_BITOPS_FLS_H_
-#define _ASM_GENERIC_BITOPS_FLS_H_
-
-/**
- * fls - find last (most-significant) bit set
- * @x: the word to search
- *
- * This is defined the same way as ffs.
- * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
- */
-
-static inline int fls(int x)
-{
-        int r = 32;
-
-        if (!x)
-                return 0;
-        if (!(x & 0xffff0000u)) {
-                x <<= 16;
-                r -= 16;
-        }
-        if (!(x & 0xff000000u)) {
-                x <<= 8;
-                r -= 8;
-        }
-        if (!(x & 0xf0000000u)) {
-                x <<= 4;
-                r -= 4;
-        }
-        if (!(x & 0xc0000000u)) {
-                x <<= 2;
-                r -= 2;
-        }
-        if (!(x & 0x80000000u)) {
-                x <<= 1;
-                r -= 1;
-        }
-        return r;
-}
-
-#endif /* _ASM_GENERIC_BITOPS_FLS_H_ */
diff --git a/tools/testing/radix-tree/linux/bitops/fls64.h b/tools/testing/radix-tree/linux/bitops/fls64.h
deleted file mode 100644
index 1b6b17ce2428..000000000000
--- a/tools/testing/radix-tree/linux/bitops/fls64.h
+++ /dev/null
@@ -1,14 +0,0 @@
-#ifndef _ASM_GENERIC_BITOPS_FLS64_H_
-#define _ASM_GENERIC_BITOPS_FLS64_H_
-
-#include <asm/types.h>
-
-static inline int fls64(__u64 x)
-{
-        __u32 h = x >> 32;
-        if (h)
-                return fls(h) + 32;
-        return fls(x);
-}
-
-#endif /* _ASM_GENERIC_BITOPS_FLS64_H_ */
diff --git a/tools/testing/radix-tree/linux/bitops/hweight.h b/tools/testing/radix-tree/linux/bitops/hweight.h
deleted file mode 100644
index fbbc383771da..000000000000
--- a/tools/testing/radix-tree/linux/bitops/hweight.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef _ASM_GENERIC_BITOPS_HWEIGHT_H_
-#define _ASM_GENERIC_BITOPS_HWEIGHT_H_
-
-#include <asm/types.h>
-
-extern unsigned int hweight32(unsigned int w);
-extern unsigned int hweight16(unsigned int w);
-extern unsigned int hweight8(unsigned int w);
-extern unsigned long hweight64(__u64 w);
-
-#endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/tools/testing/radix-tree/linux/bitops/le.h b/tools/testing/radix-tree/linux/bitops/le.h
deleted file mode 100644
index b9c7e5d2d2ad..000000000000
--- a/tools/testing/radix-tree/linux/bitops/le.h
+++ /dev/null
@@ -1,53 +0,0 @@
-#ifndef _ASM_GENERIC_BITOPS_LE_H_
-#define _ASM_GENERIC_BITOPS_LE_H_
-
-#include <asm/types.h>
-#include <asm/byteorder.h>
-
-#define BITOP_WORD(nr)          ((nr) / BITS_PER_LONG)
-#define BITOP_LE_SWIZZLE        ((BITS_PER_LONG-1) & ~0x7)
-
-#if defined(__LITTLE_ENDIAN)
-
-#define generic_test_le_bit(nr, addr) test_bit(nr, addr)
-#define generic___set_le_bit(nr, addr) __set_bit(nr, addr)
-#define generic___clear_le_bit(nr, addr) __clear_bit(nr, addr)
-
-#define generic_test_and_set_le_bit(nr, addr) test_and_set_bit(nr, addr)
-#define generic_test_and_clear_le_bit(nr, addr) test_and_clear_bit(nr, addr)
-
-#define generic___test_and_set_le_bit(nr, addr) __test_and_set_bit(nr, addr)
-#define generic___test_and_clear_le_bit(nr, addr) __test_and_clear_bit(nr, addr)
-
-#define generic_find_next_zero_le_bit(addr, size, offset) find_next_zero_bit(addr, size, offset)
-
-#elif defined(__BIG_ENDIAN)
-
-#define generic_test_le_bit(nr, addr) \
-        test_bit((nr) ^ BITOP_LE_SWIZZLE, (addr))
-#define generic___set_le_bit(nr, addr) \
-        __set_bit((nr) ^ BITOP_LE_SWIZZLE, (addr))
-#define generic___clear_le_bit(nr, addr) \
-        __clear_bit((nr) ^ BITOP_LE_SWIZZLE, (addr))
-
-#define generic_test_and_set_le_bit(nr, addr) \
-        test_and_set_bit((nr) ^ BITOP_LE_SWIZZLE, (addr))
-#define generic_test_and_clear_le_bit(nr, addr) \
-        test_and_clear_bit((nr) ^ BITOP_LE_SWIZZLE, (addr))
-
-#define generic___test_and_set_le_bit(nr, addr) \
-        __test_and_set_bit((nr) ^ BITOP_LE_SWIZZLE, (addr))
-#define generic___test_and_clear_le_bit(nr, addr) \
-        __test_and_clear_bit((nr) ^ BITOP_LE_SWIZZLE, (addr))
-
-extern unsigned long generic_find_next_zero_le_bit(const unsigned long *addr,
-                unsigned long size, unsigned long offset);
-
-#else
-#error "Please fix <asm/byteorder.h>"
-#endif
-
-#define generic_find_first_zero_le_bit(addr, size) \
-        generic_find_next_zero_le_bit((addr), (size), 0)
-
-#endif /* _ASM_GENERIC_BITOPS_LE_H_ */
diff --git a/tools/testing/radix-tree/linux/bitops/non-atomic.h b/tools/testing/radix-tree/linux/bitops/non-atomic.h
deleted file mode 100644
index 6a1bcb9d2c4a..000000000000
--- a/tools/testing/radix-tree/linux/bitops/non-atomic.h
+++ /dev/null
@@ -1,110 +0,0 @@
-#ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
-#define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
-
-#include <asm/types.h>
-
-#define BITOP_WORD(nr)          ((nr) / BITS_PER_LONG)
-
-/**
- * __set_bit - Set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * Unlike set_bit(), this function is non-atomic and may be reordered.
- * If it's called on the same region of memory simultaneously, the effect
- * may be that only one operation succeeds.
- */
-static inline void __set_bit(int nr, volatile unsigned long *addr)
-{
-        unsigned long mask = BIT_MASK(nr);
-        unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
-
-        *p  |= mask;
-}
-
-static inline void __clear_bit(int nr, volatile unsigned long *addr)
-{
-        unsigned long mask = BIT_MASK(nr);
-        unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
-
-        *p &= ~mask;
-}
-
-/**
- * __change_bit - Toggle a bit in memory
- * @nr: the bit to change
- * @addr: the address to start counting from
- *
- * Unlike change_bit(), this function is non-atomic and may be reordered.
- * If it's called on the same region of memory simultaneously, the effect
- * may be that only one operation succeeds.
- */
-static inline void __change_bit(int nr, volatile unsigned long *addr)
-{
-        unsigned long mask = BIT_MASK(nr);
-        unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
-
-        *p ^= mask;
-}
-
-/**
- * __test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.
- * If two examples of this operation race, one can appear to succeed
- * but actually fail.  You must protect multiple accesses with a lock.
- */
-static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
-{
-        unsigned long mask = BIT_MASK(nr);
-        unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
-        unsigned long old = *p;
-
-        *p = old | mask;
-        return (old & mask) != 0;
-}
-
-/**
- * __test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.
- * If two examples of this operation race, one can appear to succeed
- * but actually fail.  You must protect multiple accesses with a lock.
- */
-static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
-{
-        unsigned long mask = BIT_MASK(nr);
-        unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
-        unsigned long old = *p;
-
-        *p = old & ~mask;
-        return (old & mask) != 0;
-}
-
-/* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(int nr,
-                                            volatile unsigned long *addr)
-{
-        unsigned long mask = BIT_MASK(nr);
-        unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
-        unsigned long old = *p;
-
-        *p = old ^ mask;
-        return (old & mask) != 0;
-}
-
-/**
- * test_bit - Determine whether a bit is set
- * @nr: bit number to test
- * @addr: Address to start counting from
- */
-static inline int test_bit(int nr, const volatile unsigned long *addr)
-{
-        return 1UL & (addr[BITOP_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
-}
-
-#endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
diff --git a/tools/testing/radix-tree/linux/export.h b/tools/testing/radix-tree/linux/export.h
deleted file mode 100644
index b6afd131998d..000000000000
--- a/tools/testing/radix-tree/linux/export.h
+++ /dev/null
@@ -1,2 +0,0 @@
-
-#define EXPORT_SYMBOL(sym)
diff --git a/tools/testing/radix-tree/linux/gfp.h b/tools/testing/radix-tree/linux/gfp.h
index 5b09b2ce6c33..39a0dcb9475a 100644
--- a/tools/testing/radix-tree/linux/gfp.h
+++ b/tools/testing/radix-tree/linux/gfp.h
@@ -1,6 +1,8 @@
 #ifndef _GFP_H
 #define _GFP_H
 
+#include <linux/types.h>
+
 #define __GFP_BITS_SHIFT 26
 #define __GFP_BITS_MASK ((gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
 
@@ -13,10 +15,12 @@
 #define __GFP_DIRECT_RECLAIM    0x400000u
 #define __GFP_KSWAPD_RECLAIM    0x2000000u
 
-#define __GFP_RECLAIM           (__GFP_DIRECT_RECLAIM|__GFP_KSWAPD_RECLAIM)
+#define __GFP_RECLAIM   (__GFP_DIRECT_RECLAIM|__GFP_KSWAPD_RECLAIM)
+
+#define GFP_ATOMIC      (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM)
+#define GFP_KERNEL      (__GFP_RECLAIM | __GFP_IO | __GFP_FS)
+#define GFP_NOWAIT      (__GFP_KSWAPD_RECLAIM)
 
-#define GFP_ATOMIC              (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM)
-#define GFP_KERNEL              (__GFP_RECLAIM | __GFP_IO | __GFP_FS)
 
 static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
 {
diff --git a/tools/testing/radix-tree/linux/idr.h b/tools/testing/radix-tree/linux/idr.h
new file mode 100644
index 000000000000..4e342f2e37cf
--- /dev/null
+++ b/tools/testing/radix-tree/linux/idr.h
@@ -0,0 +1 @@
+#include "../../../../include/linux/idr.h"
diff --git a/tools/testing/radix-tree/linux/init.h b/tools/testing/radix-tree/linux/init.h
index 360cabb3c4e7..1bb0afc21309 100644
--- a/tools/testing/radix-tree/linux/init.h
+++ b/tools/testing/radix-tree/linux/init.h
@@ -1 +1 @@
-/* An empty file stub that allows radix-tree.c to compile. */
+#define __init
diff --git a/tools/testing/radix-tree/linux/kernel.h b/tools/testing/radix-tree/linux/kernel.h
index 9b43b4975d83..b21a77fddcf7 100644
--- a/tools/testing/radix-tree/linux/kernel.h
+++ b/tools/testing/radix-tree/linux/kernel.h
@@ -1,64 +1,21 @@
 #ifndef _KERNEL_H
 #define _KERNEL_H
 
-#include <assert.h>
+#include "../../include/linux/kernel.h"
 #include <string.h>
 #include <stdio.h>
-#include <stddef.h>
 #include <limits.h>
 
-#include "../../include/linux/compiler.h"
-#include "../../include/linux/err.h"
+#include <linux/compiler.h>
+#include <linux/err.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
 #include "../../../include/linux/kconfig.h"
 
-#ifdef BENCHMARK
-#define RADIX_TREE_MAP_SHIFT    6
-#else
-#define RADIX_TREE_MAP_SHIFT    3
-#endif
-
-#ifndef NULL
-#define NULL    0
-#endif
-
-#define BUG_ON(expr)    assert(!(expr))
-#define WARN_ON(expr)   assert(!(expr))
-#define __init
-#define __must_check
-#define panic(expr)
 #define printk printf
-#define __force
-#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
 #define pr_debug printk
-
-#define smp_rmb()       barrier()
-#define smp_wmb()       barrier()
-#define cpu_relax()     barrier()
+#define pr_cont printk
 
 #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
 
-#define container_of(ptr, type, member) ({                      \
-        const typeof( ((type *)0)->member ) *__mptr = (ptr);    \
-        (type *)( (char *)__mptr - offsetof(type, member) );})
-#define min(a, b) ((a) < (b) ? (a) : (b))
-
-#define cond_resched()  sched_yield()
-
-static inline int in_interrupt(void)
-{
-        return 0;
-}
-
-/*
- * This looks more complex than it should be. But we need to
- * get the type for the ~ right in round_down (it needs to be
- * as wide as the result!), and we want to evaluate the macro
- * arguments just once each.
- */
-#define __round_mask(x, y) ((__typeof__(x))((y)-1))
-#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
-#define round_down(x, y) ((x) & ~__round_mask(x, y))
-
-#define xchg(ptr, x)    uatomic_xchg(ptr, x)
-
 #endif /* _KERNEL_H */
diff --git a/tools/testing/radix-tree/linux/mempool.h b/tools/testing/radix-tree/linux/mempool.h
deleted file mode 100644
index 6a2dc55b41d6..000000000000
--- a/tools/testing/radix-tree/linux/mempool.h
+++ /dev/null
@@ -1,16 +0,0 @@
-
-#include <linux/slab.h>
-
-typedef void *(mempool_alloc_t)(int gfp_mask, void *pool_data);
-typedef void (mempool_free_t)(void *element, void *pool_data);
-
-typedef struct {
-        mempool_alloc_t *alloc;
-        mempool_free_t *free;
-        void *data;
-} mempool_t;
-
-void *mempool_alloc(mempool_t *pool, int gfp_mask);
-void mempool_free(void *element, mempool_t *pool);
-mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn,
-                        mempool_free_t *free_fn, void *pool_data);
diff --git a/tools/testing/radix-tree/linux/percpu.h b/tools/testing/radix-tree/linux/percpu.h
index 5837f1d56f17..3ea01a1a88c2 100644
--- a/tools/testing/radix-tree/linux/percpu.h
+++ b/tools/testing/radix-tree/linux/percpu.h
@@ -1,7 +1,10 @@
-
+#define DECLARE_PER_CPU(type, val) extern type val
 #define DEFINE_PER_CPU(type, val) type val
 
 #define __get_cpu_var(var)      var
 #define this_cpu_ptr(var)       var
+#define this_cpu_read(var)      var
+#define this_cpu_xchg(var, val)         uatomic_xchg(&var, val)
+#define this_cpu_cmpxchg(var, old, new) uatomic_cmpxchg(&var, old, new)
 #define per_cpu_ptr(ptr, cpu)   ({ (void)(cpu); (ptr); })
 #define per_cpu(var, cpu)       (*per_cpu_ptr(&(var), cpu))
diff --git a/tools/testing/radix-tree/linux/preempt.h b/tools/testing/radix-tree/linux/preempt.h
index 65c04c226965..35c5ac81529f 100644
--- a/tools/testing/radix-tree/linux/preempt.h
+++ b/tools/testing/radix-tree/linux/preempt.h
@@ -1,4 +1,14 @@
+#ifndef __LINUX_PREEMPT_H
+#define __LINUX_PREEMPT_H
+
 extern int preempt_count;
 
 #define preempt_disable()       uatomic_inc(&preempt_count)
 #define preempt_enable()        uatomic_dec(&preempt_count)
+
+static inline int in_interrupt(void)
+{
+        return 0;
+}
+
+#endif /* __LINUX_PREEMPT_H */
diff --git a/tools/testing/radix-tree/linux/radix-tree.h b/tools/testing/radix-tree/linux/radix-tree.h
index ce694ddd4aea..bf1bb231f9b5 100644
--- a/tools/testing/radix-tree/linux/radix-tree.h
+++ b/tools/testing/radix-tree/linux/radix-tree.h
@@ -1 +1,26 @@
+#ifndef _TEST_RADIX_TREE_H
+#define _TEST_RADIX_TREE_H
+
+#include "generated/map-shift.h"
 #include "../../../../include/linux/radix-tree.h"
+
+extern int kmalloc_verbose;
+extern int test_verbose;
+
+static inline void trace_call_rcu(struct rcu_head *head,
+                void (*func)(struct rcu_head *head))
+{
+        if (kmalloc_verbose)
+                printf("Delaying free of %p to slab\n", (char *)head -
+                                offsetof(struct radix_tree_node, rcu_head));
+        call_rcu(head, func);
+}
+
+#define printv(verbosity_level, fmt, ...) \
+        if(test_verbose >= verbosity_level) \
+                printf(fmt, ##__VA_ARGS__)
+
+#undef call_rcu
+#define call_rcu(x, y) trace_call_rcu(x, y)
+
+#endif /* _TEST_RADIX_TREE_H */
diff --git a/tools/testing/radix-tree/linux/types.h b/tools/testing/radix-tree/linux/types.h
deleted file mode 100644
index 8491d89873bb..000000000000
--- a/tools/testing/radix-tree/linux/types.h
+++ /dev/null
@@ -1,23 +0,0 @@
-#ifndef _TYPES_H
-#define _TYPES_H
-
-#include "../../include/linux/types.h"
-
-#define __rcu
-#define __read_mostly
-
-static inline void INIT_LIST_HEAD(struct list_head *list)
-{
-        list->next = list;
-        list->prev = list;
-}
-
-typedef struct {
-        unsigned int x;
-} spinlock_t;
-
-#define uninitialized_var(x) x = x
-
-#include <linux/gfp.h>
-
-#endif
diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c
index f7e9801a6754..bc9a78449572 100644
--- a/tools/testing/radix-tree/main.c
+++ b/tools/testing/radix-tree/main.c
@@ -3,6 +3,7 @@
 #include <unistd.h>
 #include <time.h>
 #include <assert.h>
+#include <limits.h>
 
 #include <linux/slab.h>
 #include <linux/radix-tree.h>
@@ -67,7 +68,7 @@ void big_gang_check(bool long_run)
 
         for (i = 0; i < (long_run ? 1000 : 3); i++) {
                 __big_gang_check();
-                printf("%d ", i);
+                printv(2, "%d ", i);
                 fflush(stdout);
         }
 }
@@ -128,14 +129,19 @@ void check_copied_tags(struct radix_tree_root *tree, unsigned long start, unsign
                         putchar('.'); */
                 if (idx[i] < start || idx[i] > end) {
                         if (item_tag_get(tree, idx[i], totag)) {
-                                printf("%lu-%lu: %lu, tags %d-%d\n", start, end, idx[i], item_tag_get(tree, idx[i], fromtag), item_tag_get(tree, idx[i], totag));
+                                printv(2, "%lu-%lu: %lu, tags %d-%d\n", start,
+                                       end, idx[i], item_tag_get(tree, idx[i],
+                                                                 fromtag),
+                                       item_tag_get(tree, idx[i], totag));
                         }
                         assert(!item_tag_get(tree, idx[i], totag));
                         continue;
                 }
                 if (item_tag_get(tree, idx[i], fromtag) ^
                         item_tag_get(tree, idx[i], totag)) {
-                        printf("%lu-%lu: %lu, tags %d-%d\n", start, end, idx[i], item_tag_get(tree, idx[i], fromtag), item_tag_get(tree, idx[i], totag));
+                        printv(2, "%lu-%lu: %lu, tags %d-%d\n", start, end,
+                               idx[i], item_tag_get(tree, idx[i], fromtag),
+                               item_tag_get(tree, idx[i], totag));
                 }
                 assert(!(item_tag_get(tree, idx[i], fromtag) ^
                          item_tag_get(tree, idx[i], totag)));
@@ -237,7 +243,7 @@ static void __locate_check(struct radix_tree_root *tree, unsigned long index,
         item = item_lookup(tree, index);
         index2 = find_item(tree, item);
         if (index != index2) {
-                printf("index %ld order %d inserted; found %ld\n",
+                printv(2, "index %ld order %d inserted; found %ld\n",
                         index, order, index2);
                 abort();
         }
@@ -288,43 +294,48 @@ static void single_thread_tests(bool long_run)
 {
         int i;
 
-        printf("starting single_thread_tests: %d allocated, preempt %d\n",
+        printv(1, "starting single_thread_tests: %d allocated, preempt %d\n",
                 nr_allocated, preempt_count);
         multiorder_checks();
         rcu_barrier();
-        printf("after multiorder_check: %d allocated, preempt %d\n",
+        printv(2, "after multiorder_check: %d allocated, preempt %d\n",
                 nr_allocated, preempt_count);
         locate_check();
         rcu_barrier();
-        printf("after locate_check: %d allocated, preempt %d\n",
+        printv(2, "after locate_check: %d allocated, preempt %d\n",
                 nr_allocated, preempt_count);
         tag_check();
         rcu_barrier();
-        printf("after tag_check: %d allocated, preempt %d\n",
+        printv(2, "after tag_check: %d allocated, preempt %d\n",
                 nr_allocated, preempt_count);
         gang_check();
         rcu_barrier();
-        printf("after gang_check: %d allocated, preempt %d\n",
+        printv(2, "after gang_check: %d allocated, preempt %d\n",
                 nr_allocated, preempt_count);
         add_and_check();
         rcu_barrier();
-        printf("after add_and_check: %d allocated, preempt %d\n",
+        printv(2, "after add_and_check: %d allocated, preempt %d\n",
                 nr_allocated, preempt_count);
         dynamic_height_check();
         rcu_barrier();
-        printf("after dynamic_height_check: %d allocated, preempt %d\n",
+        printv(2, "after dynamic_height_check: %d allocated, preempt %d\n",
+                nr_allocated, preempt_count);
+        idr_checks();
+        ida_checks();
+        rcu_barrier();
+        printv(2, "after idr_checks: %d allocated, preempt %d\n",
                 nr_allocated, preempt_count);
         big_gang_check(long_run);
         rcu_barrier();
-        printf("after big_gang_check: %d allocated, preempt %d\n",
+        printv(2, "after big_gang_check: %d allocated, preempt %d\n",
                 nr_allocated, preempt_count);
         for (i = 0; i < (long_run ? 2000 : 3); i++) {
                 copy_tag_check();
-                printf("%d ", i);
+                printv(2, "%d ", i);
                 fflush(stdout);
         }
         rcu_barrier();
-        printf("after copy_tag_check: %d allocated, preempt %d\n",
+        printv(2, "after copy_tag_check: %d allocated, preempt %d\n",
                 nr_allocated, preempt_count);
 }
 
@@ -334,25 +345,30 @@ int main(int argc, char **argv)
         int opt;
         unsigned int seed = time(NULL);
 
-        while ((opt = getopt(argc, argv, "ls:")) != -1) {
+        while ((opt = getopt(argc, argv, "ls:v")) != -1) {
                 if (opt == 'l')
                         long_run = true;
                 else if (opt == 's')
                         seed = strtoul(optarg, NULL, 0);
+                else if (opt == 'v')
+                        test_verbose++;
         }
 
         printf("random seed %u\n", seed);
         srand(seed);
 
+        printf("running tests\n");
+
         rcu_register_thread();
         radix_tree_init();
 
         regression1_test();
         regression2_test();
         regression3_test();
-        iteration_test(0, 10);
-        iteration_test(7, 20);
+        iteration_test(0, 10 + 90 * long_run);
+        iteration_test(7, 10 + 90 * long_run);
         single_thread_tests(long_run);
+        ida_thread_tests();
 
         /* Free any remaining preallocated nodes */
         radix_tree_cpu_dead(0);
@@ -360,9 +376,11 @@ int main(int argc, char **argv)
         benchmark();
 
         rcu_barrier();
-        printf("after rcu_barrier: %d allocated, preempt %d\n",
+        printv(2, "after rcu_barrier: %d allocated, preempt %d\n",
                 nr_allocated, preempt_count);
         rcu_unregister_thread();
 
+        printf("tests completed\n");
+
         exit(0);
 }
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index f79812a5e070..06c71178d07d 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -30,7 +30,7 @@ static void __multiorder_tag_test(int index, int order)
         /* our canonical entry */
         base = index & ~((1 << order) - 1);
 
-        printf("Multiorder tag test with index %d, canonical entry %d\n",
+        printv(2, "Multiorder tag test with index %d, canonical entry %d\n",
                         index, base);
 
         err = item_insert_order(&tree, index, order);
@@ -150,7 +150,7 @@ static void multiorder_check(unsigned long index, int order)
         struct item *item2 = item_create(min, order);
         RADIX_TREE(tree, GFP_KERNEL);
 
-        printf("Multiorder index %ld, order %d\n", index, order);
+        printv(2, "Multiorder index %ld, order %d\n", index, order);
 
         assert(item_insert_order(&tree, index, order) == 0);
 
@@ -188,7 +188,7 @@ static void multiorder_shrink(unsigned long index, int order)
         RADIX_TREE(tree, GFP_KERNEL);
         struct radix_tree_node *node;
 
-        printf("Multiorder shrink index %ld, order %d\n", index, order);
+        printv(2, "Multiorder shrink index %ld, order %d\n", index, order);
 
         assert(item_insert_order(&tree, 0, order) == 0);
 
@@ -209,7 +209,8 @@ static void multiorder_shrink(unsigned long index, int order)
                 item_check_absent(&tree, i);
 
         if (!item_delete(&tree, 0)) {
-                printf("failed to delete index %ld (order %d)\n", index, order);                abort();
+                printv(2, "failed to delete index %ld (order %d)\n", index, order);
+                abort();
         }
 
         for (i = 0; i < 2*max; i++)
@@ -234,7 +235,7 @@ void multiorder_iteration(void)
         void **slot;
         int i, j, err;
 
-        printf("Multiorder iteration test\n");
+        printv(1, "Multiorder iteration test\n");
 
 #define NUM_ENTRIES 11
         int index[NUM_ENTRIES] = {0, 2, 4, 8, 16, 32, 34, 36, 64, 72, 128};
@@ -275,7 +276,7 @@ void multiorder_tagged_iteration(void)
         void **slot;
         int i, j;
 
-        printf("Multiorder tagged iteration test\n");
+        printv(1, "Multiorder tagged iteration test\n");
 
 #define MT_NUM_ENTRIES 9
         int index[MT_NUM_ENTRIES] = {0, 2, 4, 16, 32, 40, 64, 72, 128};
@@ -355,6 +356,10 @@ void multiorder_tagged_iteration(void)
         item_kill_tree(&tree);
 }
 
+/*
+ * Basic join checks: make sure we can't find an entry in the tree after
+ * a larger entry has replaced it
+ */
 static void multiorder_join1(unsigned long index,
                                 unsigned order1, unsigned order2)
 {
@@ -373,6 +378,10 @@ static void multiorder_join1(unsigned long index,
         item_kill_tree(&tree);
 }
 
+/*
+ * Check that the accounting of exceptional entries is handled correctly
+ * by joining an exceptional entry to a normal pointer.
+ */
 static void multiorder_join2(unsigned order1, unsigned order2)
 {
         RADIX_TREE(tree, GFP_KERNEL);
@@ -386,6 +395,9 @@ static void multiorder_join2(unsigned order1, unsigned order2)
         assert(item2 == (void *)0x12UL);
         assert(node->exceptional == 1);
 
+        item2 = radix_tree_lookup(&tree, 0);
+        free(item2);
+
         radix_tree_join(&tree, 0, order1, item1);
         item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL);
         assert(item2 == item1);
@@ -453,7 +465,7 @@ static void check_mem(unsigned old_order, unsigned new_order, unsigned alloc)
 {
         struct radix_tree_preload *rtp = &radix_tree_preloads;
         if (rtp->nr != 0)
-                printf("split(%u %u) remaining %u\n", old_order, new_order,
+                printv(2, "split(%u %u) remaining %u\n", old_order, new_order,
                                                         rtp->nr);
         /*
          * Can't check for equality here as some nodes may have been
@@ -461,7 +473,7 @@ static void check_mem(unsigned old_order, unsigned new_order, unsigned alloc)
          * nodes allocated since they should have all been preloaded.
          */
         if (nr_allocated > alloc)
-                printf("split(%u %u) allocated %u %u\n", old_order, new_order,
+                printv(2, "split(%u %u) allocated %u %u\n", old_order, new_order,
                                                         alloc, nr_allocated);
 }
 
@@ -471,6 +483,7 @@ static void __multiorder_split(int old_order, int new_order)
         void **slot;
         struct radix_tree_iter iter;
         unsigned alloc;
+        struct item *item;
 
         radix_tree_preload(GFP_KERNEL);
         assert(item_insert_order(&tree, 0, old_order) == 0);
@@ -479,7 +492,7 @@ static void __multiorder_split(int old_order, int new_order)
         /* Wipe out the preloaded cache or it'll confuse check_mem() */
         radix_tree_cpu_dead(0);
 
-        radix_tree_tag_set(&tree, 0, 2);
+        item = radix_tree_tag_set(&tree, 0, 2);
 
         radix_tree_split_preload(old_order, new_order, GFP_KERNEL);
         alloc = nr_allocated;
@@ -492,6 +505,7 @@ static void __multiorder_split(int old_order, int new_order)
         radix_tree_preload_end();
 
         item_kill_tree(&tree);
+        free(item);
 }
 
 static void __multiorder_split2(int old_order, int new_order)
@@ -633,3 +647,10 @@ void multiorder_checks(void)
 
         radix_tree_cpu_dead(0);
 }
+
+int __weak main(void)
+{
+        radix_tree_init();
+        multiorder_checks();
+        return 0;
+}
diff --git a/tools/testing/radix-tree/regression1.c b/tools/testing/radix-tree/regression1.c
index 0d6813a61b37..bf97742fc18c 100644
--- a/tools/testing/radix-tree/regression1.c
+++ b/tools/testing/radix-tree/regression1.c
@@ -193,7 +193,7 @@ void regression1_test(void)
         long arg;
 
         /* Regression #1 */
-        printf("running regression test 1, should finish in under a minute\n");
+        printv(1, "running regression test 1, should finish in under a minute\n");
         nr_threads = 2;
         pthread_barrier_init(&worker_barrier, NULL, nr_threads);
 
@@ -216,5 +216,5 @@ void regression1_test(void)
 
         free(threads);
 
-        printf("regression test 1, done\n");
+        printv(1, "regression test 1, done\n");
 }
diff --git a/tools/testing/radix-tree/regression2.c b/tools/testing/radix-tree/regression2.c
index a41325d7a170..42dd2a33ed24 100644
--- a/tools/testing/radix-tree/regression2.c
+++ b/tools/testing/radix-tree/regression2.c
@@ -80,7 +80,7 @@ void regression2_test(void)
         unsigned long int start, end;
         struct page *pages[1];
 
-        printf("running regression test 2 (should take milliseconds)\n");
+        printv(1, "running regression test 2 (should take milliseconds)\n");
         /* 0. */
         for (i = 0; i <= max_slots - 1; i++) {
                 p = page_alloc();
@@ -103,7 +103,7 @@ void regression2_test(void)
 
         /* 4. */
         for (i = max_slots - 1; i >= 0; i--)
-                radix_tree_delete(&mt_tree, i);
+                free(radix_tree_delete(&mt_tree, i));
 
         /* 5. */
         // NOTE: start should not be 0 because radix_tree_gang_lookup_tag_slot
@@ -114,7 +114,9 @@ void regression2_test(void)
                 PAGECACHE_TAG_TOWRITE);
 
         /* We remove all the remained nodes */
-        radix_tree_delete(&mt_tree, max_slots);
+        free(radix_tree_delete(&mt_tree, max_slots));
 
-        printf("regression test 2, done\n");
+        BUG_ON(!radix_tree_empty(&mt_tree));
+
+        printv(1, "regression test 2, done\n");
 }
diff --git a/tools/testing/radix-tree/regression3.c b/tools/testing/radix-tree/regression3.c
index b594841fae85..670c3d2ae7b1 100644
--- a/tools/testing/radix-tree/regression3.c
+++ b/tools/testing/radix-tree/regression3.c
@@ -34,21 +34,21 @@ void regression3_test(void)
         void **slot;
         bool first;
 
-        printf("running regression test 3 (should take milliseconds)\n");
+        printv(1, "running regression test 3 (should take milliseconds)\n");
 
         radix_tree_insert(&root, 0, ptr0);
         radix_tree_tag_set(&root, 0, 0);
 
         first = true;
         radix_tree_for_each_tagged(slot, &root, &iter, 0, 0) {
-                printf("tagged %ld %p\n", iter.index, *slot);
+                printv(2, "tagged %ld %p\n", iter.index, *slot);
                 if (first) {
                         radix_tree_insert(&root, 1, ptr);
                         radix_tree_tag_set(&root, 1, 0);
                         first = false;
                 }
                 if (radix_tree_deref_retry(*slot)) {
-                        printf("retry at %ld\n", iter.index);
+                        printv(2, "retry at %ld\n", iter.index);
                         slot = radix_tree_iter_retry(&iter);
                         continue;
                 }
@@ -57,13 +57,13 @@ void regression3_test(void)
 
         first = true;
         radix_tree_for_each_slot(slot, &root, &iter, 0) {
-                printf("slot %ld %p\n", iter.index, *slot);
+                printv(2, "slot %ld %p\n", iter.index, *slot);
                 if (first) {
                         radix_tree_insert(&root, 1, ptr);
                         first = false;
                 }
                 if (radix_tree_deref_retry(*slot)) {
-                        printk("retry at %ld\n", iter.index);
+                        printv(2, "retry at %ld\n", iter.index);
                         slot = radix_tree_iter_retry(&iter);
                         continue;
                 }
@@ -72,30 +72,30 @@ void regression3_test(void)
 
         first = true;
         radix_tree_for_each_contig(slot, &root, &iter, 0) {
-                printk("contig %ld %p\n", iter.index, *slot);
+                printv(2, "contig %ld %p\n", iter.index, *slot);
                 if (first) {
                         radix_tree_insert(&root, 1, ptr);
                         first = false;
                 }
                 if (radix_tree_deref_retry(*slot)) {
-                        printk("retry at %ld\n", iter.index);
+                        printv(2, "retry at %ld\n", iter.index);
                         slot = radix_tree_iter_retry(&iter);
                         continue;
                 }
         }
 
         radix_tree_for_each_slot(slot, &root, &iter, 0) {
-                printf("slot %ld %p\n", iter.index, *slot);
+                printv(2, "slot %ld %p\n", iter.index, *slot);
                 if (!iter.index) {
-                        printf("next at %ld\n", iter.index);
+                        printv(2, "next at %ld\n", iter.index);
                         slot = radix_tree_iter_resume(slot, &iter);
                 }
         }
 
         radix_tree_for_each_contig(slot, &root, &iter, 0) {
-                printf("contig %ld %p\n", iter.index, *slot);
+                printv(2, "contig %ld %p\n", iter.index, *slot);
                 if (!iter.index) {
-                        printf("next at %ld\n", iter.index);
+                        printv(2, "next at %ld\n", iter.index);
                         slot = radix_tree_iter_resume(slot, &iter);
                 }
         }
@@ -103,9 +103,9 @@ void regression3_test(void)
         radix_tree_tag_set(&root, 0, 0);
         radix_tree_tag_set(&root, 1, 0);
         radix_tree_for_each_tagged(slot, &root, &iter, 0, 0) {
-                printf("tagged %ld %p\n", iter.index, *slot);
+                printv(2, "tagged %ld %p\n", iter.index, *slot);
                 if (!iter.index) {
-                        printf("next at %ld\n", iter.index);
+                        printv(2, "next at %ld\n", iter.index);
                         slot = radix_tree_iter_resume(slot, &iter);
                 }
         }
@@ -113,5 +113,5 @@ void regression3_test(void)
         radix_tree_delete(&root, 0);
         radix_tree_delete(&root, 1);
 
-        printf("regression test 3 passed\n");
+        printv(1, "regression test 3 passed\n");
 }
diff --git a/tools/testing/radix-tree/tag_check.c b/tools/testing/radix-tree/tag_check.c
index fd98c132207a..36dcf7d6945d 100644
--- a/tools/testing/radix-tree/tag_check.c
+++ b/tools/testing/radix-tree/tag_check.c
@@ -49,10 +49,10 @@ void simple_checks(void)
         }
         verify_tag_consistency(&tree, 0);
         verify_tag_consistency(&tree, 1);
-        printf("before item_kill_tree: %d allocated\n", nr_allocated);
+        printv(2, "before item_kill_tree: %d allocated\n", nr_allocated);
         item_kill_tree(&tree);
         rcu_barrier();
-        printf("after item_kill_tree: %d allocated\n", nr_allocated);
+        printv(2, "after item_kill_tree: %d allocated\n", nr_allocated);
 }
 
 /*
@@ -257,7 +257,7 @@ static void do_thrash(struct radix_tree_root *tree, char *thrash_state, int tag)
 
                 gang_check(tree, thrash_state, tag);
 
-                printf("%d(%d) %d(%d) %d(%d) %d(%d) / "
+                printv(2, "%d(%d) %d(%d) %d(%d) %d(%d) / "
                                 "%d(%d) present, %d(%d) tagged\n",
                         insert_chunk, nr_inserted,
                         delete_chunk, nr_deleted,
@@ -296,13 +296,13 @@ static void __leak_check(void)
 {
         RADIX_TREE(tree, GFP_KERNEL);
 
-        printf("%d: nr_allocated=%d\n", __LINE__, nr_allocated);
+        printv(2, "%d: nr_allocated=%d\n", __LINE__, nr_allocated);
         item_insert(&tree, 1000000);
-        printf("%d: nr_allocated=%d\n", __LINE__, nr_allocated);
+        printv(2, "%d: nr_allocated=%d\n", __LINE__, nr_allocated);
         item_delete(&tree, 1000000);
-        printf("%d: nr_allocated=%d\n", __LINE__, nr_allocated);
+        printv(2, "%d: nr_allocated=%d\n", __LINE__, nr_allocated);
         item_kill_tree(&tree);
-        printf("%d: nr_allocated=%d\n", __LINE__, nr_allocated);
+        printv(2, "%d: nr_allocated=%d\n", __LINE__, nr_allocated);
 }
 
 static void single_check(void)
@@ -330,21 +330,50 @@ static void single_check(void)
         item_kill_tree(&tree);
 }
 
+void radix_tree_clear_tags_test(void)
+{
+        unsigned long index;
+        struct radix_tree_node *node;
+        struct radix_tree_iter iter;
+        void **slot;
+
+        RADIX_TREE(tree, GFP_KERNEL);
+
+        item_insert(&tree, 0);
+        item_tag_set(&tree, 0, 0);
+        __radix_tree_lookup(&tree, 0, &node, &slot);
+        radix_tree_clear_tags(&tree, node, slot);
+        assert(item_tag_get(&tree, 0, 0) == 0);
+
+        for (index = 0; index < 1000; index++) {
+                item_insert(&tree, index);
+                item_tag_set(&tree, index, 0);
+        }
+
+        radix_tree_for_each_slot(slot, &tree, &iter, 0) {
+                radix_tree_clear_tags(&tree, iter.node, slot);
+                assert(item_tag_get(&tree, iter.index, 0) == 0);
+        }
+
+        item_kill_tree(&tree);
+}
+
 void tag_check(void)
 {
         single_check();
         extend_checks();
         contract_checks();
         rcu_barrier();
-        printf("after extend_checks: %d allocated\n", nr_allocated);
+        printv(2, "after extend_checks: %d allocated\n", nr_allocated);
         __leak_check();
         leak_check();
         rcu_barrier();
-        printf("after leak_check: %d allocated\n", nr_allocated);
+        printv(2, "after leak_check: %d allocated\n", nr_allocated);
         simple_checks();
         rcu_barrier();
-        printf("after simple_checks: %d allocated\n", nr_allocated);
+        printv(2, "after simple_checks: %d allocated\n", nr_allocated);
         thrash_tags();
         rcu_barrier();
-        printf("after thrash_tags: %d allocated\n", nr_allocated);
+        printv(2, "after thrash_tags: %d allocated\n", nr_allocated);
+        radix_tree_clear_tags_test();
 }
diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index e5726e373646..1a257d738a1e 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -29,15 +29,28 @@ int __item_insert(struct radix_tree_root *root, struct item *item)
         return __radix_tree_insert(root, item->index, item->order, item);
 }
 
-int item_insert(struct radix_tree_root *root, unsigned long index)
+struct item *item_create(unsigned long index, unsigned int order)
 {
-        return __item_insert(root, item_create(index, 0));
+        struct item *ret = malloc(sizeof(*ret));
+
+        ret->index = index;
+        ret->order = order;
+        return ret;
 }
 
 int item_insert_order(struct radix_tree_root *root, unsigned long index,
                         unsigned order)
 {
-        return __item_insert(root, item_create(index, order));
+        struct item *item = item_create(index, order);
+        int err = __item_insert(root, item);
+        if (err)
+                free(item);
+        return err;
+}
+
+int item_insert(struct radix_tree_root *root, unsigned long index)
+{
+        return item_insert_order(root, index, 0);
 }
 
 void item_sanity(struct item *item, unsigned long index)
@@ -61,15 +74,6 @@ int item_delete(struct radix_tree_root *root, unsigned long index)
         return 0;
 }
 
-struct item *item_create(unsigned long index, unsigned int order)
-{
-        struct item *ret = malloc(sizeof(*ret));
-
-        ret->index = index;
-        ret->order = order;
-        return ret;
-}
-
 void item_check_present(struct radix_tree_root *root, unsigned long index)
 {
         struct item *item;
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index 056a23b56467..0f8220cc6166 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -34,6 +34,9 @@ void tag_check(void);
 void multiorder_checks(void);
 void iteration_test(unsigned order, unsigned duration);
 void benchmark(void);
+void idr_checks(void);
+void ida_checks(void);
+void ida_thread_tests(void);
 
 struct item *
 item_tag_set(struct radix_tree_root *root, unsigned long index, int tag);
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 831022b12848..d8593f1251ec 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -1,6 +1,7 @@
 TARGETS =  bpf
 TARGETS += breakpoints
 TARGETS += capabilities
+TARGETS += cpufreq
 TARGETS += cpu-hotplug
 TARGETS += efivarfs
 TARGETS += exec
@@ -8,6 +9,7 @@ TARGETS += firmware
 TARGETS += ftrace
 TARGETS += futex
 TARGETS += gpio
+TARGETS += intel_pstate
 TARGETS += ipc
 TARGETS += kcmp
 TARGETS += lib
@@ -24,6 +26,7 @@ TARGETS += ptrace
 TARGETS += seccomp
 TARGETS += sigaltstack
 TARGETS += size
+TARGETS += splice
 TARGETS += static_keys
 TARGETS += sync
 TARGETS += sysctl
@@ -49,29 +52,44 @@ override LDFLAGS =
 override MAKEFLAGS =
 endif
 
+BUILD := $(O)
+ifndef BUILD
+  BUILD := $(KBUILD_OUTPUT)
+endif
+ifndef BUILD
+  BUILD := $(shell pwd)
+endif
+
+export BUILD
 all:
-        for TARGET in $(TARGETS); do \
-                make -C $$TARGET; \
+        for TARGET in $(TARGETS); do            \
+                BUILD_TARGET=$$BUILD/$$TARGET;  \
+                mkdir $$BUILD_TARGET  -p;       \
+                make OUTPUT=$$BUILD_TARGET -C $$TARGET;\
         done;
 
 run_tests: all
         for TARGET in $(TARGETS); do \
-                make -C $$TARGET run_tests; \
+                BUILD_TARGET=$$BUILD/$$TARGET;  \
+                make OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\
         done;
 
 hotplug:
         for TARGET in $(TARGETS_HOTPLUG); do \
-                make -C $$TARGET; \
+                BUILD_TARGET=$$BUILD/$$TARGET;  \
+                make OUTPUT=$$BUILD_TARGET -C $$TARGET;\
         done;
 
 run_hotplug: hotplug
         for TARGET in $(TARGETS_HOTPLUG); do \
-                make -C $$TARGET run_full_test; \
+                BUILD_TARGET=$$BUILD/$$TARGET;  \
+                make OUTPUT=$$BUILD_TARGET -C $$TARGET run_full_test;\
         done;
 
 clean_hotplug:
         for TARGET in $(TARGETS_HOTPLUG); do \
-                make -C $$TARGET clean; \
+                BUILD_TARGET=$$BUILD/$$TARGET;  \
+                make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\
         done;
 
 run_pstore_crash:
@@ -86,7 +104,8 @@ ifdef INSTALL_PATH
         @# Ask all targets to install their files
         mkdir -p $(INSTALL_PATH)
         for TARGET in $(TARGETS); do \
-                make -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \
+                BUILD_TARGET=$$BUILD/$$TARGET;  \
+                make OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \
         done;
 
         @# Ask all targets to emit their test scripts
@@ -95,10 +114,11 @@ ifdef INSTALL_PATH
         echo "ROOT=\$$PWD" >> $(ALL_SCRIPT)
 
         for TARGET in $(TARGETS); do \
+                BUILD_TARGET=$$BUILD/$$TARGET;  \
                 echo "echo ; echo Running tests in $$TARGET" >> $(ALL_SCRIPT); \
                 echo "echo ========================================" >> $(ALL_SCRIPT); \
                 echo "cd $$TARGET" >> $(ALL_SCRIPT); \
-                make -s --no-print-directory -C $$TARGET emit_tests >> $(ALL_SCRIPT); \
+                make -s --no-print-directory OUTPUT=$$BUILD_TARGET -C $$TARGET emit_tests >> $(ALL_SCRIPT); \
                 echo "cd \$$ROOT" >> $(ALL_SCRIPT); \
         done;
 
@@ -109,7 +129,8 @@ endif
 
 clean:
         for TARGET in $(TARGETS); do \
-                make -C $$TARGET clean; \
+                BUILD_TARGET=$$BUILD/$$TARGET;  \
+                make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\
         done;
 
 .PHONY: install
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 071431bedde8..541d9d7fad5a 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -1,3 +1,5 @@
 test_verifier
 test_maps
 test_lru_map
+test_lpm_map
+test_tag
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 7a5f24543a5f..67531f47781b 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -1,13 +1,22 @@
-CFLAGS += -Wall -O2 -I../../../../usr/include
+LIBDIR := ../../../lib
+BPFOBJ := $(LIBDIR)/bpf/bpf.o
 
-test_objs = test_verifier test_maps test_lru_map
+CFLAGS += -Wall -O2 -lcap -I../../../include/uapi -I$(LIBDIR) $(BPFOBJ)
 
-TEST_PROGS := test_verifier test_maps test_lru_map test_kmod.sh
-TEST_FILES := $(test_objs)
+TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map
 
-all: $(test_objs)
+TEST_PROGS := test_kmod.sh
 
-include ../lib.mk
+all: $(TEST_GEN_PROGS)
+
+.PHONY: all clean force
+
+# force a rebuild of BPFOBJ when its dependencies are updated
+force:
 
-clean:
-        $(RM) $(test_objs)
+$(BPFOBJ): force
+        $(MAKE) -C $(dir $(BPFOBJ))
+
+$(test_objs): $(BPFOBJ)
+
+include ../lib.mk
diff --git a/tools/testing/selftests/bpf/bpf_sys.h b/tools/testing/selftests/bpf/bpf_sys.h
deleted file mode 100644
index 6b4565f2a3f2..000000000000
--- a/tools/testing/selftests/bpf/bpf_sys.h
+++ /dev/null
@@ -1,108 +0,0 @@
-#ifndef __BPF_SYS__
-#define __BPF_SYS__
-
-#include <stdint.h>
-#include <stdlib.h>
-
-#include <sys/syscall.h>
-
-#include <linux/bpf.h>
-
-static inline __u64 bpf_ptr_to_u64(const void *ptr)
-{
-        return (__u64)(unsigned long) ptr;
-}
-
-static inline int bpf(int cmd, union bpf_attr *attr, unsigned int size)
-{
-#ifdef __NR_bpf
-        return syscall(__NR_bpf, cmd, attr, size);
-#else
-        fprintf(stderr, "No bpf syscall, kernel headers too old?\n");
-        errno = ENOSYS;
-        return -1;
-#endif
-}
-
-static inline int bpf_map_lookup(int fd, const void *key, void *value)
-{
-        union bpf_attr attr = {};
-
-        attr.map_fd = fd;
-        attr.key = bpf_ptr_to_u64(key);
-        attr.value = bpf_ptr_to_u64(value);
-
-        return bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
-}
-
-static inline int bpf_map_update(int fd, const void *key, const void *value,
-                                 uint64_t flags)
-{
-        union bpf_attr attr = {};
-
-        attr.map_fd = fd;
-        attr.key = bpf_ptr_to_u64(key);
-        attr.value = bpf_ptr_to_u64(value);
-        attr.flags = flags;
-
-        return bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
-}
-
-static inline int bpf_map_delete(int fd, const void *key)
-{
-        union bpf_attr attr = {};
-
-        attr.map_fd = fd;
-        attr.key = bpf_ptr_to_u64(key);
-
-        return bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
-}
-
-static inline int bpf_map_next_key(int fd, const void *key, void *next_key)
-{
-        union bpf_attr attr = {};
-
-        attr.map_fd = fd;
-        attr.key = bpf_ptr_to_u64(key);
-        attr.next_key = bpf_ptr_to_u64(next_key);
-
-        return bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr));
-}
-
-static inline int bpf_map_create(enum bpf_map_type type, uint32_t size_key,
-                                 uint32_t size_value, uint32_t max_elem,
-                                 uint32_t flags)
-{
-        union bpf_attr attr = {};
-
-        attr.map_type = type;
-        attr.key_size = size_key;
-        attr.value_size = size_value;
-        attr.max_entries = max_elem;
-        attr.map_flags = flags;
-
-        return bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
-}
-
-static inline int bpf_prog_load(enum bpf_prog_type type,
-                                const struct bpf_insn *insns, size_t size_insns,
-                                const char *license, char *log, size_t size_log)
-{
-        union bpf_attr attr = {};
-
-        attr.prog_type = type;
-        attr.insns = bpf_ptr_to_u64(insns);
-        attr.insn_cnt = size_insns / sizeof(struct bpf_insn);
-        attr.license = bpf_ptr_to_u64(license);
-
-        if (size_log > 0) {
-                attr.log_buf = bpf_ptr_to_u64(log);
-                attr.log_size = size_log;
-                attr.log_level = 1;
-                log[0] = 0;
-        }
-
-        return bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
-}
-
-#endif /* __BPF_SYS__ */
diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c
new file mode 100644
index 000000000000..e97565243d59
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_lpm_map.c
@@ -0,0 +1,358 @@
+/*
+ * Randomized tests for eBPF longest-prefix-match maps
+ *
+ * This program runs randomized tests against the lpm-bpf-map. It implements a
+ * "Trivial Longest Prefix Match" (tlpm) based on simple, linear, singly linked
+ * lists. The implementation should be pretty straightforward.
+ *
+ * Based on tlpm, this inserts randomized data into bpf-lpm-maps and verifies
+ * the trie-based bpf-map implementation behaves the same way as tlpm.
+ */
+
+#include <assert.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <linux/bpf.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+
+#include <bpf/bpf.h>
+#include "bpf_util.h"
+
+struct tlpm_node {
+        struct tlpm_node *next;
+        size_t n_bits;
+        uint8_t key[];
+};
+
+static struct tlpm_node *tlpm_add(struct tlpm_node *list,
+                                  const uint8_t *key,
+                                  size_t n_bits)
+{
+        struct tlpm_node *node;
+        size_t n;
+
+        /* add new entry with @key/@n_bits to @list and return new head */
+
+        n = (n_bits + 7) / 8;
+        node = malloc(sizeof(*node) + n);
+        assert(node);
+
+        node->next = list;
+        node->n_bits = n_bits;
+        memcpy(node->key, key, n);
+
+        return node;
+}
+
+static void tlpm_clear(struct tlpm_node *list)
+{
+        struct tlpm_node *node;
+
+        /* free all entries in @list */
+
+        while ((node = list)) {
+                list = list->next;
+                free(node);
+        }
+}
+
+static struct tlpm_node *tlpm_match(struct tlpm_node *list,
+                                    const uint8_t *key,
+                                    size_t n_bits)
+{
+        struct tlpm_node *best = NULL;
+        size_t i;
+
+        /* Perform longest prefix-match on @key/@n_bits. That is, iterate all
+         * entries and match each prefix against @key. Remember the "best"
+         * entry we find (i.e., the longest prefix that matches) and return it
+         * to the caller when done.
+         */
+
+        for ( ; list; list = list->next) {
+                for (i = 0; i < n_bits && i < list->n_bits; ++i) {
+                        if ((key[i / 8] & (1 << (7 - i % 8))) !=
+                            (list->key[i / 8] & (1 << (7 - i % 8))))
+                                break;
+                }
+
+                if (i >= list->n_bits) {
+                        if (!best || i > best->n_bits)
+                                best = list;
+                }
+        }
+
+        return best;
+}
+
+static void test_lpm_basic(void)
+{
+        struct tlpm_node *list = NULL, *t1, *t2;
+
+        /* very basic, static tests to verify tlpm works as expected */
+
+        assert(!tlpm_match(list, (uint8_t[]){ 0xff }, 8));
+
+        t1 = list = tlpm_add(list, (uint8_t[]){ 0xff }, 8);
+        assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff }, 8));
+        assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 16));
+        assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0x00 }, 16));
+        assert(!tlpm_match(list, (uint8_t[]){ 0x7f }, 8));
+        assert(!tlpm_match(list, (uint8_t[]){ 0xfe }, 8));
+        assert(!tlpm_match(list, (uint8_t[]){ 0xff }, 7));
+
+        t2 = list = tlpm_add(list, (uint8_t[]){ 0xff, 0xff }, 16);
+        assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff }, 8));
+        assert(t2 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 16));
+        assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 15));
+        assert(!tlpm_match(list, (uint8_t[]){ 0x7f, 0xff }, 16));
+
+        tlpm_clear(list);
+}
+
+static void test_lpm_order(void)
+{
+        struct tlpm_node *t1, *t2, *l1 = NULL, *l2 = NULL;
+        size_t i, j;
+
+        /* Verify the tlpm implementation works correctly regardless of the
+         * order of entries. Insert a random set of entries into @l1, and copy
+         * the same data in reverse order into @l2. Then verify a lookup of
+         * random keys will yield the same result in both sets.
+         */
+
+        for (i = 0; i < (1 << 12); ++i)
+                l1 = tlpm_add(l1, (uint8_t[]){
+                                        rand() % 0xff,
+                                        rand() % 0xff,
+                                }, rand() % 16 + 1);
+
+        for (t1 = l1; t1; t1 = t1->next)
+                l2 = tlpm_add(l2, t1->key, t1->n_bits);
+
+        for (i = 0; i < (1 << 8); ++i) {
+                uint8_t key[] = { rand() % 0xff, rand() % 0xff };
+
+                t1 = tlpm_match(l1, key, 16);
+                t2 = tlpm_match(l2, key, 16);
+
+                assert(!t1 == !t2);
+                if (t1) {
+                        assert(t1->n_bits == t2->n_bits);
+                        for (j = 0; j < t1->n_bits; ++j)
+                                assert((t1->key[j / 8] & (1 << (7 - j % 8))) ==
+                                       (t2->key[j / 8] & (1 << (7 - j % 8))));
+                }
+        }
+
+        tlpm_clear(l1);
+        tlpm_clear(l2);
+}
+
+static void test_lpm_map(int keysize)
+{
+        size_t i, j, n_matches, n_nodes, n_lookups;
+        struct tlpm_node *t, *list = NULL;
+        struct bpf_lpm_trie_key *key;
+        uint8_t *data, *value;
+        int r, map;
+
+        /* Compare behavior of tlpm vs. bpf-lpm. Create a randomized set of
+         * prefixes and insert it into both tlpm and bpf-lpm. Then run some
+         * randomized lookups and verify both maps return the same result.
+         */
+
+        n_matches = 0;
+        n_nodes = 1 << 8;
+        n_lookups = 1 << 16;
+
+        data = alloca(keysize);
+        memset(data, 0, keysize);
+
+        value = alloca(keysize + 1);
+        memset(value, 0, keysize + 1);
+
+        key = alloca(sizeof(*key) + keysize);
+        memset(key, 0, sizeof(*key) + keysize);
+
+        map = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE,
+                             sizeof(*key) + keysize,
+                             keysize + 1,
+                             4096,
+                             BPF_F_NO_PREALLOC);
+        assert(map >= 0);
+
+        for (i = 0; i < n_nodes; ++i) {
+                for (j = 0; j < keysize; ++j)
+                        value[j] = rand() & 0xff;
+                value[keysize] = rand() % (8 * keysize + 1);
+
+                list = tlpm_add(list, value, value[keysize]);
+
+                key->prefixlen = value[keysize];
+                memcpy(key->data, value, keysize);
+                r = bpf_map_update_elem(map, key, value, 0);
+                assert(!r);
+        }
+
+        for (i = 0; i < n_lookups; ++i) {
+                for (j = 0; j < keysize; ++j)
+                        data[j] = rand() & 0xff;
+
+                t = tlpm_match(list, data, 8 * keysize);
+
+                key->prefixlen = 8 * keysize;
+                memcpy(key->data, data, keysize);
+                r = bpf_map_lookup_elem(map, key, value);
+                assert(!r || errno == ENOENT);
+                assert(!t == !!r);
+
+                if (t) {
+                        ++n_matches;
+                        assert(t->n_bits == value[keysize]);
+                        for (j = 0; j < t->n_bits; ++j)
+                                assert((t->key[j / 8] & (1 << (7 - j % 8))) ==
+                                       (value[j / 8] & (1 << (7 - j % 8))));
+                }
+        }
+
+        close(map);
+        tlpm_clear(list);
+
+        /* With 255 random nodes in the map, we are pretty likely to match
+         * something on every lookup. For statistics, use this:
+         *
+         *     printf("  nodes: %zu\n"
+         *            "lookups: %zu\n"
+         *            "matches: %zu\n", n_nodes, n_lookups, n_matches);
+         */
+}
+
+/* Test the implementation with some 'real world' examples */
+
+static void test_lpm_ipaddr(void)
+{
+        struct bpf_lpm_trie_key *key_ipv4;
+        struct bpf_lpm_trie_key *key_ipv6;
+        size_t key_size_ipv4;
+        size_t key_size_ipv6;
+        int map_fd_ipv4;
+        int map_fd_ipv6;
+        __u64 value;
+
+        key_size_ipv4 = sizeof(*key_ipv4) + sizeof(__u32);
+        key_size_ipv6 = sizeof(*key_ipv6) + sizeof(__u32) * 4;
+        key_ipv4 = alloca(key_size_ipv4);
+        key_ipv6 = alloca(key_size_ipv6);
+
+        map_fd_ipv4 = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE,
+                                     key_size_ipv4, sizeof(value),
+                                     100, BPF_F_NO_PREALLOC);
+        assert(map_fd_ipv4 >= 0);
+
+        map_fd_ipv6 = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE,
+                                     key_size_ipv6, sizeof(value),
+                                     100, BPF_F_NO_PREALLOC);
+        assert(map_fd_ipv6 >= 0);
+
+        /* Fill data some IPv4 and IPv6 address ranges */
+        value = 1;
+        key_ipv4->prefixlen = 16;
+        inet_pton(AF_INET, "192.168.0.0", key_ipv4->data);
+        assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0);
+
+        value = 2;
+        key_ipv4->prefixlen = 24;
+        inet_pton(AF_INET, "192.168.0.0", key_ipv4->data);
+        assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0);
+
+        value = 3;
+        key_ipv4->prefixlen = 24;
+        inet_pton(AF_INET, "192.168.128.0", key_ipv4->data);
+        assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0);
+
+        value = 5;
+        key_ipv4->prefixlen = 24;
+        inet_pton(AF_INET, "192.168.1.0", key_ipv4->data);
+        assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0);
+
+        value = 4;
+        key_ipv4->prefixlen = 23;
+        inet_pton(AF_INET, "192.168.0.0", key_ipv4->data);
+        assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0);
+
+        value = 0xdeadbeef;
+        key_ipv6->prefixlen = 64;
+        inet_pton(AF_INET6, "2a00:1450:4001:814::200e", key_ipv6->data);
+        assert(bpf_map_update_elem(map_fd_ipv6, key_ipv6, &value, 0) == 0);
+
+        /* Set tprefixlen to maximum for lookups */
+        key_ipv4->prefixlen = 32;
+        key_ipv6->prefixlen = 128;
+
+        /* Test some lookups that should come back with a value */
+        inet_pton(AF_INET, "192.168.128.23", key_ipv4->data);
+        assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == 0);
+        assert(value == 3);
+
+        inet_pton(AF_INET, "192.168.0.1", key_ipv4->data);
+        assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == 0);
+        assert(value == 2);
+
+        inet_pton(AF_INET6, "2a00:1450:4001:814::", key_ipv6->data);
+        assert(bpf_map_lookup_elem(map_fd_ipv6, key_ipv6, &value) == 0);
+        assert(value == 0xdeadbeef);
+
+        inet_pton(AF_INET6, "2a00:1450:4001:814::1", key_ipv6->data);
+        assert(bpf_map_lookup_elem(map_fd_ipv6, key_ipv6, &value) == 0);
+        assert(value == 0xdeadbeef);
+
+        /* Test some lookups that should not match any entry */
+        inet_pton(AF_INET, "10.0.0.1", key_ipv4->data);
+        assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == -1 &&
+               errno == ENOENT);
+
+        inet_pton(AF_INET, "11.11.11.11", key_ipv4->data);
+        assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == -1 &&
+               errno == ENOENT);
+
+        inet_pton(AF_INET6, "2a00:ffff::", key_ipv6->data);
+        assert(bpf_map_lookup_elem(map_fd_ipv6, key_ipv6, &value) == -1 &&
+               errno == ENOENT);
+
+        close(map_fd_ipv4);
+        close(map_fd_ipv6);
+}
+
+int main(void)
+{
+        struct rlimit limit  = { RLIM_INFINITY, RLIM_INFINITY };
+        int i, ret;
+
+        /* we want predictable, pseudo random tests */
+        srand(0xf00ba1);
+
+        /* allow unlimited locked memory */
+        ret = setrlimit(RLIMIT_MEMLOCK, &limit);
+        if (ret < 0)
+                perror("Unable to lift memlock rlimit");
+
+        test_lpm_basic();
+        test_lpm_order();
+
+        /* Test with 8, 16, 24, 32, ... 128 bit prefix length */
+        for (i = 1; i <= 16; ++i)
+                test_lpm_map(i);
+
+        test_lpm_ipaddr();
+
+        printf("test_lpm: OK\n");
+        return 0;
+}
diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c
index 9f7bd1915c21..00b0aff56e2e 100644
--- a/tools/testing/selftests/bpf/test_lru_map.c
+++ b/tools/testing/selftests/bpf/test_lru_map.c
@@ -18,7 +18,7 @@
 #include <sys/wait.h>
 #include <sys/resource.h>
 
-#include "bpf_sys.h"
+#include <bpf/bpf.h>
 #include "bpf_util.h"
 
 #define LOCAL_FREE_TARGET       (128)
@@ -30,11 +30,11 @@ static int create_map(int map_type, int map_flags, unsigned int size)
 {
         int map_fd;
 
-        map_fd = bpf_map_create(map_type, sizeof(unsigned long long),
+        map_fd = bpf_create_map(map_type, sizeof(unsigned long long),
                                 sizeof(unsigned long long), size, map_flags);
 
         if (map_fd == -1)
-                perror("bpf_map_create");
+                perror("bpf_create_map");
 
         return map_fd;
 }
@@ -45,9 +45,9 @@ static int map_subset(int map0, int map1)
         unsigned long long value0[nr_cpus], value1[nr_cpus];
         int ret;
 
-        while (!bpf_map_next_key(map1, &next_key, &next_key)) {
-                assert(!bpf_map_lookup(map1, &next_key, value1));
-                ret = bpf_map_lookup(map0, &next_key, value0);
+        while (!bpf_map_get_next_key(map1, &next_key, &next_key)) {
+                assert(!bpf_map_lookup_elem(map1, &next_key, value1));
+                ret = bpf_map_lookup_elem(map0, &next_key, value0);
                 if (ret) {
                         printf("key:%llu not found from map. %s(%d)\n",
                                next_key, strerror(errno), errno);
@@ -119,52 +119,54 @@ static void test_lru_sanity0(int map_type, int map_flags)
         /* insert key=1 element */
 
         key = 1;
-        assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
-        assert(!bpf_map_update(expected_map_fd, &key, value, BPF_NOEXIST));
+        assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST));
+        assert(!bpf_map_update_elem(expected_map_fd, &key, value,
+                                    BPF_NOEXIST));
 
         /* BPF_NOEXIST means: add new element if it doesn't exist */
-        assert(bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST) == -1 &&
+        assert(bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST) == -1
                /* key=1 already exists */
-               errno == EEXIST);
+               && errno == EEXIST);
 
-        assert(bpf_map_update(lru_map_fd, &key, value, -1) == -1 &&
+        assert(bpf_map_update_elem(lru_map_fd, &key, value, -1) == -1 &&
                errno == EINVAL);
 
         /* insert key=2 element */
 
         /* check that key=2 is not found */
         key = 2;
-        assert(bpf_map_lookup(lru_map_fd, &key, value) == -1 &&
+        assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1 &&
                errno == ENOENT);
 
         /* BPF_EXIST means: update existing element */
-        assert(bpf_map_update(lru_map_fd, &key, value, BPF_EXIST) == -1 &&
+        assert(bpf_map_update_elem(lru_map_fd, &key, value, BPF_EXIST) == -1 &&
                /* key=2 is not there */
                errno == ENOENT);
 
-        assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+        assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST));
 
         /* insert key=3 element */
 
         /* check that key=3 is not found */
         key = 3;
-        assert(bpf_map_lookup(lru_map_fd, &key, value) == -1 &&
+        assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1 &&
                errno == ENOENT);
 
         /* check that key=1 can be found and mark the ref bit to
          * stop LRU from removing key=1
          */
         key = 1;
-        assert(!bpf_map_lookup(lru_map_fd, &key, value));
+        assert(!bpf_map_lookup_elem(lru_map_fd, &key, value));
         assert(value[0] == 1234);
 
         key = 3;
-        assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
-        assert(!bpf_map_update(expected_map_fd, &key, value, BPF_NOEXIST));
+        assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST));
+        assert(!bpf_map_update_elem(expected_map_fd, &key, value,
+                                    BPF_NOEXIST));
 
         /* key=2 has been removed from the LRU */
         key = 2;
-        assert(bpf_map_lookup(lru_map_fd, &key, value) == -1);
+        assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1);
 
         assert(map_equal(lru_map_fd, expected_map_fd));
 
@@ -217,14 +219,15 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
         /* Insert 1 to tgt_free (+tgt_free keys) */
         end_key = 1 + tgt_free;
         for (key = 1; key < end_key; key++)
-                assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+                assert(!bpf_map_update_elem(lru_map_fd, &key, value,
+                                            BPF_NOEXIST));
 
         /* Lookup 1 to tgt_free/2 */
         end_key = 1 + batch_size;
         for (key = 1; key < end_key; key++) {
-                assert(!bpf_map_lookup(lru_map_fd, &key, value));
-                assert(!bpf_map_update(expected_map_fd, &key, value,
-                                       BPF_NOEXIST));
+                assert(!bpf_map_lookup_elem(lru_map_fd, &key, value));
+                assert(!bpf_map_update_elem(expected_map_fd, &key, value,
+                                            BPF_NOEXIST));
         }
 
         /* Insert 1+tgt_free to 2*tgt_free
@@ -234,9 +237,10 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
         key = 1 + tgt_free;
         end_key = key + tgt_free;
         for (; key < end_key; key++) {
-                assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
-                assert(!bpf_map_update(expected_map_fd, &key, value,
-                                       BPF_NOEXIST));
+                assert(!bpf_map_update_elem(lru_map_fd, &key, value,
+                                            BPF_NOEXIST));
+                assert(!bpf_map_update_elem(expected_map_fd, &key, value,
+                                            BPF_NOEXIST));
         }
 
         assert(map_equal(lru_map_fd, expected_map_fd));
@@ -301,9 +305,10 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
         /* Insert 1 to tgt_free (+tgt_free keys) */
         end_key = 1 + tgt_free;
         for (key = 1; key < end_key; key++)
-                assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+                assert(!bpf_map_update_elem(lru_map_fd, &key, value,
+                                            BPF_NOEXIST));
 
-        /* Any bpf_map_update will require to acquire a new node
+        /* Any bpf_map_update_elem will require to acquire a new node
          * from LRU first.
          *
          * The local list is running out of free nodes.
@@ -316,10 +321,12 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
          */
         key = 1;
         if (map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
-                assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
-                assert(!bpf_map_delete(lru_map_fd, &key));
+                assert(!bpf_map_update_elem(lru_map_fd, &key, value,
+                                            BPF_NOEXIST));
+                assert(!bpf_map_delete_elem(lru_map_fd, &key));
         } else {
-                assert(bpf_map_update(lru_map_fd, &key, value, BPF_EXIST));
+                assert(bpf_map_update_elem(lru_map_fd, &key, value,
+                                           BPF_EXIST));
         }
 
         /* Re-insert 1 to tgt_free/2 again and do a lookup
@@ -328,12 +335,13 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
         end_key = 1 + batch_size;
         value[0] = 4321;
         for (key = 1; key < end_key; key++) {
-                assert(bpf_map_lookup(lru_map_fd, &key, value));
-                assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
-                assert(!bpf_map_lookup(lru_map_fd, &key, value));
+                assert(bpf_map_lookup_elem(lru_map_fd, &key, value));
+                assert(!bpf_map_update_elem(lru_map_fd, &key, value,
+                                            BPF_NOEXIST));
+                assert(!bpf_map_lookup_elem(lru_map_fd, &key, value));
                 assert(value[0] == 4321);
-                assert(!bpf_map_update(expected_map_fd, &key, value,
-                                       BPF_NOEXIST));
+                assert(!bpf_map_update_elem(expected_map_fd, &key, value,
+                                            BPF_NOEXIST));
         }
 
         value[0] = 1234;
@@ -344,14 +352,16 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
                 /* These newly added but not referenced keys will be
                  * gone during the next LRU shrink.
                  */
-                assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+                assert(!bpf_map_update_elem(lru_map_fd, &key, value,
+                                            BPF_NOEXIST));
 
         /* Insert 1+tgt_free*3/2 to  tgt_free*5/2 */
         end_key = key + tgt_free;
         for (; key < end_key; key++) {
-                assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
-                assert(!bpf_map_update(expected_map_fd, &key, value,
-                                       BPF_NOEXIST));
+                assert(!bpf_map_update_elem(lru_map_fd, &key, value,
+                                            BPF_NOEXIST));
+                assert(!bpf_map_update_elem(expected_map_fd, &key, value,
+                                            BPF_NOEXIST));
         }
 
         assert(map_equal(lru_map_fd, expected_map_fd));
@@ -401,14 +411,15 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
         /* Insert 1 to 2*tgt_free (+2*tgt_free keys) */
         end_key = 1 + (2 * tgt_free);
         for (key = 1; key < end_key; key++)
-                assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+                assert(!bpf_map_update_elem(lru_map_fd, &key, value,
+                                            BPF_NOEXIST));
 
         /* Lookup key 1 to tgt_free*3/2 */
         end_key = tgt_free + batch_size;
         for (key = 1; key < end_key; key++) {
-                assert(!bpf_map_lookup(lru_map_fd, &key, value));
-                assert(!bpf_map_update(expected_map_fd, &key, value,
-                                       BPF_NOEXIST));
+                assert(!bpf_map_lookup_elem(lru_map_fd, &key, value));
+                assert(!bpf_map_update_elem(expected_map_fd, &key, value,
+                                            BPF_NOEXIST));
         }
 
         /* Add 1+2*tgt_free to tgt_free*5/2
@@ -417,9 +428,10 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
         key = 2 * tgt_free + 1;
         end_key = key + batch_size;
         for (; key < end_key; key++) {
-                assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
-                assert(!bpf_map_update(expected_map_fd, &key, value,
-                                       BPF_NOEXIST));
+                assert(!bpf_map_update_elem(lru_map_fd, &key, value,
+                                            BPF_NOEXIST));
+                assert(!bpf_map_update_elem(expected_map_fd, &key, value,
+                                            BPF_NOEXIST));
         }
 
         assert(map_equal(lru_map_fd, expected_map_fd));
@@ -457,27 +469,29 @@ static void test_lru_sanity4(int map_type, int map_flags, unsigned int tgt_free)
         value[0] = 1234;
 
         for (key = 1; key <= 2 * tgt_free; key++)
-                assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+                assert(!bpf_map_update_elem(lru_map_fd, &key, value,
+                                            BPF_NOEXIST));
 
         key = 1;
-        assert(bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+        assert(bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST));
 
         for (key = 1; key <= tgt_free; key++) {
-                assert(!bpf_map_lookup(lru_map_fd, &key, value));
-                assert(!bpf_map_update(expected_map_fd, &key, value,
-                                       BPF_NOEXIST));
+                assert(!bpf_map_lookup_elem(lru_map_fd, &key, value));
+                assert(!bpf_map_update_elem(expected_map_fd, &key, value,
+                                            BPF_NOEXIST));
         }
 
         for (; key <= 2 * tgt_free; key++) {
-                assert(!bpf_map_delete(lru_map_fd, &key));
-                assert(bpf_map_delete(lru_map_fd, &key));
+                assert(!bpf_map_delete_elem(lru_map_fd, &key));
+                assert(bpf_map_delete_elem(lru_map_fd, &key));
         }
 
         end_key = key + 2 * tgt_free;
         for (; key < end_key; key++) {
-                assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
-                assert(!bpf_map_update(expected_map_fd, &key, value,
-                                       BPF_NOEXIST));
+                assert(!bpf_map_update_elem(lru_map_fd, &key, value,
+                                            BPF_NOEXIST));
+                assert(!bpf_map_update_elem(expected_map_fd, &key, value,
+                                            BPF_NOEXIST));
         }
 
         assert(map_equal(lru_map_fd, expected_map_fd));
@@ -493,16 +507,16 @@ static void do_test_lru_sanity5(unsigned long long last_key, int map_fd)
         unsigned long long key, value[nr_cpus];
 
         /* Ensure the last key inserted by previous CPU can be found */
-        assert(!bpf_map_lookup(map_fd, &last_key, value));
+        assert(!bpf_map_lookup_elem(map_fd, &last_key, value));
 
         value[0] = 1234;
 
         key = last_key + 1;
-        assert(!bpf_map_update(map_fd, &key, value, BPF_NOEXIST));
-        assert(!bpf_map_lookup(map_fd, &key, value));
+        assert(!bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST));
+        assert(!bpf_map_lookup_elem(map_fd, &key, value));
 
         /* Cannot find the last key because it was removed by LRU */
-        assert(bpf_map_lookup(map_fd, &last_key, value));
+        assert(bpf_map_lookup_elem(map_fd, &last_key, value));
 }
 
 /* Test map with only one element */
@@ -523,7 +537,7 @@ static void test_lru_sanity5(int map_type, int map_flags)
 
         value[0] = 1234;
         key = 0;
-        assert(!bpf_map_update(map_fd, &key, value, BPF_NOEXIST));
+        assert(!bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST));
 
         while (sched_next_online(0, &next_cpu) != -1) {
                 pid_t pid;
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index eedfef8d2946..cada17ac00b8 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -21,7 +21,7 @@
 
 #include <linux/bpf.h>
 
-#include "bpf_sys.h"
+#include <bpf/bpf.h>
 #include "bpf_util.h"
 
 static int map_flags;
@@ -31,7 +31,7 @@ static void test_hashmap(int task, void *data)
         long long key, next_key, value;
         int fd;
 
-        fd = bpf_map_create(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
+        fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
                             2, map_flags);
         if (fd < 0) {
                 printf("Failed to create hashmap '%s'!\n", strerror(errno));
@@ -41,69 +41,70 @@ static void test_hashmap(int task, void *data)
         key = 1;
         value = 1234;
         /* Insert key=1 element. */
-        assert(bpf_map_update(fd, &key, &value, BPF_ANY) == 0);
+        assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0);
 
         value = 0;
         /* BPF_NOEXIST means add new element if it doesn't exist. */
-        assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == -1 &&
+        assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 &&
                /* key=1 already exists. */
                errno == EEXIST);
 
         /* -1 is an invalid flag. */
-        assert(bpf_map_update(fd, &key, &value, -1) == -1 && errno == EINVAL);
+        assert(bpf_map_update_elem(fd, &key, &value, -1) == -1 &&
+               errno == EINVAL);
 
         /* Check that key=1 can be found. */
-        assert(bpf_map_lookup(fd, &key, &value) == 0 && value == 1234);
+        assert(bpf_map_lookup_elem(fd, &key, &value) == 0 && value == 1234);
 
         key = 2;
         /* Check that key=2 is not found. */
-        assert(bpf_map_lookup(fd, &key, &value) == -1 && errno == ENOENT);
+        assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT);
 
         /* BPF_EXIST means update existing element. */
-        assert(bpf_map_update(fd, &key, &value, BPF_EXIST) == -1 &&
+        assert(bpf_map_update_elem(fd, &key, &value, BPF_EXIST) == -1 &&
                /* key=2 is not there. */
                errno == ENOENT);
 
         /* Insert key=2 element. */
-        assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == 0);
+        assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == 0);
 
         /* key=1 and key=2 were inserted, check that key=0 cannot be
          * inserted due to max_entries limit.
          */
         key = 0;
-        assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == -1 &&
+        assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 &&
                errno == E2BIG);
 
         /* Update existing element, though the map is full. */
         key = 1;
-        assert(bpf_map_update(fd, &key, &value, BPF_EXIST) == 0);
+        assert(bpf_map_update_elem(fd, &key, &value, BPF_EXIST) == 0);
         key = 2;
-        assert(bpf_map_update(fd, &key, &value, BPF_ANY) == 0);
+        assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0);
         key = 1;
-        assert(bpf_map_update(fd, &key, &value, BPF_ANY) == 0);
+        assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0);
 
         /* Check that key = 0 doesn't exist. */
         key = 0;
-        assert(bpf_map_delete(fd, &key) == -1 && errno == ENOENT);
+        assert(bpf_map_delete_elem(fd, &key) == -1 && errno == ENOENT);
 
         /* Iterate over two elements. */
-        assert(bpf_map_next_key(fd, &key, &next_key) == 0 &&
+        assert(bpf_map_get_next_key(fd, &key, &next_key) == 0 &&
                (next_key == 1 || next_key == 2));
-        assert(bpf_map_next_key(fd, &next_key, &next_key) == 0 &&
+        assert(bpf_map_get_next_key(fd, &next_key, &next_key) == 0 &&
                (next_key == 1 || next_key == 2));
-        assert(bpf_map_next_key(fd, &next_key, &next_key) == -1 &&
+        assert(bpf_map_get_next_key(fd, &next_key, &next_key) == -1 &&
                errno == ENOENT);
 
         /* Delete both elements. */
         key = 1;
-        assert(bpf_map_delete(fd, &key) == 0);
+        assert(bpf_map_delete_elem(fd, &key) == 0);
         key = 2;
-        assert(bpf_map_delete(fd, &key) == 0);
-        assert(bpf_map_delete(fd, &key) == -1 && errno == ENOENT);
+        assert(bpf_map_delete_elem(fd, &key) == 0);
+        assert(bpf_map_delete_elem(fd, &key) == -1 && errno == ENOENT);
 
         key = 0;
         /* Check that map is empty. */
-        assert(bpf_map_next_key(fd, &key, &next_key) == -1 &&
+        assert(bpf_map_get_next_key(fd, &key, &next_key) == -1 &&
                errno == ENOENT);
 
         close(fd);
@@ -117,7 +118,7 @@ static void test_hashmap_percpu(int task, void *data)
         int expected_key_mask = 0;
         int fd, i;
 
-        fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_HASH, sizeof(key),
+        fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_HASH, sizeof(key),
                             sizeof(value[0]), 2, map_flags);
         if (fd < 0) {
                 printf("Failed to create hashmap '%s'!\n", strerror(errno));
@@ -130,53 +131,54 @@ static void test_hashmap_percpu(int task, void *data)
         key = 1;
         /* Insert key=1 element. */
         assert(!(expected_key_mask & key));
-        assert(bpf_map_update(fd, &key, value, BPF_ANY) == 0);
+        assert(bpf_map_update_elem(fd, &key, value, BPF_ANY) == 0);
         expected_key_mask |= key;
 
         /* BPF_NOEXIST means add new element if it doesn't exist. */
-        assert(bpf_map_update(fd, &key, value, BPF_NOEXIST) == -1 &&
+        assert(bpf_map_update_elem(fd, &key, value, BPF_NOEXIST) == -1 &&
                /* key=1 already exists. */
                errno == EEXIST);
 
         /* -1 is an invalid flag. */
-        assert(bpf_map_update(fd, &key, value, -1) == -1 && errno == EINVAL);
+        assert(bpf_map_update_elem(fd, &key, value, -1) == -1 &&
+               errno == EINVAL);
 
         /* Check that key=1 can be found. Value could be 0 if the lookup
          * was run from a different CPU.
          */
         value[0] = 1;
-        assert(bpf_map_lookup(fd, &key, value) == 0 && value[0] == 100);
+        assert(bpf_map_lookup_elem(fd, &key, value) == 0 && value[0] == 100);
 
         key = 2;
         /* Check that key=2 is not found. */
-        assert(bpf_map_lookup(fd, &key, value) == -1 && errno == ENOENT);
+        assert(bpf_map_lookup_elem(fd, &key, value) == -1 && errno == ENOENT);
 
         /* BPF_EXIST means update existing element. */
-        assert(bpf_map_update(fd, &key, value, BPF_EXIST) == -1 &&
+        assert(bpf_map_update_elem(fd, &key, value, BPF_EXIST) == -1 &&
                /* key=2 is not there. */
                errno == ENOENT);
 
         /* Insert key=2 element. */
         assert(!(expected_key_mask & key));
-        assert(bpf_map_update(fd, &key, value, BPF_NOEXIST) == 0);
+        assert(bpf_map_update_elem(fd, &key, value, BPF_NOEXIST) == 0);
         expected_key_mask |= key;
 
         /* key=1 and key=2 were inserted, check that key=0 cannot be
          * inserted due to max_entries limit.
          */
         key = 0;
-        assert(bpf_map_update(fd, &key, value, BPF_NOEXIST) == -1 &&
+        assert(bpf_map_update_elem(fd, &key, value, BPF_NOEXIST) == -1 &&
                errno == E2BIG);
 
         /* Check that key = 0 doesn't exist. */
-        assert(bpf_map_delete(fd, &key) == -1 && errno == ENOENT);
+        assert(bpf_map_delete_elem(fd, &key) == -1 && errno == ENOENT);
 
         /* Iterate over two elements. */
-        while (!bpf_map_next_key(fd, &key, &next_key)) {
+        while (!bpf_map_get_next_key(fd, &key, &next_key)) {
                 assert((expected_key_mask & next_key) == next_key);
                 expected_key_mask &= ~next_key;
 
-                assert(bpf_map_lookup(fd, &next_key, value) == 0);
+                assert(bpf_map_lookup_elem(fd, &next_key, value) == 0);
 
                 for (i = 0; i < nr_cpus; i++)
                         assert(value[i] == i + 100);
@@ -187,18 +189,18 @@ static void test_hashmap_percpu(int task, void *data)
 
         /* Update with BPF_EXIST. */
         key = 1;
-        assert(bpf_map_update(fd, &key, value, BPF_EXIST) == 0);
+        assert(bpf_map_update_elem(fd, &key, value, BPF_EXIST) == 0);
 
         /* Delete both elements. */
         key = 1;
-        assert(bpf_map_delete(fd, &key) == 0);
+        assert(bpf_map_delete_elem(fd, &key) == 0);
         key = 2;
-        assert(bpf_map_delete(fd, &key) == 0);
-        assert(bpf_map_delete(fd, &key) == -1 && errno == ENOENT);
+        assert(bpf_map_delete_elem(fd, &key) == 0);
+        assert(bpf_map_delete_elem(fd, &key) == -1 && errno == ENOENT);
 
         key = 0;
         /* Check that map is empty. */
-        assert(bpf_map_next_key(fd, &key, &next_key) == -1 &&
+        assert(bpf_map_get_next_key(fd, &key, &next_key) == -1 &&
                errno == ENOENT);
 
         close(fd);
@@ -209,7 +211,7 @@ static void test_arraymap(int task, void *data)
         int key, next_key, fd;
         long long value;
 
-        fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, sizeof(key), sizeof(value),
+        fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(key), sizeof(value),
                             2, 0);
         if (fd < 0) {
                 printf("Failed to create arraymap '%s'!\n", strerror(errno));
@@ -219,40 +221,40 @@ static void test_arraymap(int task, void *data)
         key = 1;
         value = 1234;
         /* Insert key=1 element. */
-        assert(bpf_map_update(fd, &key, &value, BPF_ANY) == 0);
+        assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0);
 
         value = 0;
-        assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == -1 &&
+        assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 &&
                errno == EEXIST);
 
         /* Check that key=1 can be found. */
-        assert(bpf_map_lookup(fd, &key, &value) == 0 && value == 1234);
+        assert(bpf_map_lookup_elem(fd, &key, &value) == 0 && value == 1234);
 
         key = 0;
         /* Check that key=0 is also found and zero initialized. */
-        assert(bpf_map_lookup(fd, &key, &value) == 0 && value == 0);
+        assert(bpf_map_lookup_elem(fd, &key, &value) == 0 && value == 0);
 
         /* key=0 and key=1 were inserted, check that key=2 cannot be inserted
          * due to max_entries limit.
          */
         key = 2;
-        assert(bpf_map_update(fd, &key, &value, BPF_EXIST) == -1 &&
+        assert(bpf_map_update_elem(fd, &key, &value, BPF_EXIST) == -1 &&
                errno == E2BIG);
 
         /* Check that key = 2 doesn't exist. */
-        assert(bpf_map_lookup(fd, &key, &value) == -1 && errno == ENOENT);
+        assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT);
 
         /* Iterate over two elements. */
-        assert(bpf_map_next_key(fd, &key, &next_key) == 0 &&
+        assert(bpf_map_get_next_key(fd, &key, &next_key) == 0 &&
                next_key == 0);
-        assert(bpf_map_next_key(fd, &next_key, &next_key) == 0 &&
+        assert(bpf_map_get_next_key(fd, &next_key, &next_key) == 0 &&
                next_key == 1);
-        assert(bpf_map_next_key(fd, &next_key, &next_key) == -1 &&
+        assert(bpf_map_get_next_key(fd, &next_key, &next_key) == -1 &&
                errno == ENOENT);
 
         /* Delete shouldn't succeed. */
         key = 1;
-        assert(bpf_map_delete(fd, &key) == -1 && errno == EINVAL);
+        assert(bpf_map_delete_elem(fd, &key) == -1 && errno == EINVAL);
 
         close(fd);
 }
@@ -263,7 +265,7 @@ static void test_arraymap_percpu(int task, void *data)
         int key, next_key, fd, i;
         long values[nr_cpus];
 
-        fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key),
+        fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key),
                             sizeof(values[0]), 2, 0);
         if (fd < 0) {
                 printf("Failed to create arraymap '%s'!\n", strerror(errno));
@@ -275,39 +277,39 @@ static void test_arraymap_percpu(int task, void *data)
 
         key = 1;
         /* Insert key=1 element. */
-        assert(bpf_map_update(fd, &key, values, BPF_ANY) == 0);
+        assert(bpf_map_update_elem(fd, &key, values, BPF_ANY) == 0);
 
         values[0] = 0;
-        assert(bpf_map_update(fd, &key, values, BPF_NOEXIST) == -1 &&
+        assert(bpf_map_update_elem(fd, &key, values, BPF_NOEXIST) == -1 &&
                errno == EEXIST);
 
         /* Check that key=1 can be found. */
-        assert(bpf_map_lookup(fd, &key, values) == 0 && values[0] == 100);
+        assert(bpf_map_lookup_elem(fd, &key, values) == 0 && values[0] == 100);
 
         key = 0;
         /* Check that key=0 is also found and zero initialized. */
-        assert(bpf_map_lookup(fd, &key, values) == 0 &&
+        assert(bpf_map_lookup_elem(fd, &key, values) == 0 &&
                values[0] == 0 && values[nr_cpus - 1] == 0);
 
         /* Check that key=2 cannot be inserted due to max_entries limit. */
         key = 2;
-        assert(bpf_map_update(fd, &key, values, BPF_EXIST) == -1 &&
+        assert(bpf_map_update_elem(fd, &key, values, BPF_EXIST) == -1 &&
                errno == E2BIG);
 
         /* Check that key = 2 doesn't exist. */
-        assert(bpf_map_lookup(fd, &key, values) == -1 && errno == ENOENT);
+        assert(bpf_map_lookup_elem(fd, &key, values) == -1 && errno == ENOENT);
 
         /* Iterate over two elements. */
-        assert(bpf_map_next_key(fd, &key, &next_key) == 0 &&
+        assert(bpf_map_get_next_key(fd, &key, &next_key) == 0 &&
                next_key == 0);
-        assert(bpf_map_next_key(fd, &next_key, &next_key) == 0 &&
+        assert(bpf_map_get_next_key(fd, &next_key, &next_key) == 0 &&
                next_key == 1);
-        assert(bpf_map_next_key(fd, &next_key, &next_key) == -1 &&
+        assert(bpf_map_get_next_key(fd, &next_key, &next_key) == -1 &&
                errno == ENOENT);
 
         /* Delete shouldn't succeed. */
         key = 1;
-        assert(bpf_map_delete(fd, &key) == -1 && errno == EINVAL);
+        assert(bpf_map_delete_elem(fd, &key) == -1 && errno == EINVAL);
 
         close(fd);
 }
@@ -319,7 +321,7 @@ static void test_arraymap_percpu_many_keys(void)
         long values[nr_cpus];
         int key, fd, i;
 
-        fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key),
+        fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key),
                             sizeof(values[0]), nr_keys, 0);
         if (fd < 0) {
                 printf("Failed to create per-cpu arraymap '%s'!\n",
@@ -331,13 +333,13 @@ static void test_arraymap_percpu_many_keys(void)
                 values[i] = i + 10;
 
         for (key = 0; key < nr_keys; key++)
-                assert(bpf_map_update(fd, &key, values, BPF_ANY) == 0);
+                assert(bpf_map_update_elem(fd, &key, values, BPF_ANY) == 0);
 
         for (key = 0; key < nr_keys; key++) {
                 for (i = 0; i < nr_cpus; i++)
                         values[i] = 0;
 
-                assert(bpf_map_lookup(fd, &key, values) == 0);
+                assert(bpf_map_lookup_elem(fd, &key, values) == 0);
 
                 for (i = 0; i < nr_cpus; i++)
                         assert(values[i] == i + 10);
@@ -357,7 +359,7 @@ static void test_map_large(void)
         } key;
         int fd, i, value;
 
-        fd = bpf_map_create(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
+        fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
                             MAP_SIZE, map_flags);
         if (fd < 0) {
                 printf("Failed to create large map '%s'!\n", strerror(errno));
@@ -368,22 +370,22 @@ static void test_map_large(void)
                 key = (struct bigkey) { .c = i };
                 value = i;
 
-                assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == 0);
+                assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == 0);
         }
 
         key.c = -1;
-        assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == -1 &&
+        assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 &&
                errno == E2BIG);
 
         /* Iterate through all elements. */
         for (i = 0; i < MAP_SIZE; i++)
-                assert(bpf_map_next_key(fd, &key, &key) == 0);
-        assert(bpf_map_next_key(fd, &key, &key) == -1 && errno == ENOENT);
+                assert(bpf_map_get_next_key(fd, &key, &key) == 0);
+        assert(bpf_map_get_next_key(fd, &key, &key) == -1 && errno == ENOENT);
 
         key.c = 0;
-        assert(bpf_map_lookup(fd, &key, &value) == 0 && value == 0);
+        assert(bpf_map_lookup_elem(fd, &key, &value) == 0 && value == 0);
         key.a = 1;
-        assert(bpf_map_lookup(fd, &key, &value) == -1 && errno == ENOENT);
+        assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT);
 
         close(fd);
 }
@@ -437,10 +439,12 @@ static void do_work(int fn, void *data)
                 key = value = i;
 
                 if (do_update) {
-                        assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == 0);
-                        assert(bpf_map_update(fd, &key, &value, BPF_EXIST) == 0);
+                        assert(bpf_map_update_elem(fd, &key, &value,
+                                                   BPF_NOEXIST) == 0);
+                        assert(bpf_map_update_elem(fd, &key, &value,
+                                                   BPF_EXIST) == 0);
                 } else {
-                        assert(bpf_map_delete(fd, &key) == 0);
+                        assert(bpf_map_delete_elem(fd, &key) == 0);
                 }
         }
 }
@@ -450,7 +454,7 @@ static void test_map_parallel(void)
         int i, fd, key = 0, value = 0;
         int data[2];
 
-        fd = bpf_map_create(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
+        fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
                             MAP_SIZE, map_flags);
         if (fd < 0) {
                 printf("Failed to create map for parallel test '%s'!\n",
@@ -468,20 +472,20 @@ static void test_map_parallel(void)
         run_parallel(TASKS, do_work, data);
 
         /* Check that key=0 is already there. */
-        assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == -1 &&
+        assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 &&
                errno == EEXIST);
 
         /* Check that all elements were inserted. */
         key = -1;
         for (i = 0; i < MAP_SIZE; i++)
-                assert(bpf_map_next_key(fd, &key, &key) == 0);
-        assert(bpf_map_next_key(fd, &key, &key) == -1 && errno == ENOENT);
+                assert(bpf_map_get_next_key(fd, &key, &key) == 0);
+        assert(bpf_map_get_next_key(fd, &key, &key) == -1 && errno == ENOENT);
 
         /* Another check for all elements */
         for (i = 0; i < MAP_SIZE; i++) {
                 key = MAP_SIZE - i - 1;
 
-                assert(bpf_map_lookup(fd, &key, &value) == 0 &&
+                assert(bpf_map_lookup_elem(fd, &key, &value) == 0 &&
                        value == key);
         }
 
@@ -491,7 +495,7 @@ static void test_map_parallel(void)
 
         /* Nothing should be left. */
         key = -1;
-        assert(bpf_map_next_key(fd, &key, &key) == -1 && errno == ENOENT);
+        assert(bpf_map_get_next_key(fd, &key, &key) == -1 && errno == ENOENT);
 }
 
 static void run_all_tests(void)
diff --git a/tools/testing/selftests/bpf/test_tag.c b/tools/testing/selftests/bpf/test_tag.c
new file mode 100644
index 000000000000..de409fc50c35
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tag.c
@@ -0,0 +1,203 @@
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <ctype.h>
+#include <time.h>
+#include <errno.h>
+#include <unistd.h>
+#include <string.h>
+#include <sched.h>
+#include <limits.h>
+#include <assert.h>
+
+#include <sys/socket.h>
+#include <sys/resource.h>
+
+#include <linux/filter.h>
+#include <linux/bpf.h>
+#include <linux/if_alg.h>
+
+#include <bpf/bpf.h>
+
+#include "../../../include/linux/filter.h"
+
+static struct bpf_insn prog[BPF_MAXINSNS];
+
+static void bpf_gen_imm_prog(unsigned int insns, int fd_map)
+{
+        int i;
+
+        srand(time(NULL));
+        for (i = 0; i < insns; i++)
+                prog[i] = BPF_ALU64_IMM(BPF_MOV, i % BPF_REG_10, rand());
+        prog[i - 1] = BPF_EXIT_INSN();
+}
+
+static void bpf_gen_map_prog(unsigned int insns, int fd_map)
+{
+        int i, j = 0;
+
+        for (i = 0; i + 1 < insns; i += 2) {
+                struct bpf_insn tmp[] = {
+                        BPF_LD_MAP_FD(j++ % BPF_REG_10, fd_map)
+                };
+
+                memcpy(&prog[i], tmp, sizeof(tmp));
+        }
+        if (insns % 2 == 0)
+                prog[insns - 2] = BPF_ALU64_IMM(BPF_MOV, i % BPF_REG_10, 42);
+        prog[insns - 1] = BPF_EXIT_INSN();
+}
+
+static int bpf_try_load_prog(int insns, int fd_map,
+                             void (*bpf_filler)(unsigned int insns,
+                                                int fd_map))
+{
+        int fd_prog;
+
+        bpf_filler(insns, fd_map);
+        fd_prog = bpf_load_program(BPF_PROG_TYPE_SCHED_CLS, prog, insns, "", 0,
+                                   NULL, 0);
+        assert(fd_prog > 0);
+        if (fd_map > 0)
+                bpf_filler(insns, 0);
+        return fd_prog;
+}
+
+static int __hex2bin(char ch)
+{
+        if ((ch >= '0') && (ch <= '9'))
+                return ch - '0';
+        ch = tolower(ch);
+        if ((ch >= 'a') && (ch <= 'f'))
+                return ch - 'a' + 10;
+        return -1;
+}
+
+static int hex2bin(uint8_t *dst, const char *src, size_t count)
+{
+        while (count--) {
+                int hi = __hex2bin(*src++);
+                int lo = __hex2bin(*src++);
+
+                if ((hi < 0) || (lo < 0))
+                        return -1;
+                *dst++ = (hi << 4) | lo;
+        }
+        return 0;
+}
+
+static void tag_from_fdinfo(int fd_prog, uint8_t *tag, uint32_t len)
+{
+        const int prefix_len = sizeof("prog_tag:\t") - 1;
+        char buff[256];
+        int ret = -1;
+        FILE *fp;
+
+        snprintf(buff, sizeof(buff), "/proc/%d/fdinfo/%d", getpid(),
+                 fd_prog);
+        fp = fopen(buff, "r");
+        assert(fp);
+
+        while (fgets(buff, sizeof(buff), fp)) {
+                if (strncmp(buff, "prog_tag:\t", prefix_len))
+                        continue;
+                ret = hex2bin(tag, buff + prefix_len, len);
+                break;
+        }
+
+        fclose(fp);
+        assert(!ret);
+}
+
+static void tag_from_alg(int insns, uint8_t *tag, uint32_t len)
+{
+        static const struct sockaddr_alg alg = {
+                .salg_family    = AF_ALG,
+                .salg_type      = "hash",
+                .salg_name      = "sha1",
+        };
+        int fd_base, fd_alg, ret;
+        ssize_t size;
+
+        fd_base = socket(AF_ALG, SOCK_SEQPACKET, 0);
+        assert(fd_base > 0);
+
+        ret = bind(fd_base, (struct sockaddr *)&alg, sizeof(alg));
+        assert(!ret);
+
+        fd_alg = accept(fd_base, NULL, 0);
+        assert(fd_alg > 0);
+
+        insns *= sizeof(struct bpf_insn);
+        size = write(fd_alg, prog, insns);
+        assert(size == insns);
+
+        size = read(fd_alg, tag, len);
+        assert(size == len);
+
+        close(fd_alg);
+        close(fd_base);
+}
+
+static void tag_dump(const char *prefix, uint8_t *tag, uint32_t len)
+{
+        int i;
+
+        printf("%s", prefix);
+        for (i = 0; i < len; i++)
+                printf("%02x", tag[i]);
+        printf("\n");
+}
+
+static void tag_exit_report(int insns, int fd_map, uint8_t *ftag,
+                            uint8_t *atag, uint32_t len)
+{
+        printf("Program tag mismatch for %d insns%s!\n", insns,
+               fd_map < 0 ? "" : " with map");
+
+        tag_dump("  fdinfo result: ", ftag, len);
+        tag_dump("  af_alg result: ", atag, len);
+        exit(1);
+}
+
+static void do_test(uint32_t *tests, int start_insns, int fd_map,
+                    void (*bpf_filler)(unsigned int insns, int fd))
+{
+        int i, fd_prog;
+
+        for (i = start_insns; i <= BPF_MAXINSNS; i++) {
+                uint8_t ftag[8], atag[sizeof(ftag)];
+
+                fd_prog = bpf_try_load_prog(i, fd_map, bpf_filler);
+                tag_from_fdinfo(fd_prog, ftag, sizeof(ftag));
+                tag_from_alg(i, atag, sizeof(atag));
+                if (memcmp(ftag, atag, sizeof(ftag)))
+                        tag_exit_report(i, fd_map, ftag, atag, sizeof(ftag));
+
+                close(fd_prog);
+                sched_yield();
+                (*tests)++;
+        }
+}
+
+int main(void)
+{
+        struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY };
+        uint32_t tests = 0;
+        int i, fd_map;
+
+        setrlimit(RLIMIT_MEMLOCK, &rinf);
+        fd_map = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(int),
+                                sizeof(int), 1, BPF_F_NO_PREALLOC);
+        assert(fd_map > 0);
+
+        for (i = 0; i < 5; i++) {
+                do_test(&tests, 2, -1,     bpf_gen_imm_prog);
+                do_test(&tests, 3, fd_map, bpf_gen_map_prog);
+        }
+
+        printf("test_tag: OK (%u tests)\n", tests);
+        close(fd_map);
+        return 0;
+}
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 853d7e43434a..d1555e4240c0 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -8,7 +8,11 @@
  * License as published by the Free Software Foundation.
  */
 
+#include <asm/types.h>
+#include <linux/types.h>
+#include <stdint.h>
 #include <stdio.h>
+#include <stdlib.h>
 #include <unistd.h>
 #include <errno.h>
 #include <string.h>
@@ -16,6 +20,7 @@
 #include <stdbool.h>
 #include <sched.h>
 
+#include <sys/capability.h>
 #include <sys/resource.h>
 
 #include <linux/unistd.h>
@@ -23,9 +28,9 @@
 #include <linux/bpf_perf_event.h>
 #include <linux/bpf.h>
 
-#include "../../../include/linux/filter.h"
+#include <bpf/bpf.h>
 
-#include "bpf_sys.h"
+#include "../../../include/linux/filter.h"
 
 #ifndef ARRAY_SIZE
 # define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
@@ -859,17 +864,453 @@ static struct bpf_test tests[] = {
                 .result = REJECT,
         },
         {
-                "check non-u32 access to cb",
+                "check cb access: byte",
                 .insns = {
-                        BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_1,
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[0])),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[0]) + 1),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[0]) + 2),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[0]) + 3),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[1])),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[1]) + 1),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[1]) + 2),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[1]) + 3),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[2])),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[2]) + 1),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[2]) + 2),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[2]) + 3),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[3])),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[3]) + 1),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[3]) + 2),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[3]) + 3),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[4])),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[4]) + 1),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[4]) + 2),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[4]) + 3),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
                                     offsetof(struct __sk_buff, cb[0])),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[0]) + 1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[0]) + 2),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[0]) + 3),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[1])),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[1]) + 1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[1]) + 2),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[1]) + 3),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[2])),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[2]) + 1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[2]) + 2),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[2]) + 3),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[3])),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[3]) + 1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[3]) + 2),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[3]) + 3),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[4])),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[4]) + 1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[4]) + 2),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[4]) + 3),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+        },
+        {
+                "check cb access: byte, oob 1",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[4]) + 4),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+        },
+        {
+                "check cb access: byte, oob 2",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[0]) - 1),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+        },
+        {
+                "check cb access: byte, oob 3",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[4]) + 4),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+        },
+        {
+                "check cb access: byte, oob 4",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[0]) - 1),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+        },
+        {
+                "check cb access: byte, wrong type",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[0])),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+        },
+        {
+                "check cb access: half",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[0])),
+                        BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[0]) + 2),
+                        BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[1])),
+                        BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[1]) + 2),
+                        BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[2])),
+                        BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[2]) + 2),
+                        BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[3])),
+                        BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[3]) + 2),
+                        BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[4])),
+                        BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[4]) + 2),
+                        BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[0])),
+                        BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[0]) + 2),
+                        BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[1])),
+                        BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[1]) + 2),
+                        BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[2])),
+                        BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[2]) + 2),
+                        BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[3])),
+                        BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[3]) + 2),
+                        BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[4])),
+                        BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[4]) + 2),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+        },
+        {
+                "check cb access: half, unaligned",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[0]) + 1),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "misaligned access",
+                .result = REJECT,
+        },
+        {
+                "check cb access: half, oob 1",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[4]) + 4),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+        },
+        {
+                "check cb access: half, oob 2",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[0]) - 2),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+        },
+        {
+                "check cb access: half, oob 3",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[4]) + 4),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+        },
+        {
+                "check cb access: half, oob 4",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[0]) - 2),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+        },
+        {
+                "check cb access: half, wrong type",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[0])),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+        },
+        {
+                "check cb access: word",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[0])),
+                        BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[1])),
+                        BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[2])),
+                        BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[3])),
+                        BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[4])),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[0])),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[1])),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[2])),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[3])),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[4])),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+        },
+        {
+                "check cb access: word, unaligned 1",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[0]) + 2),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "misaligned access",
+                .result = REJECT,
+        },
+        {
+                "check cb access: word, unaligned 2",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[4]) + 1),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "misaligned access",
+                .result = REJECT,
+        },
+        {
+                "check cb access: word, unaligned 3",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[4]) + 2),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "misaligned access",
+                .result = REJECT,
+        },
+        {
+                "check cb access: word, unaligned 4",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[4]) + 3),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "misaligned access",
+                .result = REJECT,
+        },
+        {
+                "check cb access: double",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[0])),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[2])),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[0])),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[2])),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+        },
+        {
+                "check cb access: double, unaligned 1",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[1])),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "misaligned access",
+                .result = REJECT,
+        },
+        {
+                "check cb access: double, unaligned 2",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[3])),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "misaligned access",
+                .result = REJECT,
+        },
+        {
+                "check cb access: double, oob 1",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[4])),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+        },
+        {
+                "check cb access: double, oob 2",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[4]) + 8),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+        },
+        {
+                "check cb access: double, oob 3",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[0]) - 8),
                         BPF_EXIT_INSN(),
                 },
                 .errstr = "invalid bpf_context access",
-                .errstr_unpriv = "R1 leaks addr",
                 .result = REJECT,
         },
         {
+                "check cb access: double, oob 4",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[4])),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+        },
+        {
+                "check cb access: double, oob 5",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[4]) + 8),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+        },
+        {
+                "check cb access: double, oob 6",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, cb[0]) - 8),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+        },
+        {
+                "check cb access: double, wrong type",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, cb[0])),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+        },
+        {
                 "check out of range skb->cb access",
                 .insns = {
                         BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
@@ -1890,6 +2331,107 @@ static struct bpf_test tests[] = {
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
         },
         {
+                "direct packet access: test11 (shift, good access)",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data_end)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 22),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 8),
+                        BPF_MOV64_IMM(BPF_REG_3, 144),
+                        BPF_MOV64_REG(BPF_REG_5, BPF_REG_3),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 23),
+                        BPF_ALU64_IMM(BPF_RSH, BPF_REG_5, 3),
+                        BPF_MOV64_REG(BPF_REG_6, BPF_REG_2),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_5),
+                        BPF_MOV64_IMM(BPF_REG_0, 1),
+                        BPF_EXIT_INSN(),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "direct packet access: test12 (and, good access)",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data_end)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 22),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 8),
+                        BPF_MOV64_IMM(BPF_REG_3, 144),
+                        BPF_MOV64_REG(BPF_REG_5, BPF_REG_3),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 23),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_5, 15),
+                        BPF_MOV64_REG(BPF_REG_6, BPF_REG_2),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_5),
+                        BPF_MOV64_IMM(BPF_REG_0, 1),
+                        BPF_EXIT_INSN(),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "direct packet access: test13 (branches, good access)",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data_end)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 22),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 13),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct __sk_buff, mark)),
+                        BPF_MOV64_IMM(BPF_REG_4, 1),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_4, 2),
+                        BPF_MOV64_IMM(BPF_REG_3, 14),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+                        BPF_MOV64_IMM(BPF_REG_3, 24),
+                        BPF_MOV64_REG(BPF_REG_5, BPF_REG_3),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 23),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_5, 15),
+                        BPF_MOV64_REG(BPF_REG_6, BPF_REG_2),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_5),
+                        BPF_MOV64_IMM(BPF_REG_0, 1),
+                        BPF_EXIT_INSN(),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "direct packet access: test14 (pkt_ptr += 0, CONST_IMM, good access)",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data_end)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 22),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 7),
+                        BPF_MOV64_IMM(BPF_REG_5, 12),
+                        BPF_ALU64_IMM(BPF_RSH, BPF_REG_5, 4),
+                        BPF_MOV64_REG(BPF_REG_6, BPF_REG_2),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_5),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 1),
+                        BPF_EXIT_INSN(),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
                 "helper access to packet: test1, valid packet_ptr range",
                 .insns = {
                         BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
@@ -2905,6 +3447,1012 @@ static struct bpf_test tests[] = {
                 .result = REJECT,
                 .errstr = "invalid bpf_context access",
         },
+        {
+                "helper access to map: full range",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to map: partial range",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_MOV64_IMM(BPF_REG_2, 8),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to map: empty range",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr = "invalid access to map value, value_size=48 off=0 size=0",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to map: out-of-bound range",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val) + 8),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr = "invalid access to map value, value_size=48 off=0 size=56",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to map: negative range",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_MOV64_IMM(BPF_REG_2, -8),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr = "invalid access to map value, value_size=48 off=0 size=-8",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to adjusted map (via const imm): full range",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1,
+                                offsetof(struct test_val, foo)),
+                        BPF_MOV64_IMM(BPF_REG_2,
+                                sizeof(struct test_val) -
+                                offsetof(struct test_val, foo)),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to adjusted map (via const imm): partial range",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1,
+                                offsetof(struct test_val, foo)),
+                        BPF_MOV64_IMM(BPF_REG_2, 8),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to adjusted map (via const imm): empty range",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1,
+                                offsetof(struct test_val, foo)),
+                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr = "R1 min value is outside of the array range",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to adjusted map (via const imm): out-of-bound range",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1,
+                                offsetof(struct test_val, foo)),
+                        BPF_MOV64_IMM(BPF_REG_2,
+                                sizeof(struct test_val) -
+                                offsetof(struct test_val, foo) + 8),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr = "invalid access to map value, value_size=48 off=4 size=52",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to adjusted map (via const imm): negative range (> adjustment)",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1,
+                                offsetof(struct test_val, foo)),
+                        BPF_MOV64_IMM(BPF_REG_2, -8),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr = "invalid access to map value, value_size=48 off=4 size=-8",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to adjusted map (via const imm): negative range (< adjustment)",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1,
+                                offsetof(struct test_val, foo)),
+                        BPF_MOV64_IMM(BPF_REG_2, -1),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr = "R1 min value is outside of the array range",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to adjusted map (via const reg): full range",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_MOV64_IMM(BPF_REG_3,
+                                offsetof(struct test_val, foo)),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_MOV64_IMM(BPF_REG_2,
+                                sizeof(struct test_val) -
+                                offsetof(struct test_val, foo)),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to adjusted map (via const reg): partial range",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_MOV64_IMM(BPF_REG_3,
+                                offsetof(struct test_val, foo)),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_MOV64_IMM(BPF_REG_2, 8),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to adjusted map (via const reg): empty range",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr = "R1 min value is outside of the array range",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to adjusted map (via const reg): out-of-bound range",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_MOV64_IMM(BPF_REG_3,
+                                offsetof(struct test_val, foo)),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_MOV64_IMM(BPF_REG_2,
+                                sizeof(struct test_val) -
+                                offsetof(struct test_val, foo) + 8),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr = "invalid access to map value, value_size=48 off=4 size=52",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to adjusted map (via const reg): negative range (> adjustment)",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_MOV64_IMM(BPF_REG_3,
+                                offsetof(struct test_val, foo)),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_MOV64_IMM(BPF_REG_2, -8),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr = "invalid access to map value, value_size=48 off=4 size=-8",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to adjusted map (via const reg): negative range (< adjustment)",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_MOV64_IMM(BPF_REG_3,
+                                offsetof(struct test_val, foo)),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_MOV64_IMM(BPF_REG_2, -1),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr = "R1 min value is outside of the array range",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to adjusted map (via variable): full range",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JGT, BPF_REG_3,
+                                offsetof(struct test_val, foo), 4),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_MOV64_IMM(BPF_REG_2,
+                                sizeof(struct test_val) -
+                                offsetof(struct test_val, foo)),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to adjusted map (via variable): partial range",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JGT, BPF_REG_3,
+                                offsetof(struct test_val, foo), 4),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_MOV64_IMM(BPF_REG_2, 8),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to adjusted map (via variable): empty range",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JGT, BPF_REG_3,
+                                offsetof(struct test_val, foo), 4),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr = "R1 min value is outside of the array range",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to adjusted map (via variable): no max check",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr = "R1 min value is negative, either use unsigned index or do a if (index >=0) check",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to adjusted map (via variable): wrong max check",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JGT, BPF_REG_3,
+                                offsetof(struct test_val, foo), 4),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_MOV64_IMM(BPF_REG_2,
+                                sizeof(struct test_val) -
+                                offsetof(struct test_val, foo) + 1),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr = "invalid access to map value, value_size=48 off=4 size=45",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "map element value is preserved across register spilling",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -184),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_1, 0),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 42),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr_unpriv = "R0 leaks addr",
+                .result = ACCEPT,
+                .result_unpriv = REJECT,
+        },
+        {
+                "map element value (adjusted) is preserved across register spilling",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0,
+                                offsetof(struct test_val, foo)),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -184),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_1, 0),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 42),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .result = ACCEPT,
+                .result_unpriv = REJECT,
+        },
+        {
+                "helper access to variable memory: stack, bitwise AND + JMP, correct bounds",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -64),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -56),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -48),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -40),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -32),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+                        BPF_MOV64_IMM(BPF_REG_2, 16),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64),
+                        BPF_MOV64_IMM(BPF_REG_4, 0),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to variable memory: stack, bitwise AND, zero included",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
+                        BPF_MOV64_IMM(BPF_REG_2, 16),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid stack type R1 off=-64 access_size=0",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to variable memory: stack, bitwise AND + JMP, wrong max",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
+                        BPF_MOV64_IMM(BPF_REG_2, 16),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 65),
+                        BPF_MOV64_IMM(BPF_REG_4, 0),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid stack type R1 off=-64 access_size=65",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to variable memory: stack, JMP, correct bounds",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -64),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -56),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -48),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -40),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -32),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+                        BPF_MOV64_IMM(BPF_REG_2, 16),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
+                        BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 64, 4),
+                        BPF_MOV64_IMM(BPF_REG_4, 0),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to variable memory: stack, JMP (signed), correct bounds",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -64),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -56),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -48),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -40),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -32),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+                        BPF_MOV64_IMM(BPF_REG_2, 16),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
+                        BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, 64, 4),
+                        BPF_MOV64_IMM(BPF_REG_4, 0),
+                        BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to variable memory: stack, JMP, bounds + offset",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
+                        BPF_MOV64_IMM(BPF_REG_2, 16),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
+                        BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 64, 5),
+                        BPF_MOV64_IMM(BPF_REG_4, 0),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 3),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid stack type R1 off=-64 access_size=65",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to variable memory: stack, JMP, wrong max",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
+                        BPF_MOV64_IMM(BPF_REG_2, 16),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
+                        BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 65, 4),
+                        BPF_MOV64_IMM(BPF_REG_4, 0),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid stack type R1 off=-64 access_size=65",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to variable memory: stack, JMP, no max check",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
+                        BPF_MOV64_IMM(BPF_REG_2, 16),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
+                        BPF_MOV64_IMM(BPF_REG_4, 0),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R2 unbounded memory access",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to variable memory: stack, JMP, no min check",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
+                        BPF_MOV64_IMM(BPF_REG_2, 16),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
+                        BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 64, 3),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid stack type R1 off=-64 access_size=0",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to variable memory: stack, JMP (signed), no min check",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
+                        BPF_MOV64_IMM(BPF_REG_2, 16),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
+                        BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, 64, 3),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R2 min value is negative",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to variable memory: map, JMP, correct bounds",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128),
+                        BPF_JMP_IMM(BPF_JSGT, BPF_REG_2,
+                                sizeof(struct test_val), 4),
+                        BPF_MOV64_IMM(BPF_REG_4, 0),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to variable memory: map, JMP, wrong max",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128),
+                        BPF_JMP_IMM(BPF_JSGT, BPF_REG_2,
+                                sizeof(struct test_val) + 1, 4),
+                        BPF_MOV64_IMM(BPF_REG_4, 0),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr = "invalid access to map value, value_size=48 off=0 size=49",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to variable memory: map adjusted, JMP, correct bounds",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 20),
+                        BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128),
+                        BPF_JMP_IMM(BPF_JSGT, BPF_REG_2,
+                                sizeof(struct test_val) - 20, 4),
+                        BPF_MOV64_IMM(BPF_REG_4, 0),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to variable memory: map adjusted, JMP, wrong max",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 20),
+                        BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128),
+                        BPF_JMP_IMM(BPF_JSGT, BPF_REG_2,
+                                sizeof(struct test_val) - 19, 4),
+                        BPF_MOV64_IMM(BPF_REG_4, 0),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr = "R1 min value is outside of the array range",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to variable memory: size > 0 not allowed on NULL",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_1, 0),
+                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_MOV64_IMM(BPF_REG_4, 0),
+                        BPF_MOV64_IMM(BPF_REG_5, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_csum_diff),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 type=imm expected=fp",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "helper access to variable memory: size = 0 not allowed on != NULL",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, 0),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 8),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_MOV64_IMM(BPF_REG_4, 0),
+                        BPF_MOV64_IMM(BPF_REG_5, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_csum_diff),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid stack type R1 off=-8 access_size=0",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "helper access to variable memory: 8 bytes leak",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -64),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -56),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -48),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -40),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 63),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid indirect read from stack off -64+32 size 64",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to variable memory: 8 bytes no leak (init memory)",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -64),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -56),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -48),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -40),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -32),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
+                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 32),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 32),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "invalid and of negative number",
+                .insns = {
+                        BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+                        BPF_MOV64_IMM(BPF_REG_1, 6),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_1, -4),
+                        BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 2),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_0, 0,
+                                   offsetof(struct test_val, foo)),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
+                .result = REJECT,
+                .result_unpriv = REJECT,
+        },
+        {
+                "invalid range check",
+                .insns = {
+                        BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 12),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+                        BPF_MOV64_IMM(BPF_REG_9, 1),
+                        BPF_ALU32_IMM(BPF_MOD, BPF_REG_1, 2),
+                        BPF_ALU32_IMM(BPF_ADD, BPF_REG_1, 1),
+                        BPF_ALU32_REG(BPF_AND, BPF_REG_9, BPF_REG_1),
+                        BPF_ALU32_IMM(BPF_ADD, BPF_REG_9, 1),
+                        BPF_ALU32_IMM(BPF_RSH, BPF_REG_9, 1),
+                        BPF_MOV32_IMM(BPF_REG_3, 1),
+                        BPF_ALU32_REG(BPF_SUB, BPF_REG_3, BPF_REG_9),
+                        BPF_ALU32_IMM(BPF_MUL, BPF_REG_3, 0x10000000),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_3),
+                        BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_3, 0),
+                        BPF_MOV64_REG(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
+                .result = REJECT,
+                .result_unpriv = REJECT,
+        }
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
@@ -2921,7 +4469,7 @@ static int create_map(uint32_t size_value, uint32_t max_elem)
 {
         int fd;
 
-        fd = bpf_map_create(BPF_MAP_TYPE_HASH, sizeof(long long),
+        fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(long long),
                             size_value, max_elem, BPF_F_NO_PREALLOC);
         if (fd < 0)
                 printf("Failed to create hash map '%s'!\n", strerror(errno));
@@ -2933,7 +4481,7 @@ static int create_prog_array(void)
 {
         int fd;
 
-        fd = bpf_map_create(BPF_MAP_TYPE_PROG_ARRAY, sizeof(int),
+        fd = bpf_create_map(BPF_MAP_TYPE_PROG_ARRAY, sizeof(int),
                             sizeof(int), 4, 0);
         if (fd < 0)
                 printf("Failed to create prog array '%s'!\n", strerror(errno));
@@ -2991,9 +4539,9 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 
         do_test_fixup(test, prog, &fd_f1, &fd_f2, &fd_f3);
 
-        fd_prog = bpf_prog_load(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
-                                prog, prog_len * sizeof(struct bpf_insn),
-                                "GPL", bpf_vlog, sizeof(bpf_vlog));
+        fd_prog = bpf_load_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
+                                   prog, prog_len, "GPL", 0, bpf_vlog,
+                                   sizeof(bpf_vlog));
 
         expected_ret = unpriv && test->result_unpriv != UNDEF ?
                        test->result_unpriv : test->result;
@@ -3031,6 +4579,57 @@ fail_log:
         goto close_fds;
 }
 
+static bool is_admin(void)
+{
+        cap_t caps;
+        cap_flag_value_t sysadmin = CAP_CLEAR;
+        const cap_value_t cap_val = CAP_SYS_ADMIN;
+
+#ifdef CAP_IS_SUPPORTED
+        if (!CAP_IS_SUPPORTED(CAP_SETFCAP)) {
+                perror("cap_get_flag");
+                return false;
+        }
+#endif
+        caps = cap_get_proc();
+        if (!caps) {
+                perror("cap_get_proc");
+                return false;
+        }
+        if (cap_get_flag(caps, cap_val, CAP_EFFECTIVE, &sysadmin))
+                perror("cap_get_flag");
+        if (cap_free(caps))
+                perror("cap_free");
+        return (sysadmin == CAP_SET);
+}
+
+static int set_admin(bool admin)
+{
+        cap_t caps;
+        const cap_value_t cap_val = CAP_SYS_ADMIN;
+        int ret = -1;
+
+        caps = cap_get_proc();
+        if (!caps) {
+                perror("cap_get_proc");
+                return -1;
+        }
+        if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_val,
+                                admin ? CAP_SET : CAP_CLEAR)) {
+                perror("cap_set_flag");
+                goto out;
+        }
+        if (cap_set_proc(caps)) {
+                perror("cap_set_proc");
+                goto out;
+        }
+        ret = 0;
+out:
+        if (cap_free(caps))
+                perror("cap_free");
+        return ret;
+}
+
 static int do_test(bool unpriv, unsigned int from, unsigned int to)
 {
         int i, passes = 0, errors = 0;
@@ -3041,11 +4640,19 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to)
                 /* Program types that are not supported by non-root we
                  * skip right away.
                  */
-                if (unpriv && test->prog_type)
-                        continue;
+                if (!test->prog_type) {
+                        if (!unpriv)
+                                set_admin(false);
+                        printf("#%d/u %s ", i, test->descr);
+                        do_test_single(test, true, &passes, &errors);
+                        if (!unpriv)
+                                set_admin(true);
+                }
 
-                printf("#%d %s ", i, test->descr);
-                do_test_single(test, unpriv, &passes, &errors);
+                if (!unpriv) {
+                        printf("#%d/p %s ", i, test->descr);
+                        do_test_single(test, false, &passes, &errors);
+                }
         }
 
         printf("Summary: %d PASSED, %d FAILED\n", passes, errors);
@@ -3057,7 +4664,7 @@ int main(int argc, char **argv)
         struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY };
         struct rlimit rlim = { 1 << 20, 1 << 20 };
         unsigned int from = 0, to = ARRAY_SIZE(tests);
-        bool unpriv = geteuid() != 0;
+        bool unpriv = !is_admin();
 
         if (argc == 3) {
                 unsigned int l = atoi(argv[argc - 2]);
diff --git a/tools/testing/selftests/breakpoints/Makefile b/tools/testing/selftests/breakpoints/Makefile
index 61b79e8df1f4..72aa103e4141 100644
--- a/tools/testing/selftests/breakpoints/Makefile
+++ b/tools/testing/selftests/breakpoints/Makefile
@@ -3,17 +3,13 @@ uname_M := $(shell uname -m 2>/dev/null || echo not)
 ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
 
 ifeq ($(ARCH),x86)
-TEST_PROGS := breakpoint_test
+TEST_GEN_PROGS := breakpoint_test
 endif
 ifeq ($(ARCH),aarch64)
-TEST_PROGS := breakpoint_test_arm64
+TEST_GEN_PROGS := breakpoint_test_arm64
 endif
 
-TEST_PROGS += step_after_suspend_test
-
-all: $(TEST_PROGS)
+TEST_GEN_PROGS += step_after_suspend_test
 
 include ../lib.mk
 
-clean:
-        rm -fr breakpoint_test breakpoint_test_arm64 step_after_suspend_test
diff --git a/tools/testing/selftests/capabilities/Makefile b/tools/testing/selftests/capabilities/Makefile
index 008602aed920..29b8adfdac71 100644
--- a/tools/testing/selftests/capabilities/Makefile
+++ b/tools/testing/selftests/capabilities/Makefile
@@ -1,15 +1,8 @@
-TEST_FILES := validate_cap
-TEST_PROGS := test_execve
-
-BINARIES := $(TEST_FILES) $(TEST_PROGS)
+TEST_GEN_FILES := validate_cap
+TEST_GEN_PROGS := test_execve
 
 CFLAGS += -O2 -g -std=gnu99 -Wall
 LDLIBS += -lcap-ng -lrt -ldl
 
-all: $(BINARIES)
-
-clean:
-        $(RM) $(BINARIES)
-
 include ../lib.mk
 
diff --git a/tools/testing/selftests/cpufreq/Makefile b/tools/testing/selftests/cpufreq/Makefile
new file mode 100644
index 000000000000..3955cd96f3a2
--- /dev/null
+++ b/tools/testing/selftests/cpufreq/Makefile
@@ -0,0 +1,8 @@
+all:
+
+TEST_PROGS := main.sh
+TEST_FILES := cpu.sh cpufreq.sh governor.sh module.sh special-tests.sh
+
+include ../lib.mk
+
+clean:
diff --git a/tools/testing/selftests/cpufreq/cpu.sh b/tools/testing/selftests/cpufreq/cpu.sh
new file mode 100755
index 000000000000..8e08a83d65f2
--- /dev/null
+++ b/tools/testing/selftests/cpufreq/cpu.sh
@@ -0,0 +1,84 @@
+#!/bin/bash
+#
+# CPU helpers
+
+# protect against multiple inclusion
+if [ $FILE_CPU ]; then
+        return 0
+else
+        FILE_CPU=DONE
+fi
+
+source cpufreq.sh
+
+for_each_cpu()
+{
+        cpus=$(ls $CPUROOT | grep "cpu[0-9].*")
+        for cpu in $cpus; do
+                $@ $cpu
+        done
+}
+
+for_each_non_boot_cpu()
+{
+        cpus=$(ls $CPUROOT | grep "cpu[1-9].*")
+        for cpu in $cpus; do
+                $@ $cpu
+        done
+}
+
+#$1: cpu
+offline_cpu()
+{
+        printf "Offline $1\n"
+        echo 0 > $CPUROOT/$1/online
+}
+
+#$1: cpu
+online_cpu()
+{
+        printf "Online $1\n"
+        echo 1 > $CPUROOT/$1/online
+}
+
+#$1: cpu
+reboot_cpu()
+{
+        offline_cpu $1
+        online_cpu $1
+}
+
+# Reboot CPUs
+# param: number of times we want to run the loop
+reboot_cpus()
+{
+        printf "** Test: Running ${FUNCNAME[0]} for $1 loops **\n\n"
+
+        for i in `seq 1 $1`; do
+                for_each_non_boot_cpu offline_cpu
+                for_each_non_boot_cpu online_cpu
+                printf "\n"
+        done
+
+        printf "\n%s\n\n" "------------------------------------------------"
+}
+
+# Prints warning for all CPUs with missing cpufreq directory
+print_unmanaged_cpus()
+{
+        for_each_cpu cpu_should_have_cpufreq_directory
+}
+
+# Counts CPUs with cpufreq directories
+count_cpufreq_managed_cpus()
+{
+        count=0;
+
+        for cpu in `ls $CPUROOT | grep "cpu[0-9].*"`; do
+                if [ -d $CPUROOT/$cpu/cpufreq ]; then
+                        let count=count+1;
+                fi
+        done
+
+        echo $count;
+}
diff --git a/tools/testing/selftests/cpufreq/cpufreq.sh b/tools/testing/selftests/cpufreq/cpufreq.sh
new file mode 100755
index 000000000000..1ed3832030b4
--- /dev/null
+++ b/tools/testing/selftests/cpufreq/cpufreq.sh
@@ -0,0 +1,241 @@
+#!/bin/bash
+
+# protect against multiple inclusion
+if [ $FILE_CPUFREQ ]; then
+        return 0
+else
+        FILE_CPUFREQ=DONE
+fi
+
+source cpu.sh
+
+
+# $1: cpu
+cpu_should_have_cpufreq_directory()
+{
+        if [ ! -d $CPUROOT/$1/cpufreq ]; then
+                printf "Warning: No cpufreq directory present for $1\n"
+        fi
+}
+
+cpu_should_not_have_cpufreq_directory()
+{
+        if [ -d $CPUROOT/$1/cpufreq ]; then
+                printf "Warning: cpufreq directory present for $1\n"
+        fi
+}
+
+for_each_policy()
+{
+        policies=$(ls $CPUFREQROOT| grep "policy[0-9].*")
+        for policy in $policies; do
+                $@ $policy
+        done
+}
+
+for_each_policy_concurrent()
+{
+        policies=$(ls $CPUFREQROOT| grep "policy[0-9].*")
+        for policy in $policies; do
+                $@ $policy &
+        done
+}
+
+# $1: Path
+read_cpufreq_files_in_dir()
+{
+        local files=`ls $1`
+
+        printf "Printing directory: $1\n\n"
+
+        for file in $files; do
+                if [ -f $1/$file ]; then
+                        printf "$file:"
+                        cat $1/$file
+                else
+                        printf "\n"
+                        read_cpufreq_files_in_dir "$1/$file"
+                fi
+        done
+        printf "\n"
+}
+
+
+read_all_cpufreq_files()
+{
+        printf "** Test: Running ${FUNCNAME[0]} **\n\n"
+
+        read_cpufreq_files_in_dir $CPUFREQROOT
+
+        printf "%s\n\n" "------------------------------------------------"
+}
+
+
+# UPDATE CPUFREQ FILES
+
+# $1: directory path
+update_cpufreq_files_in_dir()
+{
+        local files=`ls $1`
+
+        printf "Updating directory: $1\n\n"
+
+        for file in $files; do
+                if [ -f $1/$file ]; then
+                        # file is writable ?
+                        local wfile=$(ls -l $1/$file | awk '$1 ~ /^.*w.*/ { print $NF; }')
+
+                        if [ ! -z $wfile ]; then
+                                # scaling_setspeed is a special file and we
+                                # should skip updating it
+                                if [ $file != "scaling_setspeed" ]; then
+                                        local val=$(cat $1/$file)
+                                        printf "Writing $val to: $file\n"
+                                        echo $val > $1/$file
+                                fi
+                        fi
+                else
+                        printf "\n"
+                        update_cpufreq_files_in_dir "$1/$file"
+                fi
+        done
+
+        printf "\n"
+}
+
+# Update all writable files with their existing values
+update_all_cpufreq_files()
+{
+        printf "** Test: Running ${FUNCNAME[0]} **\n\n"
+
+        update_cpufreq_files_in_dir $CPUFREQROOT
+
+        printf "%s\n\n" "------------------------------------------------"
+}
+
+
+# CHANGE CPU FREQUENCIES
+
+# $1: policy
+find_current_freq()
+{
+        cat $CPUFREQROOT/$1/scaling_cur_freq
+}
+
+# $1: policy
+# $2: frequency
+set_cpu_frequency()
+{
+        printf "Change frequency for $1 to $2\n"
+        echo $2 > $CPUFREQROOT/$1/scaling_setspeed
+}
+
+# $1: policy
+test_all_frequencies()
+{
+        local filepath="$CPUFREQROOT/$1"
+
+        backup_governor $1
+
+        local found=$(switch_governor $1 "userspace")
+        if [ $found = 1 ]; then
+                printf "${FUNCNAME[0]}: userspace governor not available for: $1\n"
+                return;
+        fi
+
+        printf "Switched governor for $1 to userspace\n\n"
+
+        local freqs=$(cat $filepath/scaling_available_frequencies)
+        printf "Available frequencies for $1: $freqs\n\n"
+
+        # Set all frequencies one-by-one
+        for freq in $freqs; do
+                set_cpu_frequency $1 $freq
+        done
+
+        printf "\n"
+
+        restore_governor $1
+}
+
+# $1: loop count
+shuffle_frequency_for_all_cpus()
+{
+        printf "** Test: Running ${FUNCNAME[0]} for $1 loops **\n\n"
+
+        for i in `seq 1 $1`; do
+                for_each_policy test_all_frequencies
+        done
+        printf "\n%s\n\n" "------------------------------------------------"
+}
+
+# Basic cpufreq tests
+cpufreq_basic_tests()
+{
+        printf "*** RUNNING CPUFREQ SANITY TESTS ***\n"
+        printf "====================================\n\n"
+
+        count=$(count_cpufreq_managed_cpus)
+        if [ $count = 0 ]; then
+                printf "No cpu is managed by cpufreq core, exiting\n"
+                exit;
+        else
+                printf "CPUFreq manages: $count CPUs\n\n"
+        fi
+
+        # Detect & print which CPUs are not managed by cpufreq
+        print_unmanaged_cpus
+
+        # read/update all cpufreq files
+        read_all_cpufreq_files
+        update_all_cpufreq_files
+
+        # hotplug cpus
+        reboot_cpus 5
+
+        # Test all frequencies
+        shuffle_frequency_for_all_cpus 2
+
+        # Test all governors
+        shuffle_governors_for_all_cpus 1
+}
+
+# Suspend/resume
+# $1: "suspend" or "hibernate", $2: loop count
+do_suspend()
+{
+        printf "** Test: Running ${FUNCNAME[0]}: Trying $1 for $2 loops **\n\n"
+
+        # Is the directory available
+        if [ ! -d $SYSFS/power/ -o ! -f $SYSFS/power/state ]; then
+                printf "$SYSFS/power/state not available\n"
+                return 1
+        fi
+
+        if [ $1 = "suspend" ]; then
+                filename="mem"
+        elif [ $1 = "hibernate" ]; then
+                filename="disk"
+        else
+                printf "$1 is not a valid option\n"
+                return 1
+        fi
+
+        if [ -n $filename ]; then
+                present=$(cat $SYSFS/power/state | grep $filename)
+
+                if [ -z "$present" ]; then
+                        printf "Tried to $1 but $filename isn't present in $SYSFS/power/state\n"
+                        return 1;
+                fi
+
+                for i in `seq 1 $2`; do
+                        printf "Starting $1\n"
+                        echo $filename > $SYSFS/power/state
+                        printf "Came out of $1\n"
+
+                        printf "Do basic tests after finishing $1 to verify cpufreq state\n\n"
+                        cpufreq_basic_tests
+                done
+        fi
+}
diff --git a/tools/testing/selftests/cpufreq/governor.sh b/tools/testing/selftests/cpufreq/governor.sh
new file mode 100755
index 000000000000..def645103555
--- /dev/null
+++ b/tools/testing/selftests/cpufreq/governor.sh
@@ -0,0 +1,153 @@
+#!/bin/bash
+#
+# Test governors
+
+# protect against multiple inclusion
+if [ $FILE_GOVERNOR ]; then
+        return 0
+else
+        FILE_GOVERNOR=DONE
+fi
+
+source cpu.sh
+source cpufreq.sh
+
+CUR_GOV=
+CUR_FREQ=
+
+# Find governor's directory path
+# $1: policy, $2: governor
+find_gov_directory()
+{
+        if [ -d $CPUFREQROOT/$2 ]; then
+                printf "$CPUFREQROOT/$2\n"
+        elif [ -d $CPUFREQROOT/$1/$2 ]; then
+                printf "$CPUFREQROOT/$1/$2\n"
+        else
+                printf "INVALID\n"
+        fi
+}
+
+# $1: policy
+find_current_governor()
+{
+        cat $CPUFREQROOT/$1/scaling_governor
+}
+
+# $1: policy
+backup_governor()
+{
+        CUR_GOV=$(find_current_governor $1)
+
+        printf "Governor backup done for $1: $CUR_GOV\n"
+
+        if [ $CUR_GOV == "userspace" ]; then
+                CUR_FREQ=$(find_current_freq $1)
+                printf "Governor frequency backup done for $1: $CUR_FREQ\n"
+        fi
+
+        printf "\n"
+}
+
+# $1: policy
+restore_governor()
+{
+        __switch_governor $1 $CUR_GOV
+
+        printf "Governor restored for $1 to $CUR_GOV\n"
+
+        if [ $CUR_GOV == "userspace" ]; then
+                set_cpu_frequency $1 $CUR_FREQ
+                printf "Governor frequency restored for $1: $CUR_FREQ\n"
+        fi
+
+        printf "\n"
+}
+
+# param:
+# $1: policy, $2: governor
+__switch_governor()
+{
+        echo $2 > $CPUFREQROOT/$1/scaling_governor
+}
+
+# param:
+# $1: cpu, $2: governor
+__switch_governor_for_cpu()
+{
+        echo $2 > $CPUROOT/$1/cpufreq/scaling_governor
+}
+
+# SWITCH GOVERNORS
+
+# $1: cpu, $2: governor
+switch_governor()
+{
+        local filepath=$CPUFREQROOT/$1/scaling_available_governors
+
+        # check if governor is available
+        local found=$(cat $filepath | grep $2 | wc -l)
+        if [ $found = 0 ]; then
+                echo 1;
+                return
+        fi
+
+        __switch_governor $1 $2
+        echo 0;
+}
+
+# $1: policy, $2: governor
+switch_show_governor()
+{
+        cur_gov=find_current_governor
+        if [ $cur_gov == "userspace" ]; then
+                cur_freq=find_current_freq
+        fi
+
+        # switch governor
+        __switch_governor $1 $2
+
+        printf "\nSwitched governor for $1 to $2\n\n"
+
+        if [ $2 == "userspace" -o $2 == "powersave" -o $2 == "performance" ]; then
+                printf "No files to read for $2 governor\n\n"
+                return
+        fi
+
+        # show governor files
+        local govpath=$(find_gov_directory $1 $2)
+        read_cpufreq_files_in_dir $govpath
+}
+
+# $1: function to be called, $2: policy
+call_for_each_governor()
+{
+        local filepath=$CPUFREQROOT/$2/scaling_available_governors
+
+        # Exit if cpu isn't managed by cpufreq core
+        if [ ! -f $filepath ]; then
+                return;
+        fi
+
+        backup_governor $2
+
+        local governors=$(cat $filepath)
+        printf "Available governors for $2: $governors\n"
+
+        for governor in $governors; do
+                $1 $2 $governor
+        done
+
+        restore_governor $2
+}
+
+# $1: loop count
+shuffle_governors_for_all_cpus()
+{
+        printf "** Test: Running ${FUNCNAME[0]} for $1 loops **\n\n"
+
+        for i in `seq 1 $1`; do
+                for_each_policy call_for_each_governor switch_show_governor
+        done
+        printf "%s\n\n" "------------------------------------------------"
+}
diff --git a/tools/testing/selftests/cpufreq/main.sh b/tools/testing/selftests/cpufreq/main.sh
new file mode 100755
index 000000000000..01bac76ac0ec
--- /dev/null
+++ b/tools/testing/selftests/cpufreq/main.sh
@@ -0,0 +1,194 @@
+#!/bin/bash
+
+source cpu.sh
+source cpufreq.sh
+source governor.sh
+source module.sh
+source special-tests.sh
+
+FUNC=basic      # do basic tests by default
+OUTFILE=cpufreq_selftest
+SYSFS=
+CPUROOT=
+CPUFREQROOT=
+
+helpme()
+{
+        printf "Usage: $0 [-h] [-todg args]
+        [-h <help>]
+        [-o <output-file-for-dump>]
+        [-t <basic: Basic cpufreq testing
+             suspend: suspend/resume,
+             hibernate: hibernate/resume,
+             modtest: test driver or governor modules. Only to be used with -d or -g options,
+             sptest1: Simple governor switch to produce lockdep.
+             sptest2: Concurrent governor switch to produce lockdep.
+             sptest3: Governor races, shuffle between governors quickly.
+             sptest4: CPU hotplugs with updates to cpufreq files.>]
+        [-d <driver's module name: only with \"-t modtest>\"]
+        [-g <governor's module name: only with \"-t modtest>\"]
+        \n"
+        exit 2
+}
+
+prerequisite()
+{
+        msg="skip all tests:"
+
+        if [ $UID != 0 ]; then
+                echo $msg must be run as root >&2
+                exit 2
+        fi
+
+        taskset -p 01 $$
+
+        SYSFS=`mount -t sysfs | head -1 | awk '{ print $3 }'`
+
+        if [ ! -d "$SYSFS" ]; then
+                echo $msg sysfs is not mounted >&2
+                exit 2
+        fi
+
+        CPUROOT=$SYSFS/devices/system/cpu
+        CPUFREQROOT="$CPUROOT/cpufreq"
+
+        if ! ls $CPUROOT/cpu* > /dev/null 2>&1; then
+                echo $msg cpus not available in sysfs >&2
+                exit 2
+        fi
+
+        if ! ls $CPUROOT/cpufreq > /dev/null 2>&1; then
+                echo $msg cpufreq directory not available in sysfs >&2
+                exit 2
+        fi
+}
+
+parse_arguments()
+{
+        while getopts ht:o:d:g: arg
+        do
+                case $arg in
+                        h) # --help
+                                helpme
+                                ;;
+
+                        t) # --func_type (Function to perform: basic, suspend, hibernate, modtest, sptest1/2/3/4 (default: basic))
+                                FUNC=$OPTARG
+                                ;;
+
+                        o) # --output-file (Output file to store dumps)
+                                OUTFILE=$OPTARG
+                                ;;
+
+                        d) # --driver-mod-name (Name of the driver module)
+                                DRIVER_MOD=$OPTARG
+                                ;;
+
+                        g) # --governor-mod-name (Name of the governor module)
+                                GOVERNOR_MOD=$OPTARG
+                                ;;
+
+                        \?)
+                                helpme
+                                ;;
+                esac
+        done
+}
+
+do_test()
+{
+        # Check if CPUs are managed by cpufreq or not
+        count=$(count_cpufreq_managed_cpus)
+
+        if [ $count = 0 -a $FUNC != "modtest" ]; then
+                echo "No cpu is managed by cpufreq core, exiting"
+                exit 2;
+        fi
+
+        case "$FUNC" in
+                "basic")
+                cpufreq_basic_tests
+                ;;
+
+                "suspend")
+                do_suspend "suspend" 1
+                ;;
+
+                "hibernate")
+                do_suspend "hibernate" 1
+                ;;
+
+                "modtest")
+                # Do we have modules in place?
+                if [ -z $DRIVER_MOD ] && [ -z $GOVERNOR_MOD ]; then
+                        echo "No driver or governor module passed with -d or -g"
+                        exit 2;
+                fi
+
+                if [ $DRIVER_MOD ]; then
+                        if [ $GOVERNOR_MOD ]; then
+                                module_test $DRIVER_MOD $GOVERNOR_MOD
+                        else
+                                module_driver_test $DRIVER_MOD
+                        fi
+                else
+                        if [ $count = 0 ]; then
+                                echo "No cpu is managed by cpufreq core, exiting"
+                                exit 2;
+                        fi
+
+                        module_governor_test $GOVERNOR_MOD
+                fi
+                ;;
+
+                "sptest1")
+                simple_lockdep
+                ;;
+
+                "sptest2")
+                concurrent_lockdep
+                ;;
+
+                "sptest3")
+                governor_race
+                ;;
+
+                "sptest4")
+                hotplug_with_updates
+                ;;
+
+                *)
+                echo "Invalid [-f] function type"
+                helpme
+                ;;
+        esac
+}
+
+# clear dumps
+# $1: file name
+clear_dumps()
+{
+        echo "" > $1.txt
+        echo "" > $1.dmesg_cpufreq.txt
+        echo "" > $1.dmesg_full.txt
+}
+
+# $1: output file name
+dmesg_dumps()
+{
+        dmesg | grep cpufreq >> $1.dmesg_cpufreq.txt
+
+        # We may need the full logs as well
+        dmesg >> $1.dmesg_full.txt
+}
+
+# Parse arguments
+parse_arguments $@
+
+# Make sure all requirements are met
+prerequisite
+
+# Run requested functions
+clear_dumps $OUTFILE
+do_test >> $OUTFILE.txt
+dmesg_dumps $OUTFILE
diff --git a/tools/testing/selftests/cpufreq/module.sh b/tools/testing/selftests/cpufreq/module.sh
new file mode 100755
index 000000000000..8ff2244a33a1
--- /dev/null
+++ b/tools/testing/selftests/cpufreq/module.sh
@@ -0,0 +1,243 @@
+#!/bin/bash
+#
+# Modules specific tests cases
+
+# protect against multiple inclusion
+if [ $FILE_MODULE ]; then
+        return 0
+else
+        FILE_MODULE=DONE
+fi
+
+source cpu.sh
+source cpufreq.sh
+source governor.sh
+
+# Check basic insmod/rmmod
+# $1: module
+test_basic_insmod_rmmod()
+{
+        printf "** Test: Running ${FUNCNAME[0]} **\n\n"
+
+        printf "Inserting $1 module\n"
+        # insert module
+        insmod $1
+        if [ $? != 0 ]; then
+                printf "Insmod $1 failed\n"
+                exit;
+        fi
+
+        printf "Removing $1 module\n"
+        # remove module
+        rmmod $1
+        if [ $? != 0 ]; then
+                printf "rmmod $1 failed\n"
+                exit;
+        fi
+
+        printf "\n"
+}
+
+# Insert cpufreq driver module and perform basic tests
+# $1: cpufreq-driver module to insert
+# $2: If we want to play with CPUs (1) or not (0)
+module_driver_test_single()
+{
+        printf "** Test: Running ${FUNCNAME[0]} for driver $1 and cpus_hotplug=$2 **\n\n"
+
+        if [ $2 -eq 1 ]; then
+                # offline all non-boot CPUs
+                for_each_non_boot_cpu offline_cpu
+                printf "\n"
+        fi
+
+        # insert module
+        printf "Inserting $1 module\n\n"
+        insmod $1
+        if [ $? != 0 ]; then
+                printf "Insmod $1 failed\n"
+                return;
+        fi
+
+        if [ $2 -eq 1 ]; then
+                # online all non-boot CPUs
+                for_each_non_boot_cpu online_cpu
+                printf "\n"
+        fi
+
+        # run basic tests
+        cpufreq_basic_tests
+
+        # remove module
+        printf "Removing $1 module\n\n"
+        rmmod $1
+        if [ $? != 0 ]; then
+                printf "rmmod $1 failed\n"
+                return;
+        fi
+
+        # There shouldn't be any cpufreq directories now.
+        for_each_cpu cpu_should_not_have_cpufreq_directory
+        printf "\n"
+}
+
+# $1: cpufreq-driver module to insert
+module_driver_test()
+{
+        printf "** Test: Running ${FUNCNAME[0]} **\n\n"
+
+        # check if module is present or not
+        ls $1 > /dev/null
+        if [ $? != 0 ]; then
+                printf "$1: not present in `pwd` folder\n"
+                return;
+        fi
+
+        # test basic module tests
+        test_basic_insmod_rmmod $1
+
+        # Do simple module test
+        module_driver_test_single $1 0
+
+        # Remove CPUs before inserting module and then bring them back
+        module_driver_test_single $1 1
+        printf "\n"
+}
+
+# find governor name based on governor module name
+# $1: governor module name
+find_gov_name()
+{
+        if [ $1 = "cpufreq_ondemand.ko" ]; then
+                printf "ondemand"
+        elif [ $1 = "cpufreq_conservative.ko" ]; then
+                printf "conservative"
+        elif [ $1 = "cpufreq_userspace.ko" ]; then
+                printf "userspace"
+        elif [ $1 = "cpufreq_performance.ko" ]; then
+                printf "performance"
+        elif [ $1 = "cpufreq_powersave.ko" ]; then
+                printf "powersave"
+        elif [ $1 = "cpufreq_schedutil.ko" ]; then
+                printf "schedutil"
+        fi
+}
+
+# $1: governor string, $2: governor module, $3: policy
+# example: module_governor_test_single "ondemand" "cpufreq_ondemand.ko" 2
+module_governor_test_single()
+{
+        printf "** Test: Running ${FUNCNAME[0]} for $3 **\n\n"
+
+        backup_governor $3
+
+        # switch to new governor
+        printf "Switch from $CUR_GOV to $1\n"
+        switch_show_governor $3 $1
+
+        # try removing module, it should fail as governor is used
+        printf "Removing $2 module\n\n"
+        rmmod $2
+        if [ $? = 0 ]; then
+                printf "WARN: rmmod $2 succeeded even if governor is used\n"
+                insmod $2
+        else
+                printf "Pass: unable to remove $2 while it is being used\n\n"
+        fi
+
+        # switch back to old governor
+        printf "Switchback to $CUR_GOV from $1\n"
+        restore_governor $3
+        printf "\n"
+}
+
+# Insert cpufreq governor module and perform basic tests
+# $1: cpufreq-governor module to insert
+module_governor_test()
+{
+        printf "** Test: Running ${FUNCNAME[0]} **\n\n"
+
+        # check if module is present or not
+        ls $1 > /dev/null
+        if [ $? != 0 ]; then
+                printf "$1: not present in `pwd` folder\n"
+                return;
+        fi
+
+        # test basic module tests
+        test_basic_insmod_rmmod $1
+
+        # insert module
+        printf "Inserting $1 module\n\n"
+        insmod $1
+        if [ $? != 0 ]; then
+                printf "Insmod $1 failed\n"
+                return;
+        fi
+
+        # switch to new governor for each cpu
+        for_each_policy module_governor_test_single $(find_gov_name $1) $1
+
+        # remove module
+        printf "Removing $1 module\n\n"
+        rmmod $1
+        if [ $? != 0 ]; then
+                printf "rmmod $1 failed\n"
+                return;
+        fi
+        printf "\n"
+}
+
+# test modules: driver and governor
+# $1: driver module, $2: governor module
+module_test()
+{
+        printf "** Test: Running ${FUNCNAME[0]} **\n\n"
+
+        # check if modules are present or not
+        ls $1 $2 > /dev/null
+        if [ $? != 0 ]; then
+                printf "$1 or $2: is not present in `pwd` folder\n"
+                return;
+        fi
+
+        # TEST1: Insert gov after driver
+        # insert driver module
+        printf "Inserting $1 module\n\n"
+        insmod $1
+        if [ $? != 0 ]; then
+                printf "Insmod $1 failed\n"
+                return;
+        fi
+
+        # run governor tests
+        module_governor_test $2
+
+        # remove driver module
+        printf "Removing $1 module\n\n"
+        rmmod $1
+        if [ $? != 0 ]; then
+                printf "rmmod $1 failed\n"
+                return;
+        fi
+
+        # TEST2: Insert driver after governor
+        # insert governor module
+        printf "Inserting $2 module\n\n"
+        insmod $2
+        if [ $? != 0 ]; then
+                printf "Insmod $2 failed\n"
+                return;
+        fi
+
+        # run governor tests
+        module_driver_test $1
+
+        # remove driver module
+        printf "Removing $2 module\n\n"
+        rmmod $2
+        if [ $? != 0 ]; then
+                printf "rmmod $2 failed\n"
+                return;
+        fi
+}
diff --git a/tools/testing/selftests/cpufreq/special-tests.sh b/tools/testing/selftests/cpufreq/special-tests.sh
new file mode 100755
index 000000000000..58b730f23ef7
--- /dev/null
+++ b/tools/testing/selftests/cpufreq/special-tests.sh
@@ -0,0 +1,115 @@
+#!/bin/bash
+#
+# Special test cases reported by people
+
+# Testcase 1: Reported here: http://marc.info/?l=linux-pm&m=140618592709858&w=2
+
+# protect against multiple inclusion
+if [ $FILE_SPECIAL ]; then
+        return 0
+else
+        FILE_SPECIAL=DONE
+fi
+
+source cpu.sh
+source cpufreq.sh
+source governor.sh
+
+# Test 1
+# $1: policy
+__simple_lockdep()
+{
+        # switch to ondemand
+        __switch_governor $1 "ondemand"
+
+        # cat ondemand files
+        local ondir=$(find_gov_directory $1 "ondemand")
+        if [ -z $ondir ]; then
+                printf "${FUNCNAME[0]}Ondemand directory not created, quit"
+                return
+        fi
+
+        cat $ondir/*
+
+        # switch to conservative
+        __switch_governor $1 "conservative"
+}
+
+simple_lockdep()
+{
+        printf "** Test: Running ${FUNCNAME[0]} **\n"
+
+        for_each_policy __simple_lockdep
+}
+
+# Test 2
+# $1: policy
+__concurrent_lockdep()
+{
+        for i in `seq 0 100`; do
+                __simple_lockdep $1
+        done
+}
+
+concurrent_lockdep()
+{
+        printf "** Test: Running ${FUNCNAME[0]} **\n"
+
+        for_each_policy_concurrent __concurrent_lockdep
+}
+
+# Test 3
+quick_shuffle()
+{
+        # this is called concurrently from governor_race
+        for I in `seq 1000`
+        do
+                echo ondemand | sudo tee $CPUFREQROOT/policy*/scaling_governor &
+                echo userspace | sudo tee $CPUFREQROOT/policy*/scaling_governor &
+        done
+}
+
+governor_race()
+{
+        printf "** Test: Running ${FUNCNAME[0]} **\n"
+
+        # run 8 concurrent instances
+        for I in `seq 8`
+        do
+                quick_shuffle &
+        done
+}
+
+# Test 4
+# $1: cpu
+hotplug_with_updates_cpu()
+{
+        local filepath="$CPUROOT/$1/cpufreq"
+
+        # switch to ondemand
+        __switch_governor_for_cpu $1 "ondemand"
+
+        for i in `seq 1 5000`
+        do
+                reboot_cpu $1
+        done &
+
+        local freqs=$(cat $filepath/scaling_available_frequencies)
+        local oldfreq=$(cat $filepath/scaling_min_freq)
+
+        for j in `seq 1 5000`
+        do
+                # Set all frequencies one-by-one
+                for freq in $freqs; do
+                        echo $freq > $filepath/scaling_min_freq
+                done
+        done
+
+        # restore old freq
+        echo $oldfreq > $filepath/scaling_min_freq
+}
+
+hotplug_with_updates()
+{
+        for_each_non_boot_cpu hotplug_with_updates_cpu
+}
diff --git a/tools/testing/selftests/drivers/gpu/drm_mm.sh b/tools/testing/selftests/drivers/gpu/drm_mm.sh
new file mode 100755
index 000000000000..96dd55c92799
--- /dev/null
+++ b/tools/testing/selftests/drivers/gpu/drm_mm.sh
@@ -0,0 +1,15 @@
+#!/bin/sh
+# Runs API tests for struct drm_mm (DRM range manager)
+
+if ! /sbin/modprobe -n -q test-drm_mm; then
+       echo "drivers/gpu/drm_mm: [skip]"
+       exit 77
+fi
+
+if /sbin/modprobe -q test-drm_mm; then
+       /sbin/modprobe -q -r test-drm_mm
+       echo "drivers/gpu/drm_mm: ok"
+else
+       echo "drivers/gpu/drm_mm: [FAIL]"
+       exit 1
+fi
diff --git a/tools/testing/selftests/efivarfs/Makefile b/tools/testing/selftests/efivarfs/Makefile
index 736c3ddfc787..c49dcea69319 100644
--- a/tools/testing/selftests/efivarfs/Makefile
+++ b/tools/testing/selftests/efivarfs/Makefile
@@ -1,13 +1,7 @@
 CFLAGS = -Wall
 
-test_objs = open-unlink create-read
-
-all: $(test_objs)
-
+TEST_GEN_FILES := open-unlink create-read
 TEST_PROGS := efivarfs.sh
-TEST_FILES := $(test_objs)
 
 include ../lib.mk
 
-clean:
-        rm -f $(test_objs)
diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile
index d4300602bf37..2e13035dff7f 100644
--- a/tools/testing/selftests/exec/Makefile
+++ b/tools/testing/selftests/exec/Makefile
@@ -1,27 +1,23 @@
 CFLAGS = -Wall
-BINARIES = execveat
-DEPS = execveat.symlink execveat.denatured script subdir
-all: $(BINARIES) $(DEPS)
 
-subdir:
+TEST_GEN_PROGS := execveat
+TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir
+# Makefile is a run-time dependency, since it's accessed by the execveat test
+TEST_FILES := Makefile
+
+EXTRA_CLEAN := $(OUTPUT)/subdir.moved $(OUTPUT)/execveat.moved $(OUTPUT)/xxxxx*
+
+include ../lib.mk
+
+$(OUTPUT)/subdir:
         mkdir -p $@
-script:
+$(OUTPUT)/script:
         echo '#!/bin/sh' > $@
         echo 'exit $$*' >> $@
         chmod +x $@
-execveat.symlink: execveat
-        ln -s -f $< $@
-execveat.denatured: execveat
+$(OUTPUT)/execveat.symlink: $(OUTPUT)/execveat
+        cd $(OUTPUT) && ln -s -f $(shell basename $<) $(shell basename $@)
+$(OUTPUT)/execveat.denatured: $(OUTPUT)/execveat
         cp $< $@
         chmod -x $@
-%: %.c
-        $(CC) $(CFLAGS) -o $@ $^
-
-TEST_PROGS := execveat
-# Makefile is a run-time dependency, since it's accessed by the execveat test
-TEST_FILES := $(DEPS) Makefile
-
-include ../lib.mk
 
-clean:
-        rm -rf $(BINARIES) $(DEPS) subdir.moved execveat.moved xxxxx*
diff --git a/tools/testing/selftests/firmware/Makefile b/tools/testing/selftests/firmware/Makefile
index 9bf82234855b..1894d625af2d 100644
--- a/tools/testing/selftests/firmware/Makefile
+++ b/tools/testing/selftests/firmware/Makefile
@@ -3,7 +3,7 @@
 # No binaries, but make sure arg-less "make" doesn't trigger "run_tests"
 all:
 
-TEST_PROGS := fw_filesystem.sh fw_userhelper.sh
+TEST_PROGS := fw_filesystem.sh fw_fallback.sh
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/firmware/fw_fallback.sh b/tools/testing/selftests/firmware/fw_fallback.sh
new file mode 100755
index 000000000000..2e4c22d5abf7
--- /dev/null
+++ b/tools/testing/selftests/firmware/fw_fallback.sh
@@ -0,0 +1,224 @@
+#!/bin/sh
+# This validates that the kernel will fall back to using the fallback mechanism
+# to load firmware it can't find on disk itself. We must request a firmware
+# that the kernel won't find, and any installed helper (e.g. udev) also
+# won't find so that we can do the load ourself manually.
+set -e
+
+modprobe test_firmware
+
+DIR=/sys/devices/virtual/misc/test_firmware
+
+# CONFIG_FW_LOADER_USER_HELPER has a sysfs class under /sys/class/firmware/
+# These days no one enables CONFIG_FW_LOADER_USER_HELPER so check for that
+# as an indicator for CONFIG_FW_LOADER_USER_HELPER.
+HAS_FW_LOADER_USER_HELPER=$(if [ -d /sys/class/firmware/ ]; then echo yes; else echo no; fi)
+
+if [ "$HAS_FW_LOADER_USER_HELPER" = "yes" ]; then
+       OLD_TIMEOUT=$(cat /sys/class/firmware/timeout)
+else
+        echo "usermode helper disabled so ignoring test"
+        exit 0
+fi
+
+FWPATH=$(mktemp -d)
+FW="$FWPATH/test-firmware.bin"
+
+test_finish()
+{
+        echo "$OLD_TIMEOUT" >/sys/class/firmware/timeout
+        rm -f "$FW"
+        rmdir "$FWPATH"
+}
+
+load_fw()
+{
+        local name="$1"
+        local file="$2"
+
+        # This will block until our load (below) has finished.
+        echo -n "$name" >"$DIR"/trigger_request &
+
+        # Give kernel a chance to react.
+        local timeout=10
+        while [ ! -e "$DIR"/"$name"/loading ]; do
+                sleep 0.1
+                timeout=$(( $timeout - 1 ))
+                if [ "$timeout" -eq 0 ]; then
+                        echo "$0: firmware interface never appeared" >&2
+                        exit 1
+                fi
+        done
+
+        echo 1 >"$DIR"/"$name"/loading
+        cat "$file" >"$DIR"/"$name"/data
+        echo 0 >"$DIR"/"$name"/loading
+
+        # Wait for request to finish.
+        wait
+}
+
+load_fw_cancel()
+{
+        local name="$1"
+        local file="$2"
+
+        # This will block until our load (below) has finished.
+        echo -n "$name" >"$DIR"/trigger_request 2>/dev/null &
+
+        # Give kernel a chance to react.
+        local timeout=10
+        while [ ! -e "$DIR"/"$name"/loading ]; do
+                sleep 0.1
+                timeout=$(( $timeout - 1 ))
+                if [ "$timeout" -eq 0 ]; then
+                        echo "$0: firmware interface never appeared" >&2
+                        exit 1
+                fi
+        done
+
+        echo -1 >"$DIR"/"$name"/loading
+
+        # Wait for request to finish.
+        wait
+}
+
+load_fw_custom()
+{
+        local name="$1"
+        local file="$2"
+
+        echo -n "$name" >"$DIR"/trigger_custom_fallback 2>/dev/null &
+
+        # Give kernel a chance to react.
+        local timeout=10
+        while [ ! -e "$DIR"/"$name"/loading ]; do
+                sleep 0.1
+                timeout=$(( $timeout - 1 ))
+                if [ "$timeout" -eq 0 ]; then
+                        echo "$0: firmware interface never appeared" >&2
+                        exit 1
+                fi
+        done
+
+        echo 1 >"$DIR"/"$name"/loading
+        cat "$file" >"$DIR"/"$name"/data
+        echo 0 >"$DIR"/"$name"/loading
+
+        # Wait for request to finish.
+        wait
+}
+
+
+load_fw_custom_cancel()
+{
+        local name="$1"
+        local file="$2"
+
+        echo -n "$name" >"$DIR"/trigger_custom_fallback 2>/dev/null &
+
+        # Give kernel a chance to react.
+        local timeout=10
+        while [ ! -e "$DIR"/"$name"/loading ]; do
+                sleep 0.1
+                timeout=$(( $timeout - 1 ))
+                if [ "$timeout" -eq 0 ]; then
+                        echo "$0: firmware interface never appeared" >&2
+                        exit 1
+                fi
+        done
+
+        echo -1 >"$DIR"/"$name"/loading
+
+        # Wait for request to finish.
+        wait
+}
+
+
+trap "test_finish" EXIT
+
+# This is an unlikely real-world firmware content. :)
+echo "ABCD0123" >"$FW"
+NAME=$(basename "$FW")
+
+DEVPATH="$DIR"/"nope-$NAME"/loading
+
+# Test failure when doing nothing (timeout works).
+echo -n 2 >/sys/class/firmware/timeout
+echo -n "nope-$NAME" >"$DIR"/trigger_request 2>/dev/null &
+
+# Give the kernel some time to load the loading file, must be less
+# than the timeout above.
+sleep 1
+if [ ! -f $DEVPATH ]; then
+        echo "$0: fallback mechanism immediately cancelled"
+        echo ""
+        echo "The file never appeared: $DEVPATH"
+        echo ""
+        echo "This might be a distribution udev rule setup by your distribution"
+        echo "to immediately cancel all fallback requests, this must be"
+        echo "removed before running these tests. To confirm look for"
+        echo "a firmware rule like /lib/udev/rules.d/50-firmware.rules"
+        echo "and see if you have something like this:"
+        echo ""
+        echo "SUBSYSTEM==\"firmware\", ACTION==\"add\", ATTR{loading}=\"-1\""
+        echo ""
+        echo "If you do remove this file or comment out this line before"
+        echo "proceeding with these tests."
+        exit 1
+fi
+
+if diff -q "$FW" /dev/test_firmware >/dev/null ; then
+        echo "$0: firmware was not expected to match" >&2
+        exit 1
+else
+        echo "$0: timeout works"
+fi
+
+# Put timeout high enough for us to do work but not so long that failures
+# slow down this test too much.
+echo 4 >/sys/class/firmware/timeout
+
+# Load this script instead of the desired firmware.
+load_fw "$NAME" "$0"
+if diff -q "$FW" /dev/test_firmware >/dev/null ; then
+        echo "$0: firmware was not expected to match" >&2
+        exit 1
+else
+        echo "$0: firmware comparison works"
+fi
+
+# Do a proper load, which should work correctly.
+load_fw "$NAME" "$FW"
+if ! diff -q "$FW" /dev/test_firmware >/dev/null ; then
+        echo "$0: firmware was not loaded" >&2
+        exit 1
+else
+        echo "$0: fallback mechanism works"
+fi
+
+load_fw_cancel "nope-$NAME" "$FW"
+if diff -q "$FW" /dev/test_firmware >/dev/null ; then
+        echo "$0: firmware was expected to be cancelled" >&2
+        exit 1
+else
+        echo "$0: cancelling fallback mechanism works"
+fi
+
+load_fw_custom "$NAME" "$FW"
+if ! diff -q "$FW" /dev/test_firmware >/dev/null ; then
+        echo "$0: firmware was not loaded" >&2
+        exit 1
+else
+        echo "$0: custom fallback loading mechanism works"
+fi
+
+load_fw_custom_cancel "nope-$NAME" "$FW"
+if diff -q "$FW" /dev/test_firmware >/dev/null ; then
+        echo "$0: firmware was expected to be cancelled" >&2
+        exit 1
+else
+        echo "$0: cancelling custom fallback mechanism works"
+fi
+
+exit 0
diff --git a/tools/testing/selftests/firmware/fw_filesystem.sh b/tools/testing/selftests/firmware/fw_filesystem.sh
index 5c495ad7958a..e35691239350 100755
--- a/tools/testing/selftests/firmware/fw_filesystem.sh
+++ b/tools/testing/selftests/firmware/fw_filesystem.sh
@@ -5,9 +5,24 @@
 # know so we can be sure we're not accidentally testing the user helper.
 set -e
 
-modprobe test_firmware
-
 DIR=/sys/devices/virtual/misc/test_firmware
+TEST_DIR=$(dirname $0)
+
+test_modprobe()
+{
+        if [ ! -d $DIR ]; then
+                echo "$0: $DIR not present"
+                echo "You must have the following enabled in your kernel:"
+                cat $TEST_DIR/config
+                exit 1
+        fi
+}
+
+trap "test_modprobe" EXIT
+
+if [ ! -d $DIR ]; then
+        modprobe test_firmware
+fi
 
 # CONFIG_FW_LOADER_USER_HELPER has a sysfs class under /sys/class/firmware/
 # These days no one enables CONFIG_FW_LOADER_USER_HELPER so check for that
@@ -48,18 +63,18 @@ echo "ABCD0123" >"$FW"
 
 NAME=$(basename "$FW")
 
-if printf '\000' >"$DIR"/trigger_request; then
+if printf '\000' >"$DIR"/trigger_request 2> /dev/null; then
         echo "$0: empty filename should not succeed" >&2
         exit 1
 fi
 
-if printf '\000' >"$DIR"/trigger_async_request; then
+if printf '\000' >"$DIR"/trigger_async_request 2> /dev/null; then
         echo "$0: empty filename should not succeed (async)" >&2
         exit 1
 fi
 
 # Request a firmware that doesn't exist, it should fail.
-if echo -n "nope-$NAME" >"$DIR"/trigger_request; then
+if echo -n "nope-$NAME" >"$DIR"/trigger_request 2> /dev/null; then
         echo "$0: firmware shouldn't have loaded" >&2
         exit 1
 fi
diff --git a/tools/testing/selftests/firmware/fw_userhelper.sh b/tools/testing/selftests/firmware/fw_userhelper.sh
deleted file mode 100755
index b9983f8e09f6..000000000000
--- a/tools/testing/selftests/firmware/fw_userhelper.sh
+++ /dev/null
@@ -1,99 +0,0 @@
-#!/bin/sh
-# This validates that the kernel will fall back to using the user helper
-# to load firmware it can't find on disk itself. We must request a firmware
-# that the kernel won't find, and any installed helper (e.g. udev) also
-# won't find so that we can do the load ourself manually.
-set -e
-
-modprobe test_firmware
-
-DIR=/sys/devices/virtual/misc/test_firmware
-
-# CONFIG_FW_LOADER_USER_HELPER has a sysfs class under /sys/class/firmware/
-# These days no one enables CONFIG_FW_LOADER_USER_HELPER so check for that
-# as an indicator for CONFIG_FW_LOADER_USER_HELPER.
-HAS_FW_LOADER_USER_HELPER=$(if [ -d /sys/class/firmware/ ]; then echo yes; else echo no; fi)
-
-if [ "$HAS_FW_LOADER_USER_HELPER" = "yes" ]; then
-       OLD_TIMEOUT=$(cat /sys/class/firmware/timeout)
-else
-        echo "usermode helper disabled so ignoring test"
-        exit 0
-fi
-
-FWPATH=$(mktemp -d)
-FW="$FWPATH/test-firmware.bin"
-
-test_finish()
-{
-        echo "$OLD_TIMEOUT" >/sys/class/firmware/timeout
-        rm -f "$FW"
-        rmdir "$FWPATH"
-}
-
-load_fw()
-{
-        local name="$1"
-        local file="$2"
-
-        # This will block until our load (below) has finished.
-        echo -n "$name" >"$DIR"/trigger_request &
-
-        # Give kernel a chance to react.
-        local timeout=10
-        while [ ! -e "$DIR"/"$name"/loading ]; do
-                sleep 0.1
-                timeout=$(( $timeout - 1 ))
-                if [ "$timeout" -eq 0 ]; then
-                        echo "$0: firmware interface never appeared" >&2
-                        exit 1
-                fi
-        done
-
-        echo 1 >"$DIR"/"$name"/loading
-        cat "$file" >"$DIR"/"$name"/data
-        echo 0 >"$DIR"/"$name"/loading
-
-        # Wait for request to finish.
-        wait
-}
-
-trap "test_finish" EXIT
-
-# This is an unlikely real-world firmware content. :)
-echo "ABCD0123" >"$FW"
-NAME=$(basename "$FW")
-
-# Test failure when doing nothing (timeout works).
-echo 1 >/sys/class/firmware/timeout
-echo -n "$NAME" >"$DIR"/trigger_request
-if diff -q "$FW" /dev/test_firmware >/dev/null ; then
-        echo "$0: firmware was not expected to match" >&2
-        exit 1
-else
-        echo "$0: timeout works"
-fi
-
-# Put timeout high enough for us to do work but not so long that failures
-# slow down this test too much.
-echo 4 >/sys/class/firmware/timeout
-
-# Load this script instead of the desired firmware.
-load_fw "$NAME" "$0"
-if diff -q "$FW" /dev/test_firmware >/dev/null ; then
-        echo "$0: firmware was not expected to match" >&2
-        exit 1
-else
-        echo "$0: firmware comparison works"
-fi
-
-# Do a proper load, which should work correctly.
-load_fw "$NAME" "$FW"
-if ! diff -q "$FW" /dev/test_firmware >/dev/null ; then
-        echo "$0: firmware was not loaded" >&2
-        exit 1
-else
-        echo "$0: user helper firmware loading works"
-fi
-
-exit 0
diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile
index 4e6ed13e7f66..a8a5e21850e7 100644
--- a/tools/testing/selftests/ftrace/Makefile
+++ b/tools/testing/selftests/ftrace/Makefile
@@ -1,9 +1,7 @@
 all:
 
 TEST_PROGS := ftracetest
-TEST_DIRS := test.d
+TEST_FILES := test.d
+EXTRA_CLEAN := $(OUTPUT)/logs/*
 
 include ../lib.mk
-
-clean:
-        rm -rf logs/*
diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile
index 6a1752956283..653c5cd9e44d 100644
--- a/tools/testing/selftests/futex/Makefile
+++ b/tools/testing/selftests/futex/Makefile
@@ -3,13 +3,18 @@ SUBDIRS := functional
 TEST_PROGS := run.sh
 
 .PHONY: all clean
-all:
-        for DIR in $(SUBDIRS); do $(MAKE) -C $$DIR $@ ; done
 
 include ../lib.mk
 
+all:
+        for DIR in $(SUBDIRS); do               \
+                BUILD_TARGET=$$OUTPUT/$$DIR;    \
+                mkdir $$BUILD_TARGET  -p;       \
+                make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
+        done
+
 override define RUN_TESTS
-        ./run.sh
+        @if [ `dirname $(OUTPUT)` = $(PWD) ]; then ./run.sh; fi
 endef
 
 override define INSTALL_RULE
@@ -17,7 +22,9 @@ override define INSTALL_RULE
         install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)
 
         @for SUBDIR in $(SUBDIRS); do \
-                $(MAKE) -C $$SUBDIR INSTALL_PATH=$(INSTALL_PATH)/$$SUBDIR install; \
+                BUILD_TARGET=$$OUTPUT/$$SUBDIR; \
+                mkdir $$BUILD_TARGET  -p;       \
+                $(MAKE) OUTPUT=$$BUILD_TARGET -C $$SUBDIR INSTALL_PATH=$(INSTALL_PATH)/$$SUBDIR install; \
         done;
 endef
 
@@ -26,4 +33,8 @@ override define EMIT_TESTS
 endef
 
 clean:
-        for DIR in $(SUBDIRS); do $(MAKE) -C $$DIR $@ ; done
+        for DIR in $(SUBDIRS); do               \
+                BUILD_TARGET=$$OUTPUT/$$DIR;    \
+                mkdir $$BUILD_TARGET  -p;       \
+                make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
+        done
diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile
index 9d6b75ef7b5d..a648e7a6cbc3 100644
--- a/tools/testing/selftests/futex/functional/Makefile
+++ b/tools/testing/selftests/futex/functional/Makefile
@@ -2,8 +2,11 @@ INCLUDES := -I../include -I../../
 CFLAGS := $(CFLAGS) -g -O2 -Wall -D_GNU_SOURCE -pthread $(INCLUDES)
 LDFLAGS := $(LDFLAGS) -pthread -lrt
 
-HEADERS := ../include/futextest.h
-TARGETS := \
+HEADERS := \
+        ../include/futextest.h \
+        ../include/atomic.h \
+        ../include/logging.h
+TEST_GEN_FILES := \
         futex_wait_timeout \
         futex_wait_wouldblock \
         futex_requeue_pi \
@@ -12,14 +15,8 @@ TARGETS := \
         futex_wait_uninitialized_heap \
         futex_wait_private_mapped_file
 
-TEST_PROGS := $(TARGETS) run.sh
-
-.PHONY: all clean
-all: $(TARGETS)
-
-$(TARGETS): $(HEADERS)
+TEST_PROGS := run.sh
 
 include ../../lib.mk
 
-clean:
-        rm -f $(TARGETS)
+$(TEST_GEN_FILES): $(HEADERS)
diff --git a/tools/testing/selftests/futex/include/logging.h b/tools/testing/selftests/futex/include/logging.h
index 014aa01197af..e14469103f07 100644
--- a/tools/testing/selftests/futex/include/logging.h
+++ b/tools/testing/selftests/futex/include/logging.h
@@ -21,6 +21,7 @@
 #ifndef _LOGGING_H
 #define _LOGGING_H
 
+#include <stdio.h>
 #include <string.h>
 #include <unistd.h>
 #include <linux/futex.h>
diff --git a/tools/testing/selftests/gpio/.gitignore b/tools/testing/selftests/gpio/.gitignore
new file mode 100644
index 000000000000..7d14f743d1a4
--- /dev/null
+++ b/tools/testing/selftests/gpio/.gitignore
@@ -0,0 +1 @@
+gpio-mockup-chardev
diff --git a/tools/testing/selftests/intel_pstate/Makefile b/tools/testing/selftests/intel_pstate/Makefile
index f5f1a28715ff..19678e90efb2 100644
--- a/tools/testing/selftests/intel_pstate/Makefile
+++ b/tools/testing/selftests/intel_pstate/Makefile
@@ -1,15 +1,10 @@
-CC := $(CROSS_COMPILE)gcc
 CFLAGS := $(CFLAGS) -Wall -D_GNU_SOURCE
 LDFLAGS := $(LDFLAGS) -lm
 
-TARGETS := msr aperf
+TEST_GEN_FILES := msr aperf
 
-TEST_PROGS := $(TARGETS) run.sh
+TEST_PROGS := run.sh
 
-.PHONY: all clean
-all: $(TARGETS)
+include ../lib.mk
 
-$(TARGETS): $(HEADERS)
-
-clean:
-        rm -f $(TARGETS)
+$(TEST_GEN_FILES): $(HEADERS)
diff --git a/tools/testing/selftests/intel_pstate/aperf.c b/tools/testing/selftests/intel_pstate/aperf.c
index 6046e183f4ad..cd72f3dc83e9 100644
--- a/tools/testing/selftests/intel_pstate/aperf.c
+++ b/tools/testing/selftests/intel_pstate/aperf.c
@@ -14,7 +14,7 @@ void usage(char *name) {
 }
 
 int main(int argc, char **argv) {
-        int i, cpu, fd;
+        unsigned int i, cpu, fd;
         char msr_file_name[64];
         long long tsc, old_tsc, new_tsc;
         long long aperf, old_aperf, new_aperf;
diff --git a/tools/testing/selftests/ipc/.gitignore b/tools/testing/selftests/ipc/.gitignore
index 84b66a3c1f74..9af04c9353c0 100644
--- a/tools/testing/selftests/ipc/.gitignore
+++ b/tools/testing/selftests/ipc/.gitignore
@@ -1 +1,2 @@
 msgque_test
+msgque
diff --git a/tools/testing/selftests/ipc/Makefile b/tools/testing/selftests/ipc/Makefile
index 25d2e702c68a..30ef4c7f53ea 100644
--- a/tools/testing/selftests/ipc/Makefile
+++ b/tools/testing/selftests/ipc/Makefile
@@ -11,12 +11,7 @@ endif
 
 CFLAGS += -I../../../../usr/include/
 
-all:
-        $(CC) $(CFLAGS) msgque.c -o msgque_test
-
-TEST_PROGS := msgque_test
+TEST_GEN_PROGS := msgque
 
 include ../lib.mk
 
-clean:
-        rm -fr ./msgque_test
diff --git a/tools/testing/selftests/kcmp/Makefile b/tools/testing/selftests/kcmp/Makefile
index 2ae7450a9a89..47aa9887f9d4 100644
--- a/tools/testing/selftests/kcmp/Makefile
+++ b/tools/testing/selftests/kcmp/Makefile
@@ -1,10 +1,8 @@
 CFLAGS += -I../../../../usr/include/
 
-all: kcmp_test
+TEST_GEN_PROGS := kcmp_test
 
-TEST_PROGS := kcmp_test
+EXTRA_CLEAN := $(OUTPUT)/kcmp-test-file
 
 include ../lib.mk
 
-clean:
-        $(RM) kcmp_test kcmp-test-file
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 50a93f5f13d6..775c589ac3c0 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -2,9 +2,19 @@
 # Makefile can operate with or without the kbuild infrastructure.
 CC := $(CROSS_COMPILE)gcc
 
+ifeq (0,$(MAKELEVEL))
+OUTPUT := $(shell pwd)
+endif
+
+TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS))
+TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES))
+
+all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
+
 define RUN_TESTS
-        @for TEST in $(TEST_PROGS); do \
-                (./$$TEST && echo "selftests: $$TEST [PASS]") || echo "selftests: $$TEST [FAIL]"; \
+        @for TEST in $(TEST_GEN_PROGS) $(TEST_PROGS); do \
+                BASENAME_TEST=`basename $$TEST`;        \
+                cd `dirname $$TEST`; (./$$BASENAME_TEST && echo "selftests: $$BASENAME_TEST [PASS]") || echo "selftests:  $$BASENAME_TEST [FAIL]"; cd -;\
         done;
 endef
 
@@ -14,8 +24,13 @@ run_tests: all
 define INSTALL_RULE
         @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then                                        \
                 mkdir -p ${INSTALL_PATH};                                                                               \
-                echo "rsync -a $(TEST_DIRS) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/";       \
-                rsync -a $(TEST_DIRS) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/;              \
+                echo "rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/";    \
+                rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/;           \
+        fi
+        @if [ "X$(TEST_GEN_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then                                    \
+                mkdir -p ${INSTALL_PATH};                                                                               \
+                echo "rsync -a $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/";        \
+                rsync -a $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/;               \
         fi
 endef
 
@@ -27,12 +42,25 @@ else
 endif
 
 define EMIT_TESTS
-        @for TEST in $(TEST_PROGS); do \
-                echo "(./$$TEST && echo \"selftests: $$TEST [PASS]\") || echo \"selftests: $$TEST [FAIL]\""; \
+        @for TEST in $(TEST_GEN_PROGS) $(TEST_PROGS); do \
+                BASENAME_TEST=`basename $$TEST`;        \
+                echo "(./$$BASENAME_TEST && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \
         done;
 endef
 
 emit_tests:
         $(EMIT_TESTS)
 
+clean:
+        $(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN)
+
+$(OUTPUT)/%:%.c
+        $(LINK.c) $^ $(LDLIBS) -o $@
+
+$(OUTPUT)/%.o:%.S
+        $(COMPILE.S) $^ -o $@
+
+$(OUTPUT)/%:%.S
+        $(LINK.S) $^ $(LDLIBS) -o $@
+
 .PHONY: run_tests all clean install emit_tests
diff --git a/tools/testing/selftests/lib/prime_numbers.sh b/tools/testing/selftests/lib/prime_numbers.sh
new file mode 100755
index 000000000000..da4cbcd766f5
--- /dev/null
+++ b/tools/testing/selftests/lib/prime_numbers.sh
@@ -0,0 +1,15 @@
+#!/bin/sh
+# Checks fast/slow prime_number generation for inconsistencies
+
+if ! /sbin/modprobe -q -r prime_numbers; then
+        echo "prime_numbers: [SKIP]"
+        exit 77
+fi
+
+if /sbin/modprobe -q prime_numbers selftest=65536; then
+        /sbin/modprobe -q -r prime_numbers
+        echo "prime_numbers: ok"
+else
+        echo "prime_numbers: [FAIL]"
+        exit 1
+fi
diff --git a/tools/testing/selftests/membarrier/Makefile b/tools/testing/selftests/membarrier/Makefile
index a1a97085847d..02845532b059 100644
--- a/tools/testing/selftests/membarrier/Makefile
+++ b/tools/testing/selftests/membarrier/Makefile
@@ -1,10 +1,6 @@
 CFLAGS += -g -I../../../../usr/include/
 
-TEST_PROGS := membarrier_test
-
-all: $(TEST_PROGS)
+TEST_GEN_PROGS := membarrier_test
 
 include ../lib.mk
 
-clean:
-        $(RM) $(TEST_PROGS)
diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile
index fd396ac811b6..79891d033de1 100644
--- a/tools/testing/selftests/memfd/Makefile
+++ b/tools/testing/selftests/memfd/Makefile
@@ -1,22 +1,13 @@
-CC = $(CROSS_COMPILE)gcc
 CFLAGS += -D_FILE_OFFSET_BITS=64
 CFLAGS += -I../../../../include/uapi/
 CFLAGS += -I../../../../include/
 CFLAGS += -I../../../../usr/include/
 
-TEST_PROGS := memfd_test
-
-all: $(TEST_PROGS)
-
-include ../lib.mk
-
-build_fuse: fuse_mnt fuse_test
+TEST_PROGS := run_fuse_test.sh
+TEST_GEN_FILES := memfd_test fuse_mnt fuse_test
 
 fuse_mnt.o: CFLAGS += $(shell pkg-config fuse --cflags)
 fuse_mnt: LDFLAGS += $(shell pkg-config fuse --libs)
 
-run_fuse: build_fuse
-        @./run_fuse_test.sh || echo "fuse_test: [FAIL]"
+include ../lib.mk
 
-clean:
-        $(RM) memfd_test fuse_test
diff --git a/tools/testing/selftests/mount/Makefile b/tools/testing/selftests/mount/Makefile
index 5e35c9c50b72..9093d7ffe87f 100644
--- a/tools/testing/selftests/mount/Makefile
+++ b/tools/testing/selftests/mount/Makefile
@@ -1,14 +1,11 @@
 # Makefile for mount selftests.
 CFLAGS = -Wall \
          -O2
-all: unprivileged-remount-test
 
-unprivileged-remount-test: unprivileged-remount-test.c
-        $(CC) $(CFLAGS) unprivileged-remount-test.c -o unprivileged-remount-test
+TEST_GEN_PROGS := unprivileged-remount-test
 
 include ../lib.mk
 
-TEST_PROGS := unprivileged-remount-test
 override RUN_TESTS := if [ -f /proc/self/uid_map ] ; \
                       then      \
                                 ./unprivileged-remount-test ; \
@@ -17,5 +14,3 @@ override RUN_TESTS := if [ -f /proc/self/uid_map ] ; \
                       fi
 override EMIT_TESTS := echo "$(RUN_TESTS)"
 
-clean:
-        rm -f unprivileged-remount-test
diff --git a/tools/testing/selftests/mqueue/Makefile b/tools/testing/selftests/mqueue/Makefile
index eebac29acbd9..79a664aeb8d7 100644
--- a/tools/testing/selftests/mqueue/Makefile
+++ b/tools/testing/selftests/mqueue/Makefile
@@ -1,8 +1,6 @@
 CFLAGS += -O2
 LDLIBS = -lrt -lpthread -lpopt
-TEST_PROGS := mq_open_tests mq_perf_tests
-
-all: $(TEST_PROGS)
+TEST_GEN_PROGS := mq_open_tests mq_perf_tests
 
 include ../lib.mk
 
@@ -16,5 +14,3 @@ override define EMIT_TESTS
         echo "./mq_perf_tests || echo \"selftests: mq_perf_tests [FAIL]\""
 endef
 
-clean:
-        rm -f mq_open_tests mq_perf_tests
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index e24e4c82542e..fbfe5d0d5c2e 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -3,20 +3,13 @@
 CFLAGS =  -Wall -Wl,--no-as-needed -O2 -g
 CFLAGS += -I../../../../usr/include/
 
-NET_PROGS =  socket
-NET_PROGS += psock_fanout psock_tpacket
-NET_PROGS += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
-NET_PROGS += reuseport_dualstack
-
-all: $(NET_PROGS)
 reuseport_bpf_numa: LDFLAGS += -lnuma
-%: %.c
-        $(CC) $(CFLAGS) $(LDFLAGS) -o $@ $^
 
 TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh
-TEST_FILES := $(NET_PROGS)
+TEST_GEN_FILES =  socket
+TEST_GEN_FILES += psock_fanout psock_tpacket
+TEST_GEN_FILES += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
+TEST_GEN_FILES += reuseport_dualstack
 
 include ../lib.mk
 
-clean:
-        $(RM) $(NET_PROGS)
diff --git a/tools/testing/selftests/net/psock_lib.h b/tools/testing/selftests/net/psock_lib.h
index 24bc7ec1be7d..a77da88bf946 100644
--- a/tools/testing/selftests/net/psock_lib.h
+++ b/tools/testing/selftests/net/psock_lib.h
@@ -40,14 +40,39 @@
 
 static __maybe_unused void sock_setfilter(int fd, int lvl, int optnum)
 {
+        /* the filter below checks for all of the following conditions that
+         * are based on the contents of create_payload()
+         *  ether type 0x800 and
+         *  ip proto udp     and
+         *  skb->len == DATA_LEN and
+         *  udp[38] == 'a' or udp[38] == 'b'
+         * It can be generated from the following bpf_asm input:
+         *      ldh [12]
+         *      jne #0x800, drop        ; ETH_P_IP
+         *      ldb [23]
+         *      jneq #17, drop          ; IPPROTO_UDP
+         *      ld len                  ; ld skb->len
+         *      jlt #100, drop          ; DATA_LEN
+         *      ldb [80]
+         *      jeq #97, pass           ; DATA_CHAR
+         *      jne #98, drop           ; DATA_CHAR_1
+         *      pass:
+         *        ret #-1
+         *      drop:
+         *        ret #0
+         */
         struct sock_filter bpf_filter[] = {
-                { 0x80, 0, 0, 0x00000000 },  /* LD  pktlen                    */
-                { 0x35, 0, 4, DATA_LEN   },  /* JGE DATA_LEN  [f goto nomatch]*/
-                { 0x30, 0, 0, 0x00000050 },  /* LD  ip[80]                    */
-                { 0x15, 1, 0, DATA_CHAR  },  /* JEQ DATA_CHAR   [t goto match]*/
-                { 0x15, 0, 1, DATA_CHAR_1},  /* JEQ DATA_CHAR_1 [t goto match]*/
-                { 0x06, 0, 0, 0x00000060 },  /* RET match                     */
-                { 0x06, 0, 0, 0x00000000 },  /* RET no match                  */
+                { 0x28,  0,  0, 0x0000000c },
+                { 0x15,  0,  8, 0x00000800 },
+                { 0x30,  0,  0, 0x00000017 },
+                { 0x15,  0,  6, 0x00000011 },
+                { 0x80,  0,  0, 0000000000 },
+                { 0x35,  0,  4, 0x00000064 },
+                { 0x30,  0,  0, 0x00000050 },
+                { 0x15,  1,  0, 0x00000061 },
+                { 0x15,  0,  1, 0x00000062 },
+                { 0x06,  0,  0, 0xffffffff },
+                { 0x06,  0,  0, 0000000000 },
         };
         struct sock_fprog bpf_prog;
 
diff --git a/tools/testing/selftests/net/psock_tpacket.c b/tools/testing/selftests/net/psock_tpacket.c
index 24adf709bd9d..7f6cd9fdacf3 100644
--- a/tools/testing/selftests/net/psock_tpacket.c
+++ b/tools/testing/selftests/net/psock_tpacket.c
@@ -110,7 +110,7 @@ static unsigned int total_packets, total_bytes;
 
 static int pfsocket(int ver)
 {
-        int ret, sock = socket(PF_PACKET, SOCK_RAW, htons(ETH_P_ALL));
+        int ret, sock = socket(PF_PACKET, SOCK_RAW, 0);
         if (sock == -1) {
                 perror("socket");
                 exit(1);
@@ -239,7 +239,6 @@ static void walk_v1_v2_rx(int sock, struct ring *ring)
         bug_on(ring->type != PACKET_RX_RING);
 
         pair_udp_open(udp_sock, PORT_BASE);
-        pair_udp_setfilter(sock);
 
         memset(&pfd, 0, sizeof(pfd));
         pfd.fd = sock;
@@ -311,20 +310,33 @@ static inline void __v2_tx_user_ready(struct tpacket2_hdr *hdr)
         __sync_synchronize();
 }
 
-static inline int __v1_v2_tx_kernel_ready(void *base, int version)
+static inline int __v3_tx_kernel_ready(struct tpacket3_hdr *hdr)
+{
+        return !(hdr->tp_status & (TP_STATUS_SEND_REQUEST | TP_STATUS_SENDING));
+}
+
+static inline void __v3_tx_user_ready(struct tpacket3_hdr *hdr)
+{
+        hdr->tp_status = TP_STATUS_SEND_REQUEST;
+        __sync_synchronize();
+}
+
+static inline int __tx_kernel_ready(void *base, int version)
 {
         switch (version) {
         case TPACKET_V1:
                 return __v1_tx_kernel_ready(base);
         case TPACKET_V2:
                 return __v2_tx_kernel_ready(base);
+        case TPACKET_V3:
+                return __v3_tx_kernel_ready(base);
         default:
                 bug_on(1);
                 return 0;
         }
 }
 
-static inline void __v1_v2_tx_user_ready(void *base, int version)
+static inline void __tx_user_ready(void *base, int version)
 {
         switch (version) {
         case TPACKET_V1:
@@ -333,6 +345,9 @@ static inline void __v1_v2_tx_user_ready(void *base, int version)
         case TPACKET_V2:
                 __v2_tx_user_ready(base);
                 break;
+        case TPACKET_V3:
+                __v3_tx_user_ready(base);
+                break;
         }
 }
 
@@ -348,7 +363,22 @@ static void __v1_v2_set_packet_loss_discard(int sock)
         }
 }
 
-static void walk_v1_v2_tx(int sock, struct ring *ring)
+static inline void *get_next_frame(struct ring *ring, int n)
+{
+        uint8_t *f0 = ring->rd[0].iov_base;
+
+        switch (ring->version) {
+        case TPACKET_V1:
+        case TPACKET_V2:
+                return ring->rd[n].iov_base;
+        case TPACKET_V3:
+                return f0 + (n * ring->req3.tp_frame_size);
+        default:
+                bug_on(1);
+        }
+}
+
+static void walk_tx(int sock, struct ring *ring)
 {
         struct pollfd pfd;
         int rcv_sock, ret;
@@ -360,9 +390,19 @@ static void walk_v1_v2_tx(int sock, struct ring *ring)
                 .sll_family = PF_PACKET,
                 .sll_halen = ETH_ALEN,
         };
+        int nframes;
+
+        /* TPACKET_V{1,2} sets up the ring->rd* related variables based
+         * on frames (e.g., rd_num is tp_frame_nr) whereas V3 sets these
+         * up based on blocks (e.g, rd_num is  tp_block_nr)
+         */
+        if (ring->version <= TPACKET_V2)
+                nframes = ring->rd_num;
+        else
+                nframes = ring->req3.tp_frame_nr;
 
         bug_on(ring->type != PACKET_TX_RING);
-        bug_on(ring->rd_num < NUM_PACKETS);
+        bug_on(nframes < NUM_PACKETS);
 
         rcv_sock = socket(PF_PACKET, SOCK_RAW, htons(ETH_P_ALL));
         if (rcv_sock == -1) {
@@ -388,10 +428,11 @@ static void walk_v1_v2_tx(int sock, struct ring *ring)
         create_payload(packet, &packet_len);
 
         while (total_packets > 0) {
-                while (__v1_v2_tx_kernel_ready(ring->rd[frame_num].iov_base,
-                                               ring->version) &&
+                void *next = get_next_frame(ring, frame_num);
+
+                while (__tx_kernel_ready(next, ring->version) &&
                        total_packets > 0) {
-                        ppd.raw = ring->rd[frame_num].iov_base;
+                        ppd.raw = next;
 
                         switch (ring->version) {
                         case TPACKET_V1:
@@ -413,14 +454,27 @@ static void walk_v1_v2_tx(int sock, struct ring *ring)
                                        packet_len);
                                 total_bytes += ppd.v2->tp_h.tp_snaplen;
                                 break;
+                        case TPACKET_V3: {
+                                struct tpacket3_hdr *tx = next;
+
+                                tx->tp_snaplen = packet_len;
+                                tx->tp_len = packet_len;
+                                tx->tp_next_offset = 0;
+
+                                memcpy((uint8_t *)tx + TPACKET3_HDRLEN -
+                                       sizeof(struct sockaddr_ll), packet,
+                                       packet_len);
+                                total_bytes += tx->tp_snaplen;
+                                break;
+                        }
                         }
 
                         status_bar_update();
                         total_packets--;
 
-                        __v1_v2_tx_user_ready(ppd.raw, ring->version);
+                        __tx_user_ready(next, ring->version);
 
-                        frame_num = (frame_num + 1) % ring->rd_num;
+                        frame_num = (frame_num + 1) % nframes;
                 }
 
                 poll(&pfd, 1, 1);
@@ -460,7 +514,7 @@ static void walk_v1_v2(int sock, struct ring *ring)
         if (ring->type == PACKET_RX_RING)
                 walk_v1_v2_rx(sock, ring);
         else
-                walk_v1_v2_tx(sock, ring);
+                walk_tx(sock, ring);
 }
 
 static uint64_t __v3_prev_block_seq_num = 0;
@@ -546,7 +600,6 @@ static void walk_v3_rx(int sock, struct ring *ring)
         bug_on(ring->type != PACKET_RX_RING);
 
         pair_udp_open(udp_sock, PORT_BASE);
-        pair_udp_setfilter(sock);
 
         memset(&pfd, 0, sizeof(pfd));
         pfd.fd = sock;
@@ -583,7 +636,7 @@ static void walk_v3(int sock, struct ring *ring)
         if (ring->type == PACKET_RX_RING)
                 walk_v3_rx(sock, ring);
         else
-                bug_on(1);
+                walk_tx(sock, ring);
 }
 
 static void __v1_v2_fill(struct ring *ring, unsigned int blocks)
@@ -602,12 +655,13 @@ static void __v1_v2_fill(struct ring *ring, unsigned int blocks)
         ring->flen = ring->req.tp_frame_size;
 }
 
-static void __v3_fill(struct ring *ring, unsigned int blocks)
+static void __v3_fill(struct ring *ring, unsigned int blocks, int type)
 {
-        ring->req3.tp_retire_blk_tov = 64;
-        ring->req3.tp_sizeof_priv = 0;
-        ring->req3.tp_feature_req_word = TP_FT_REQ_FILL_RXHASH;
-
+        if (type == PACKET_RX_RING) {
+                ring->req3.tp_retire_blk_tov = 64;
+                ring->req3.tp_sizeof_priv = 0;
+                ring->req3.tp_feature_req_word = TP_FT_REQ_FILL_RXHASH;
+        }
         ring->req3.tp_block_size = getpagesize() << 2;
         ring->req3.tp_frame_size = TPACKET_ALIGNMENT << 7;
         ring->req3.tp_block_nr = blocks;
@@ -641,7 +695,7 @@ static void setup_ring(int sock, struct ring *ring, int version, int type)
                 break;
 
         case TPACKET_V3:
-                __v3_fill(ring, blocks);
+                __v3_fill(ring, blocks, type);
                 ret = setsockopt(sock, SOL_PACKET, type, &ring->req3,
                                  sizeof(ring->req3));
                 break;
@@ -685,6 +739,8 @@ static void bind_ring(int sock, struct ring *ring)
 {
         int ret;
 
+        pair_udp_setfilter(sock);
+
         ring->ll.sll_family = PF_PACKET;
         ring->ll.sll_protocol = htons(ETH_P_ALL);
         ring->ll.sll_ifindex = if_nametoindex("lo");
@@ -796,6 +852,7 @@ int main(void)
         ret |= test_tpacket(TPACKET_V2, PACKET_TX_RING);
 
         ret |= test_tpacket(TPACKET_V3, PACKET_RX_RING);
+        ret |= test_tpacket(TPACKET_V3, PACKET_TX_RING);
 
         if (ret)
                 return 1;
diff --git a/tools/testing/selftests/nsfs/Makefile b/tools/testing/selftests/nsfs/Makefile
index 2306054a901a..9ff7c7f80625 100644
--- a/tools/testing/selftests/nsfs/Makefile
+++ b/tools/testing/selftests/nsfs/Makefile
@@ -1,12 +1,5 @@
-TEST_PROGS := owner pidns
+TEST_GEN_PROGS := owner pidns
 
 CFLAGS := -Wall -Werror
 
-all: owner pidns
-owner: owner.c
-pidns: pidns.c
-
-clean:
-        $(RM) owner pidns
-
 include ../lib.mk
diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile
index c2c4211ba58b..1c5d0575802e 100644
--- a/tools/testing/selftests/powerpc/Makefile
+++ b/tools/testing/selftests/powerpc/Makefile
@@ -34,31 +34,35 @@ endif
 all: $(SUB_DIRS)
 
 $(SUB_DIRS):
-        $(MAKE) -k -C $@ all
+        BUILD_TARGET=$$OUTPUT/$@; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $@ all
 
 include ../lib.mk
 
 override define RUN_TESTS
         @for TARGET in $(SUB_DIRS); do \
-                $(MAKE) -C $$TARGET run_tests; \
+                BUILD_TARGET=$$OUTPUT/$$TARGET; \
+                $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\
         done;
 endef
 
 override define INSTALL_RULE
         @for TARGET in $(SUB_DIRS); do \
-                $(MAKE) -C $$TARGET install; \
+                BUILD_TARGET=$$OUTPUT/$$TARGET; \
+                $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install;\
         done;
 endef
 
 override define EMIT_TESTS
         @for TARGET in $(SUB_DIRS); do \
-                $(MAKE) -s -C $$TARGET emit_tests; \
+                BUILD_TARGET=$$OUTPUT/$$TARGET; \
+                $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests;\
         done;
 endef
 
 clean:
         @for TARGET in $(SUB_DIRS); do \
-                $(MAKE) -C $$TARGET clean; \
+                BUILD_TARGET=$$OUTPUT/$$TARGET; \
+                $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean; \
         done;
         rm -f tags
 
diff --git a/tools/testing/selftests/powerpc/alignment/Makefile b/tools/testing/selftests/powerpc/alignment/Makefile
index ad6a4e49da91..16b22004e75f 100644
--- a/tools/testing/selftests/powerpc/alignment/Makefile
+++ b/tools/testing/selftests/powerpc/alignment/Makefile
@@ -1,10 +1,5 @@
-TEST_PROGS := copy_unaligned copy_first_unaligned paste_unaligned paste_last_unaligned
-
-all: $(TEST_PROGS)
-
-$(TEST_PROGS): ../harness.c ../utils.c copy_paste_unaligned_common.c
+TEST_GEN_PROGS := copy_unaligned copy_first_unaligned paste_unaligned paste_last_unaligned
 
 include ../../lib.mk
 
-clean:
-        rm -f $(TEST_PROGS)
+$(TEST_GEN_PROGS): ../harness.c ../utils.c copy_paste_unaligned_common.c
diff --git a/tools/testing/selftests/powerpc/benchmarks/Makefile b/tools/testing/selftests/powerpc/benchmarks/Makefile
index 545077f98f72..fb96a89bd953 100644
--- a/tools/testing/selftests/powerpc/benchmarks/Makefile
+++ b/tools/testing/selftests/powerpc/benchmarks/Makefile
@@ -1,16 +1,11 @@
-TEST_PROGS := gettimeofday context_switch mmap_bench futex_bench null_syscall
+TEST_GEN_PROGS := gettimeofday context_switch mmap_bench futex_bench null_syscall
 
 CFLAGS += -O2
 
-all: $(TEST_PROGS)
-
-$(TEST_PROGS): ../harness.c
-
-context_switch: ../utils.c
-context_switch: CFLAGS += -maltivec -mvsx -mabi=altivec
-context_switch: LDLIBS += -lpthread
-
 include ../../lib.mk
 
-clean:
-        rm -f $(TEST_PROGS) *.o
+$(TEST_GEN_PROGS): ../harness.c
+
+$(OUTPUT)/context_switch: ../utils.c
+$(OUTPUT)/context_switch: CFLAGS += -maltivec -mvsx -mabi=altivec
+$(OUTPUT)/context_switch: LDLIBS += -lpthread
diff --git a/tools/testing/selftests/powerpc/context_switch/Makefile b/tools/testing/selftests/powerpc/context_switch/Makefile
index e164d1466466..e9351bb4285d 100644
--- a/tools/testing/selftests/powerpc/context_switch/Makefile
+++ b/tools/testing/selftests/powerpc/context_switch/Makefile
@@ -1,10 +1,5 @@
-TEST_PROGS := cp_abort
-
-all: $(TEST_PROGS)
-
-$(TEST_PROGS): ../harness.c ../utils.c
+TEST_GEN_PROGS := cp_abort
 
 include ../../lib.mk
 
-clean:
-        rm -f $(TEST_PROGS)
+$(TEST_GEN_PROGS): ../harness.c ../utils.c
diff --git a/tools/testing/selftests/powerpc/copyloops/Makefile b/tools/testing/selftests/powerpc/copyloops/Makefile
index 384843ea0d40..681ab19d0a84 100644
--- a/tools/testing/selftests/powerpc/copyloops/Makefile
+++ b/tools/testing/selftests/powerpc/copyloops/Makefile
@@ -7,19 +7,14 @@ CFLAGS += -maltivec
 # Use our CFLAGS for the implicit .S rule
 ASFLAGS = $(CFLAGS)
 
-TEST_PROGS := copyuser_64 copyuser_power7 memcpy_64 memcpy_power7
+TEST_GEN_PROGS := copyuser_64 copyuser_power7 memcpy_64 memcpy_power7
 EXTRA_SOURCES := validate.c ../harness.c
 
-all: $(TEST_PROGS)
-
-copyuser_64:     CPPFLAGS += -D COPY_LOOP=test___copy_tofrom_user_base
-copyuser_power7: CPPFLAGS += -D COPY_LOOP=test___copy_tofrom_user_power7
-memcpy_64:       CPPFLAGS += -D COPY_LOOP=test_memcpy
-memcpy_power7:   CPPFLAGS += -D COPY_LOOP=test_memcpy_power7
-
-$(TEST_PROGS): $(EXTRA_SOURCES)
-
 include ../../lib.mk
 
-clean:
-        rm -f $(TEST_PROGS) *.o
+$(OUTPUT)/copyuser_64:     CPPFLAGS += -D COPY_LOOP=test___copy_tofrom_user_base
+$(OUTPUT)/copyuser_power7: CPPFLAGS += -D COPY_LOOP=test___copy_tofrom_user_power7
+$(OUTPUT)/memcpy_64:       CPPFLAGS += -D COPY_LOOP=test_memcpy
+$(OUTPUT)/memcpy_power7:   CPPFLAGS += -D COPY_LOOP=test_memcpy_power7
+
+$(TEST_GEN_PROGS): $(EXTRA_SOURCES)
diff --git a/tools/testing/selftests/powerpc/dscr/Makefile b/tools/testing/selftests/powerpc/dscr/Makefile
index 49327ee84e3a..c5639deb8887 100644
--- a/tools/testing/selftests/powerpc/dscr/Makefile
+++ b/tools/testing/selftests/powerpc/dscr/Makefile
@@ -1,14 +1,9 @@
-TEST_PROGS := dscr_default_test dscr_explicit_test dscr_user_test       \
+TEST_GEN_PROGS := dscr_default_test dscr_explicit_test dscr_user_test   \
               dscr_inherit_test dscr_inherit_exec_test dscr_sysfs_test  \
               dscr_sysfs_thread_test
 
-dscr_default_test: LDLIBS += -lpthread
-
-all: $(TEST_PROGS)
-
-$(TEST_PROGS): ../harness.c
-
 include ../../lib.mk
 
-clean:
-        rm -f $(TEST_PROGS) *.o
+$(OUTPUT)/dscr_default_test: LDLIBS += -lpthread
+
+$(TEST_GEN_PROGS): ../harness.c
diff --git a/tools/testing/selftests/powerpc/harness.c b/tools/testing/selftests/powerpc/harness.c
index 248a820048df..66d31de60b9a 100644
--- a/tools/testing/selftests/powerpc/harness.c
+++ b/tools/testing/selftests/powerpc/harness.c
@@ -114,9 +114,11 @@ int test_harness(int (test_function)(void), char *name)
 
         rc = run_test(test_function, name);
 
-        if (rc == MAGIC_SKIP_RETURN_VALUE)
+        if (rc == MAGIC_SKIP_RETURN_VALUE) {
                 test_skip(name);
-        else
+                /* so that skipped test is not marked as failed */
+                rc = 0;
+        } else
                 test_finish(name, rc);
 
         return rc;
diff --git a/tools/testing/selftests/powerpc/include/vsx_asm.h b/tools/testing/selftests/powerpc/include/vsx_asm.h
index d828bfb6ef2d..54064ced9e95 100644
--- a/tools/testing/selftests/powerpc/include/vsx_asm.h
+++ b/tools/testing/selftests/powerpc/include/vsx_asm.h
@@ -16,56 +16,56 @@
  */
 FUNC_START(load_vsx)
         li      r5,0
-        lxvx    vs20,r5,r3
+        lxvd2x  vs20,r5,r3
         addi    r5,r5,16
-        lxvx    vs21,r5,r3
+        lxvd2x  vs21,r5,r3
         addi    r5,r5,16
-        lxvx    vs22,r5,r3
+        lxvd2x  vs22,r5,r3
         addi    r5,r5,16
-        lxvx    vs23,r5,r3
+        lxvd2x  vs23,r5,r3
         addi    r5,r5,16
-        lxvx    vs24,r5,r3
+        lxvd2x  vs24,r5,r3
         addi    r5,r5,16
-        lxvx    vs25,r5,r3
+        lxvd2x  vs25,r5,r3
         addi    r5,r5,16
-        lxvx    vs26,r5,r3
+        lxvd2x  vs26,r5,r3
         addi    r5,r5,16
-        lxvx    vs27,r5,r3
+        lxvd2x  vs27,r5,r3
         addi    r5,r5,16
-        lxvx    vs28,r5,r3
+        lxvd2x  vs28,r5,r3
         addi    r5,r5,16
-        lxvx    vs29,r5,r3
+        lxvd2x  vs29,r5,r3
         addi    r5,r5,16
-        lxvx    vs30,r5,r3
+        lxvd2x  vs30,r5,r3
         addi    r5,r5,16
-        lxvx    vs31,r5,r3
+        lxvd2x  vs31,r5,r3
         blr
 FUNC_END(load_vsx)
 
 FUNC_START(store_vsx)
         li      r5,0
-        stxvx   vs20,r5,r3
+        stxvd2x vs20,r5,r3
         addi    r5,r5,16
-        stxvx   vs21,r5,r3
+        stxvd2x vs21,r5,r3
         addi    r5,r5,16
-        stxvx   vs22,r5,r3
+        stxvd2x vs22,r5,r3
         addi    r5,r5,16
-        stxvx   vs23,r5,r3
+        stxvd2x vs23,r5,r3
         addi    r5,r5,16
-        stxvx   vs24,r5,r3
+        stxvd2x vs24,r5,r3
         addi    r5,r5,16
-        stxvx   vs25,r5,r3
+        stxvd2x vs25,r5,r3
         addi    r5,r5,16
-        stxvx   vs26,r5,r3
+        stxvd2x vs26,r5,r3
         addi    r5,r5,16
-        stxvx   vs27,r5,r3
+        stxvd2x vs27,r5,r3
         addi    r5,r5,16
-        stxvx   vs28,r5,r3
+        stxvd2x vs28,r5,r3
         addi    r5,r5,16
-        stxvx   vs29,r5,r3
+        stxvd2x vs29,r5,r3
         addi    r5,r5,16
-        stxvx   vs30,r5,r3
+        stxvd2x vs30,r5,r3
         addi    r5,r5,16
-        stxvx   vs31,r5,r3
+        stxvd2x vs31,r5,r3
         blr
 FUNC_END(store_vsx)
diff --git a/tools/testing/selftests/powerpc/math/Makefile b/tools/testing/selftests/powerpc/math/Makefile
index a505b66d408a..fa8bae920c91 100644
--- a/tools/testing/selftests/powerpc/math/Makefile
+++ b/tools/testing/selftests/powerpc/math/Makefile
@@ -1,22 +1,17 @@
-TEST_PROGS := fpu_syscall fpu_preempt fpu_signal vmx_syscall vmx_preempt vmx_signal vsx_preempt
+TEST_GEN_PROGS := fpu_syscall fpu_preempt fpu_signal vmx_syscall vmx_preempt vmx_signal vsx_preempt
 
-all: $(TEST_PROGS)
-
-$(TEST_PROGS): ../harness.c
-$(TEST_PROGS): CFLAGS += -O2 -g -pthread -m64 -maltivec
-
-fpu_syscall: fpu_asm.S
-fpu_preempt: fpu_asm.S
-fpu_signal:  fpu_asm.S
+include ../../lib.mk
 
-vmx_syscall: vmx_asm.S
-vmx_preempt: vmx_asm.S
-vmx_signal: vmx_asm.S
+$(TEST_GEN_PROGS): ../harness.c
+$(TEST_GEN_PROGS): CFLAGS += -O2 -g -pthread -m64 -maltivec
 
-vsx_preempt: CFLAGS += -mvsx
-vsx_preempt: vsx_asm.S
+$(OUTPUT)/fpu_syscall: fpu_asm.S
+$(OUTPUT)/fpu_preempt: fpu_asm.S
+$(OUTPUT)/fpu_signal:  fpu_asm.S
 
-include ../../lib.mk
+$(OUTPUT)/vmx_syscall: vmx_asm.S
+$(OUTPUT)/vmx_preempt: vmx_asm.S
+$(OUTPUT)/vmx_signal: vmx_asm.S
 
-clean:
-        rm -f $(TEST_PROGS) *.o
+$(OUTPUT)/vsx_preempt: CFLAGS += -mvsx
+$(OUTPUT)/vsx_preempt: vsx_asm.S
diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile
index 3bdb96eae558..1cffe54dccfb 100644
--- a/tools/testing/selftests/powerpc/mm/Makefile
+++ b/tools/testing/selftests/powerpc/mm/Makefile
@@ -1,19 +1,15 @@
 noarg:
         $(MAKE) -C ../
 
-TEST_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao
-TEST_FILES := tempfile
+TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao
+TEST_GEN_FILES := tempfile
 
-all: $(TEST_PROGS) $(TEST_FILES)
-
-$(TEST_PROGS): ../harness.c
+include ../../lib.mk
 
-prot_sao: ../utils.c
+$(TEST_GEN_PROGS): ../harness.c
 
-include ../../lib.mk
+$(OUTPUT)/prot_sao: ../utils.c
 
-tempfile:
-        dd if=/dev/zero of=tempfile bs=64k count=1
+$(OUTPUT)/tempfile:
+        dd if=/dev/zero of=$@ bs=64k count=1
 
-clean:
-        rm -f $(TEST_PROGS) tempfile
diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile
index ac41a7177f2e..e4e55d1d3e0f 100644
--- a/tools/testing/selftests/powerpc/pmu/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/Makefile
@@ -1,44 +1,44 @@
 noarg:
         $(MAKE) -C ../
 
-TEST_PROGS := count_instructions l3_bank_test per_event_excludes
+TEST_GEN_PROGS := count_instructions l3_bank_test per_event_excludes
 EXTRA_SOURCES := ../harness.c event.c lib.c ../utils.c
 
-all: $(TEST_PROGS) ebb
+include ../../lib.mk
+
+all: $(TEST_GEN_PROGS) ebb
 
-$(TEST_PROGS): $(EXTRA_SOURCES)
+$(TEST_GEN_PROGS): $(EXTRA_SOURCES)
 
 # loop.S can only be built 64-bit
-count_instructions: loop.S count_instructions.c $(EXTRA_SOURCES)
+$(OUTPUT)/count_instructions: loop.S count_instructions.c $(EXTRA_SOURCES)
         $(CC) $(CFLAGS) -m64 -o $@ $^
 
-per_event_excludes: ../utils.c
-
-include ../../lib.mk
+$(OUTPUT)/per_event_excludes: ../utils.c
 
 DEFAULT_RUN_TESTS := $(RUN_TESTS)
 override define RUN_TESTS
         $(DEFAULT_RUN_TESTS)
-        $(MAKE) -C ebb run_tests
+        TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests
 endef
 
 DEFAULT_EMIT_TESTS := $(EMIT_TESTS)
 override define EMIT_TESTS
         $(DEFAULT_EMIT_TESTS)
-        $(MAKE) -s -C ebb emit_tests
+        TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests
 endef
 
 DEFAULT_INSTALL_RULE := $(INSTALL_RULE)
 override define INSTALL_RULE
         $(DEFAULT_INSTALL_RULE)
-        $(MAKE) -C ebb install
+        TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install
 endef
 
 clean:
-        rm -f $(TEST_PROGS) loop.o
-        $(MAKE) -C ebb clean
+        $(RM) $(TEST_GEN_PROGS) $(OUTPUT)/loop.o
+        TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean
 
 ebb:
-        $(MAKE) -k -C $@ all
+        TARGET=$@; BUILD_TARGET=$$OUTPUT/$$TARGET; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $$TARGET all
 
 .PHONY: all run_tests clean ebb
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
index 8d2279c4bb4b..6001fb0a377a 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
@@ -4,7 +4,7 @@ noarg:
 # The EBB handler is 64-bit code and everything links against it
 CFLAGS += -m64
 
-TEST_PROGS := reg_access_test event_attributes_test cycles_test \
+TEST_GEN_PROGS := reg_access_test event_attributes_test cycles_test     \
          cycles_with_freeze_test pmc56_overflow_test            \
          ebb_vs_cpu_event_test cpu_event_vs_ebb_test            \
          cpu_event_pinned_vs_ebb_test task_event_vs_ebb_test    \
@@ -16,16 +16,11 @@ TEST_PROGS := reg_access_test event_attributes_test cycles_test	\
          lost_exception_test no_handler_test                    \
          cycles_with_mmcr2_test
 
-all: $(TEST_PROGS)
+include ../../../lib.mk
 
-$(TEST_PROGS): ../../harness.c ../../utils.c ../event.c ../lib.c \
+$(TEST_GEN_PROGS): ../../harness.c ../../utils.c ../event.c ../lib.c \
                ebb.c ebb_handler.S trace.c busy_loop.S
 
-instruction_count_test: ../loop.S
-
-lost_exception_test: ../lib.c
-
-include ../../../lib.mk
+$(OUTPUT)/instruction_count_test: ../loop.S
 
-clean:
-        rm -f $(TEST_PROGS)
+$(OUTPUT)/lost_exception_test: ../lib.c
diff --git a/tools/testing/selftests/powerpc/primitives/Makefile b/tools/testing/selftests/powerpc/primitives/Makefile
index b68c6221d3d1..175366db7be8 100644
--- a/tools/testing/selftests/powerpc/primitives/Makefile
+++ b/tools/testing/selftests/powerpc/primitives/Makefile
@@ -1,12 +1,7 @@
 CFLAGS += -I$(CURDIR)
 
-TEST_PROGS := load_unaligned_zeropad
-
-all: $(TEST_PROGS)
-
-$(TEST_PROGS): ../harness.c
+TEST_GEN_PROGS := load_unaligned_zeropad
 
 include ../../lib.mk
 
-clean:
-        rm -f $(TEST_PROGS) *.o
+$(TEST_GEN_PROGS): ../harness.c
diff --git a/tools/testing/selftests/powerpc/stringloops/Makefile b/tools/testing/selftests/powerpc/stringloops/Makefile
index 2a728f4d2873..557b9379f3bb 100644
--- a/tools/testing/selftests/powerpc/stringloops/Makefile
+++ b/tools/testing/selftests/powerpc/stringloops/Makefile
@@ -2,14 +2,9 @@
 CFLAGS += -m64
 CFLAGS += -I$(CURDIR)
 
-TEST_PROGS := memcmp
+TEST_GEN_PROGS := memcmp
 EXTRA_SOURCES := memcmp_64.S ../harness.c
 
-all: $(TEST_PROGS)
-
-$(TEST_PROGS): $(EXTRA_SOURCES)
-
 include ../../lib.mk
 
-clean:
-        rm -f $(TEST_PROGS) *.o
+$(TEST_GEN_PROGS): $(EXTRA_SOURCES)
diff --git a/tools/testing/selftests/powerpc/switch_endian/Makefile b/tools/testing/selftests/powerpc/switch_endian/Makefile
index e21d10674e54..b92c2a132c4f 100644
--- a/tools/testing/selftests/powerpc/switch_endian/Makefile
+++ b/tools/testing/selftests/powerpc/switch_endian/Makefile
@@ -1,18 +1,15 @@
-TEST_PROGS := switch_endian_test
+TEST_GEN_PROGS := switch_endian_test
 
 ASFLAGS += -O2 -Wall -g -nostdlib -m64
 
-all: $(TEST_PROGS)
+EXTRA_CLEAN = $(OUTPUT)/*.o $(OUTPUT)/check-reversed.S
 
-switch_endian_test: check-reversed.S
+include ../../lib.mk
+
+$(OUTPUT)/switch_endian_test: $(OUTPUT)/check-reversed.S
 
-check-reversed.o: check.o
+$(OUTPUT)/check-reversed.o: $(OUTPUT)/check.o
         $(CROSS_COMPILE)objcopy -j .text --reverse-bytes=4 -O binary $< $@
 
-check-reversed.S: check-reversed.o
+$(OUTPUT)/check-reversed.S: $(OUTPUT)/check-reversed.o
         hexdump -v -e '/1 ".byte 0x%02X\n"' $< > $@
-
-include ../../lib.mk
-
-clean:
-        rm -f $(TEST_PROGS) *.o check-reversed.S
diff --git a/tools/testing/selftests/powerpc/syscalls/Makefile b/tools/testing/selftests/powerpc/syscalls/Makefile
index b35c7945bec5..da22ca7c38c1 100644
--- a/tools/testing/selftests/powerpc/syscalls/Makefile
+++ b/tools/testing/selftests/powerpc/syscalls/Makefile
@@ -1,12 +1,7 @@
-TEST_PROGS := ipc_unmuxed
+TEST_GEN_PROGS := ipc_unmuxed
 
 CFLAGS += -I../../../../../usr/include
 
-all: $(TEST_PROGS)
-
-$(TEST_PROGS): ../harness.c
-
 include ../../lib.mk
 
-clean:
-        rm -f $(TEST_PROGS) *.o
+$(TEST_GEN_PROGS): ../harness.c
diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile
index c6c53c82fdd6..5576ee6a51f2 100644
--- a/tools/testing/selftests/powerpc/tm/Makefile
+++ b/tools/testing/selftests/powerpc/tm/Makefile
@@ -1,23 +1,19 @@
 SIGNAL_CONTEXT_CHK_TESTS := tm-signal-context-chk-gpr tm-signal-context-chk-fpu \
         tm-signal-context-chk-vmx tm-signal-context-chk-vsx
 
-TEST_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack \
+TEST_GEN_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack \
         tm-vmxcopy tm-fork tm-tar tm-tmspr $(SIGNAL_CONTEXT_CHK_TESTS)
 
-all: $(TEST_PROGS)
+include ../../lib.mk
 
-$(TEST_PROGS): ../harness.c ../utils.c
+$(TEST_GEN_PROGS): ../harness.c ../utils.c
 
 CFLAGS += -mhtm
 
-tm-syscall: tm-syscall-asm.S
-tm-syscall: CFLAGS += -I../../../../../usr/include
-tm-tmspr: CFLAGS += -pthread
+$(OUTPUT)/tm-syscall: tm-syscall-asm.S
+$(OUTPUT)/tm-syscall: CFLAGS += -I../../../../../usr/include
+$(OUTPUT)/tm-tmspr: CFLAGS += -pthread
 
+SIGNAL_CONTEXT_CHK_TESTS := $(patsubst %,$(OUTPUT)/%,$(SIGNAL_CONTEXT_CHK_TESTS))
 $(SIGNAL_CONTEXT_CHK_TESTS): tm-signal.S
 $(SIGNAL_CONTEXT_CHK_TESTS): CFLAGS += -mhtm -m64 -mvsx
-
-include ../../lib.mk
-
-clean:
-        rm -f $(TEST_PROGS) *.o
diff --git a/tools/testing/selftests/powerpc/vphn/Makefile b/tools/testing/selftests/powerpc/vphn/Makefile
index a485f2e286ae..f8ced26748f8 100644
--- a/tools/testing/selftests/powerpc/vphn/Makefile
+++ b/tools/testing/selftests/powerpc/vphn/Makefile
@@ -1,12 +1,8 @@
-TEST_PROGS := test-vphn
+TEST_GEN_PROGS := test-vphn
 
 CFLAGS += -m64
 
-all: $(TEST_PROGS)
-
-$(TEST_PROGS): ../harness.c
-
 include ../../lib.mk
 
-clean:
-        rm -f $(TEST_PROGS)
+$(TEST_GEN_PROGS): ../harness.c
+
diff --git a/tools/testing/selftests/pstore/Makefile b/tools/testing/selftests/pstore/Makefile
index bd7abe24ea08..c5f2440ba1f7 100644
--- a/tools/testing/selftests/pstore/Makefile
+++ b/tools/testing/selftests/pstore/Makefile
@@ -5,11 +5,9 @@ all:
 
 TEST_PROGS := pstore_tests pstore_post_reboot_tests
 TEST_FILES := common_tests pstore_crash_test
+EXTRA_CLEAN := logs/* *uuid
 
 include ../lib.mk
 
 run_crash:
         @sh pstore_crash_test || { echo "pstore_crash_test: [FAIL]"; exit 1; }
-
-clean:
-        rm -rf logs/* *uuid
diff --git a/tools/testing/selftests/ptrace/Makefile b/tools/testing/selftests/ptrace/Makefile
index 453927fea90c..8a2bc5562179 100644
--- a/tools/testing/selftests/ptrace/Makefile
+++ b/tools/testing/selftests/ptrace/Makefile
@@ -1,11 +1,5 @@
 CFLAGS += -iquote../../../../include/uapi -Wall
-peeksiginfo: peeksiginfo.c
 
-all: peeksiginfo
-
-clean:
-        rm -f peeksiginfo
-
-TEST_PROGS := peeksiginfo
+TEST_GEN_PROGS := peeksiginfo
 
 include ../lib.mk
diff --git a/tools/testing/selftests/seccomp/Makefile b/tools/testing/selftests/seccomp/Makefile
index 8401e87e34e1..5fa6fd2246b1 100644
--- a/tools/testing/selftests/seccomp/Makefile
+++ b/tools/testing/selftests/seccomp/Makefile
@@ -1,10 +1,6 @@
-TEST_PROGS := seccomp_bpf
+TEST_GEN_PROGS := seccomp_bpf
 CFLAGS += -Wl,-no-as-needed -Wall
 LDFLAGS += -lpthread
 
-all: $(TEST_PROGS)
-
 include ../lib.mk
 
-clean:
-        $(RM) $(TEST_PROGS)
diff --git a/tools/testing/selftests/sigaltstack/Makefile b/tools/testing/selftests/sigaltstack/Makefile
index 56af56eda6fa..f68fbf80d8be 100644
--- a/tools/testing/selftests/sigaltstack/Makefile
+++ b/tools/testing/selftests/sigaltstack/Makefile
@@ -1,8 +1,5 @@
 CFLAGS = -Wall
-BINARIES = sas
-all: $(BINARIES)
+TEST_GEN_PROGS = sas
 
 include ../lib.mk
 
-clean:
-        rm -rf $(BINARIES)
diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c
index 1bb01258e559..ccd07343d418 100644
--- a/tools/testing/selftests/sigaltstack/sas.c
+++ b/tools/testing/selftests/sigaltstack/sas.c
@@ -57,7 +57,7 @@ void my_usr1(int sig, siginfo_t *si, void *u)
                 exit(EXIT_FAILURE);
         }
         if (stk.ss_flags != SS_DISABLE)
-                printf("[FAIL]\tss_flags=%i, should be SS_DISABLE\n",
+                printf("[FAIL]\tss_flags=%x, should be SS_DISABLE\n",
                                 stk.ss_flags);
         else
                 printf("[OK]\tsigaltstack is disabled in sighandler\n");
@@ -122,7 +122,8 @@ int main(void)
         if (stk.ss_flags == SS_DISABLE) {
                 printf("[OK]\tInitial sigaltstack state was SS_DISABLE\n");
         } else {
-                printf("[FAIL]\tInitial sigaltstack state was %i; should have been SS_DISABLE\n", stk.ss_flags);
+                printf("[FAIL]\tInitial sigaltstack state was %x; "
+                       "should have been SS_DISABLE\n", stk.ss_flags);
                 return EXIT_FAILURE;
         }
 
@@ -165,7 +166,7 @@ int main(void)
                 exit(EXIT_FAILURE);
         }
         if (stk.ss_flags != SS_AUTODISARM) {
-                printf("[FAIL]\tss_flags=%i, should be SS_AUTODISARM\n",
+                printf("[FAIL]\tss_flags=%x, should be SS_AUTODISARM\n",
                                 stk.ss_flags);
                 exit(EXIT_FAILURE);
         }
diff --git a/tools/testing/selftests/size/Makefile b/tools/testing/selftests/size/Makefile
index bbd0b5398b61..4685b3e421fc 100644
--- a/tools/testing/selftests/size/Makefile
+++ b/tools/testing/selftests/size/Makefile
@@ -1,11 +1,5 @@
-all: get_size
+CFLAGS := -static -ffreestanding -nostartfiles -s
 
-get_size: get_size.c
-        $(CC) -static -ffreestanding -nostartfiles -s $< -o $@
-
-TEST_PROGS := get_size
+TEST_GEN_PROGS := get_size
 
 include ../lib.mk
-
-clean:
-        $(RM) get_size
diff --git a/tools/testing/selftests/splice/Makefile b/tools/testing/selftests/splice/Makefile
new file mode 100644
index 000000000000..de51f439d4a6
--- /dev/null
+++ b/tools/testing/selftests/splice/Makefile
@@ -0,0 +1,8 @@
+TEST_PROGS := default_file_splice_read.sh
+EXTRA := default_file_splice_read
+all: $(TEST_PROGS) $(EXTRA)
+
+include ../lib.mk
+
+clean:
+        rm -fr $(TEST_PROGS) $(EXTRA)
diff --git a/tools/testing/selftests/splice/default_file_splice_read.c b/tools/testing/selftests/splice/default_file_splice_read.c
new file mode 100644
index 000000000000..01dd6091554c
--- /dev/null
+++ b/tools/testing/selftests/splice/default_file_splice_read.c
@@ -0,0 +1,8 @@
+#define _GNU_SOURCE
+#include <fcntl.h>
+
+int main(int argc, char **argv)
+{
+        splice(0, 0, 1, 0, 1<<30, 0);
+        return 0;
+}
diff --git a/tools/testing/selftests/splice/default_file_splice_read.sh b/tools/testing/selftests/splice/default_file_splice_read.sh
new file mode 100755
index 000000000000..1ea2adeabc94
--- /dev/null
+++ b/tools/testing/selftests/splice/default_file_splice_read.sh
@@ -0,0 +1,7 @@
+#!/bin/sh
+n=`./default_file_splice_read </dev/null | wc -c`
+
+test "$n" = 0 && exit 0
+
+echo "default_file_splice_read broken: leaked $n"
+exit 1
diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile
index 1d5556869137..b90e50c36f9f 100644
--- a/tools/testing/selftests/timers/Makefile
+++ b/tools/testing/selftests/timers/Makefile
@@ -1,20 +1,16 @@
-CC = $(CROSS_COMPILE)gcc
 BUILD_FLAGS = -DKTEST
 CFLAGS += -O3 -Wl,-no-as-needed -Wall $(BUILD_FLAGS)
 LDFLAGS += -lrt -lpthread
 
 # these are all "safe" tests that don't modify
 # system time or require escalated privledges
-TEST_PROGS = posix_timers nanosleep nsleep-lat set-timer-lat mqueue-lat \
+TEST_GEN_PROGS = posix_timers nanosleep nsleep-lat set-timer-lat mqueue-lat \
              inconsistency-check raw_skew threadtest rtctest
 
-TEST_PROGS_EXTENDED = alarmtimer-suspend valid-adjtimex adjtick change_skew \
+TEST_GEN_PROGS_EXTENDED = alarmtimer-suspend valid-adjtimex adjtick change_skew \
                       skew_consistency clocksource-switch leap-a-day \
                       leapcrash set-tai set-2038 set-tz
 
-bins = $(TEST_PROGS) $(TEST_PROGS_EXTENDED)
-
-all: ${bins}
 
 include ../lib.mk
 
@@ -34,5 +30,3 @@ run_destructive_tests: run_tests
         ./set-tai
         ./set-2038
 
-clean:
-        rm -f ${bins}
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index bbab7f4664ac..41642ba5e318 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -1,33 +1,37 @@
 # Makefile for vm selftests
 
-CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS)
-BINARIES = compaction_test
-BINARIES += hugepage-mmap
-BINARIES += hugepage-shm
-BINARIES += map_hugetlb
-BINARIES += mlock2-tests
-BINARIES += on-fault-limit
-BINARIES += thuge-gen
-BINARIES += transhuge-stress
-BINARIES += userfaultfd
-BINARIES += mlock-random-test
-
-all: $(BINARIES)
-%: %.c
-        $(CC) $(CFLAGS) -o $@ $^ -lrt
-userfaultfd: userfaultfd.c ../../../../usr/include/linux/kernel.h
-        $(CC) $(CFLAGS) -O2 -o $@ $< -lpthread
-
-mlock-random-test: mlock-random-test.c
-        $(CC) $(CFLAGS) -o $@ $< -lcap
+ifndef OUTPUT
+  OUTPUT := $(shell pwd)
+endif
 
-../../../../usr/include/linux/kernel.h:
-        make -C ../../../.. headers_install
+CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS)
+LDLIBS = -lrt
+TEST_GEN_FILES = compaction_test
+TEST_GEN_FILES += hugepage-mmap
+TEST_GEN_FILES += hugepage-shm
+TEST_GEN_FILES += map_hugetlb
+TEST_GEN_FILES += mlock2-tests
+TEST_GEN_FILES += on-fault-limit
+TEST_GEN_FILES += thuge-gen
+TEST_GEN_FILES += transhuge-stress
+TEST_GEN_FILES += userfaultfd
+TEST_GEN_FILES += userfaultfd_hugetlb
+TEST_GEN_FILES += userfaultfd_shmem
+TEST_GEN_FILES += mlock-random-test
 
 TEST_PROGS := run_vmtests
-TEST_FILES := $(BINARIES)
 
 include ../lib.mk
 
-clean:
-        $(RM) $(BINARIES)
+$(OUTPUT)/userfaultfd: LDLIBS += -lpthread ../../../../usr/include/linux/kernel.h
+
+$(OUTPUT)/userfaultfd_hugetlb: userfaultfd.c ../../../../usr/include/linux/kernel.h
+        $(CC) $(CFLAGS) -DHUGETLB_TEST -O2 -o $@ $< -lpthread
+
+$(OUTPUT)/userfaultfd_shmem: userfaultfd.c  ../../../../usr/include/linux/kernel.h
+        $(CC) $(CFLAGS) -DSHMEM_TEST -O2 -o $@ $< -lpthread
+
+$(OUTPUT)/mlock-random-test: LDLIBS += -lcap
+
+../../../../usr/include/linux/kernel.h:
+        make -C ../../../.. headers_install
diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests
index e11968b3677e..c92f6cf31d0a 100755
--- a/tools/testing/selftests/vm/run_vmtests
+++ b/tools/testing/selftests/vm/run_vmtests
@@ -103,6 +103,30 @@ else
         echo "[PASS]"
 fi
 
+echo "----------------------------"
+echo "running userfaultfd_hugetlb"
+echo "----------------------------"
+# 258MB total huge pages == 128MB src and 128MB dst
+./userfaultfd_hugetlb 128 32 $mnt/ufd_test_file
+if [ $? -ne 0 ]; then
+        echo "[FAIL]"
+        exitcode=1
+else
+        echo "[PASS]"
+fi
+rm -f $mnt/ufd_test_file
+
+echo "----------------------------"
+echo "running userfaultfd_shmem"
+echo "----------------------------"
+./userfaultfd_shmem 128 32
+if [ $? -ne 0 ]; then
+        echo "[FAIL]"
+        exitcode=1
+else
+        echo "[PASS]"
+fi
+
 #cleanup
 umount $mnt
 rm -rf $mnt
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index d77ed41b2094..e9449c801888 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -63,6 +63,7 @@
 #include <sys/mman.h>
 #include <sys/syscall.h>
 #include <sys/ioctl.h>
+#include <sys/wait.h>
 #include <pthread.h>
 #include <linux/userfaultfd.h>
 
@@ -76,8 +77,12 @@ static unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size;
 #define BOUNCE_POLL             (1<<3)
 static int bounces;
 
+#ifdef HUGETLB_TEST
+static int huge_fd;
+static char *huge_fd_off0;
+#endif
 static unsigned long long *count_verify;
-static int uffd, finished, *pipefd;
+static int uffd, uffd_flags, finished, *pipefd;
 static char *area_src, *area_dst;
 static char *zeropage;
 pthread_attr_t attr;
@@ -97,6 +102,102 @@ pthread_attr_t attr;
                                  ~(unsigned long)(sizeof(unsigned long long) \
                                                   -  1)))
 
+#if !defined(HUGETLB_TEST) && !defined(SHMEM_TEST)
+
+/* Anonymous memory */
+#define EXPECTED_IOCTLS         ((1 << _UFFDIO_WAKE) | \
+                                 (1 << _UFFDIO_COPY) | \
+                                 (1 << _UFFDIO_ZEROPAGE))
+
+static int release_pages(char *rel_area)
+{
+        int ret = 0;
+
+        if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) {
+                perror("madvise");
+                ret = 1;
+        }
+
+        return ret;
+}
+
+static void allocate_area(void **alloc_area)
+{
+        if (posix_memalign(alloc_area, page_size, nr_pages * page_size)) {
+                fprintf(stderr, "out of memory\n");
+                *alloc_area = NULL;
+        }
+}
+
+#else /* HUGETLB_TEST or SHMEM_TEST */
+
+#define EXPECTED_IOCTLS         UFFD_API_RANGE_IOCTLS_BASIC
+
+#ifdef HUGETLB_TEST
+
+/* HugeTLB memory */
+static int release_pages(char *rel_area)
+{
+        int ret = 0;
+
+        if (fallocate(huge_fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+                                rel_area == huge_fd_off0 ? 0 :
+                                nr_pages * page_size,
+                                nr_pages * page_size)) {
+                perror("fallocate");
+                ret = 1;
+        }
+
+        return ret;
+}
+
+
+static void allocate_area(void **alloc_area)
+{
+        *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
+                                MAP_PRIVATE | MAP_HUGETLB, huge_fd,
+                                *alloc_area == area_src ? 0 :
+                                nr_pages * page_size);
+        if (*alloc_area == MAP_FAILED) {
+                fprintf(stderr, "mmap of hugetlbfs file failed\n");
+                *alloc_area = NULL;
+        }
+
+        if (*alloc_area == area_src)
+                huge_fd_off0 = *alloc_area;
+}
+
+#elif defined(SHMEM_TEST)
+
+/* Shared memory */
+static int release_pages(char *rel_area)
+{
+        int ret = 0;
+
+        if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) {
+                perror("madvise");
+                ret = 1;
+        }
+
+        return ret;
+}
+
+static void allocate_area(void **alloc_area)
+{
+        *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
+                           MAP_ANONYMOUS | MAP_SHARED, -1, 0);
+        if (*alloc_area == MAP_FAILED) {
+                fprintf(stderr, "shared memory mmap failed\n");
+                *alloc_area = NULL;
+        }
+}
+
+#else /* SHMEM_TEST */
+#error "Undefined test type"
+#endif /* HUGETLB_TEST */
+
+#endif /* !defined(HUGETLB_TEST) && !defined(SHMEM_TEST) */
+
 static int my_bcmp(char *str1, char *str2, size_t n)
 {
         unsigned long i;
@@ -217,7 +318,7 @@ static void *locking_thread(void *arg)
         return NULL;
 }
 
-static int copy_page(unsigned long offset)
+static int copy_page(int ufd, unsigned long offset)
 {
         struct uffdio_copy uffdio_copy;
 
@@ -229,7 +330,7 @@ static int copy_page(unsigned long offset)
         uffdio_copy.len = page_size;
         uffdio_copy.mode = 0;
         uffdio_copy.copy = 0;
-        if (ioctl(uffd, UFFDIO_COPY, &uffdio_copy)) {
+        if (ioctl(ufd, UFFDIO_COPY, &uffdio_copy)) {
                 /* real retval in ufdio_copy.copy */
                 if (uffdio_copy.copy != -EEXIST)
                         fprintf(stderr, "UFFDIO_COPY error %Ld\n",
@@ -247,6 +348,7 @@ static void *uffd_poll_thread(void *arg)
         unsigned long cpu = (unsigned long) arg;
         struct pollfd pollfd[2];
         struct uffd_msg msg;
+        struct uffdio_register uffd_reg;
         int ret;
         unsigned long offset;
         char tmp_chr;
@@ -278,16 +380,35 @@ static void *uffd_poll_thread(void *arg)
                                 continue;
                         perror("nonblocking read error"), exit(1);
                 }
-                if (msg.event != UFFD_EVENT_PAGEFAULT)
+                switch (msg.event) {
+                default:
                         fprintf(stderr, "unexpected msg event %u\n",
                                 msg.event), exit(1);
-                if (msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
-                        fprintf(stderr, "unexpected write fault\n"), exit(1);
-                offset = (char *)(unsigned long)msg.arg.pagefault.address -
-                         area_dst;
-                offset &= ~(page_size-1);
-                if (copy_page(offset))
-                        userfaults++;
+                        break;
+                case UFFD_EVENT_PAGEFAULT:
+                        if (msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
+                                fprintf(stderr, "unexpected write fault\n"), exit(1);
+                        offset = (char *)(unsigned long)msg.arg.pagefault.address -
+                                area_dst;
+                        offset &= ~(page_size-1);
+                        if (copy_page(uffd, offset))
+                                userfaults++;
+                        break;
+                case UFFD_EVENT_FORK:
+                        uffd = msg.arg.fork.ufd;
+                        pollfd[0].fd = uffd;
+                        break;
+                case UFFD_EVENT_REMOVE:
+                        uffd_reg.range.start = msg.arg.remove.start;
+                        uffd_reg.range.len = msg.arg.remove.end -
+                                msg.arg.remove.start;
+                        if (ioctl(uffd, UFFDIO_UNREGISTER, &uffd_reg.range))
+                                fprintf(stderr, "remove failure\n"), exit(1);
+                        break;
+                case UFFD_EVENT_REMAP:
+                        area_dst = (char *)(unsigned long)msg.arg.remap.to;
+                        break;
+                }
         }
         return (void *)userfaults;
 }
@@ -324,7 +445,7 @@ static void *uffd_read_thread(void *arg)
                 offset = (char *)(unsigned long)msg.arg.pagefault.address -
                          area_dst;
                 offset &= ~(page_size-1);
-                if (copy_page(offset))
+                if (copy_page(uffd, offset))
                         (*this_cpu_userfaults)++;
         }
         return (void *)NULL;
@@ -338,7 +459,7 @@ static void *background_thread(void *arg)
         for (page_nr = cpu * nr_pages_per_cpu;
              page_nr < (cpu+1) * nr_pages_per_cpu;
              page_nr++)
-                copy_page(page_nr * page_size);
+                copy_page(uffd, page_nr * page_size);
 
         return NULL;
 }
@@ -384,10 +505,8 @@ static int stress(unsigned long *userfaults)
          * UFFDIO_COPY without writing zero pages into area_dst
          * because the background threads already completed).
          */
-        if (madvise(area_src, nr_pages * page_size, MADV_DONTNEED)) {
-                perror("madvise");
+        if (release_pages(area_src))
                 return 1;
-        }
 
         for (cpu = 0; cpu < nr_cpus; cpu++) {
                 char c;
@@ -414,27 +533,9 @@ static int stress(unsigned long *userfaults)
         return 0;
 }
 
-static int userfaultfd_stress(void)
+static int userfaultfd_open(int features)
 {
-        void *area;
-        char *tmp_area;
-        unsigned long nr;
-        struct uffdio_register uffdio_register;
         struct uffdio_api uffdio_api;
-        unsigned long cpu;
-        int uffd_flags, err;
-        unsigned long userfaults[nr_cpus];
-
-        if (posix_memalign(&area, page_size, nr_pages * page_size)) {
-                fprintf(stderr, "out of memory\n");
-                return 1;
-        }
-        area_src = area;
-        if (posix_memalign(&area, page_size, nr_pages * page_size)) {
-                fprintf(stderr, "out of memory\n");
-                return 1;
-        }
-        area_dst = area;
 
         uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
         if (uffd < 0) {
@@ -445,7 +546,7 @@ static int userfaultfd_stress(void)
         uffd_flags = fcntl(uffd, F_GETFD, NULL);
 
         uffdio_api.api = UFFD_API;
-        uffdio_api.features = 0;
+        uffdio_api.features = features;
         if (ioctl(uffd, UFFDIO_API, &uffdio_api)) {
                 fprintf(stderr, "UFFDIO_API\n");
                 return 1;
@@ -455,6 +556,233 @@ static int userfaultfd_stress(void)
                 return 1;
         }
 
+        return 0;
+}
+
+/*
+ * For non-cooperative userfaultfd test we fork() a process that will
+ * generate pagefaults, will mremap the area monitored by the
+ * userfaultfd and at last this process will release the monitored
+ * area.
+ * For the anonymous and shared memory the area is divided into two
+ * parts, the first part is accessed before mremap, and the second
+ * part is accessed after mremap. Since hugetlbfs does not support
+ * mremap, the entire monitored area is accessed in a single pass for
+ * HUGETLB_TEST.
+ * The release of the pages currently generates event for shmem and
+ * anonymous memory (UFFD_EVENT_REMOVE), hence it is not checked
+ * for hugetlb.
+ */
+static int faulting_process(void)
+{
+        unsigned long nr;
+        unsigned long long count;
+
+#ifndef HUGETLB_TEST
+        unsigned long split_nr_pages = (nr_pages + 1) / 2;
+#else
+        unsigned long split_nr_pages = nr_pages;
+#endif
+
+        for (nr = 0; nr < split_nr_pages; nr++) {
+                count = *area_count(area_dst, nr);
+                if (count != count_verify[nr]) {
+                        fprintf(stderr,
+                                "nr %lu memory corruption %Lu %Lu\n",
+                                nr, count,
+                                count_verify[nr]), exit(1);
+                }
+        }
+
+#ifndef HUGETLB_TEST
+        area_dst = mremap(area_dst, nr_pages * page_size,  nr_pages * page_size,
+                          MREMAP_MAYMOVE | MREMAP_FIXED, area_src);
+        if (area_dst == MAP_FAILED)
+                perror("mremap"), exit(1);
+
+        for (; nr < nr_pages; nr++) {
+                count = *area_count(area_dst, nr);
+                if (count != count_verify[nr]) {
+                        fprintf(stderr,
+                                "nr %lu memory corruption %Lu %Lu\n",
+                                nr, count,
+                                count_verify[nr]), exit(1);
+                }
+        }
+
+        if (release_pages(area_dst))
+                return 1;
+
+        for (nr = 0; nr < nr_pages; nr++) {
+                if (my_bcmp(area_dst + nr * page_size, zeropage, page_size))
+                        fprintf(stderr, "nr %lu is not zero\n", nr), exit(1);
+        }
+
+#endif /* HUGETLB_TEST */
+
+        return 0;
+}
+
+static int uffdio_zeropage(int ufd, unsigned long offset)
+{
+        struct uffdio_zeropage uffdio_zeropage;
+        int ret;
+        unsigned long has_zeropage = EXPECTED_IOCTLS & (1 << _UFFDIO_ZEROPAGE);
+
+        if (offset >= nr_pages * page_size)
+                fprintf(stderr, "unexpected offset %lu\n",
+                        offset), exit(1);
+        uffdio_zeropage.range.start = (unsigned long) area_dst + offset;
+        uffdio_zeropage.range.len = page_size;
+        uffdio_zeropage.mode = 0;
+        ret = ioctl(ufd, UFFDIO_ZEROPAGE, &uffdio_zeropage);
+        if (ret) {
+                /* real retval in ufdio_zeropage.zeropage */
+                if (has_zeropage) {
+                        if (uffdio_zeropage.zeropage == -EEXIST)
+                                fprintf(stderr, "UFFDIO_ZEROPAGE -EEXIST\n"),
+                                        exit(1);
+                        else
+                                fprintf(stderr, "UFFDIO_ZEROPAGE error %Ld\n",
+                                        uffdio_zeropage.zeropage), exit(1);
+                } else {
+                        if (uffdio_zeropage.zeropage != -EINVAL)
+                                fprintf(stderr,
+                                        "UFFDIO_ZEROPAGE not -EINVAL %Ld\n",
+                                        uffdio_zeropage.zeropage), exit(1);
+                }
+        } else if (has_zeropage) {
+                if (uffdio_zeropage.zeropage != page_size) {
+                        fprintf(stderr, "UFFDIO_ZEROPAGE unexpected %Ld\n",
+                                uffdio_zeropage.zeropage), exit(1);
+                } else
+                        return 1;
+        } else {
+                fprintf(stderr,
+                        "UFFDIO_ZEROPAGE succeeded %Ld\n",
+                        uffdio_zeropage.zeropage), exit(1);
+        }
+
+        return 0;
+}
+
+/* exercise UFFDIO_ZEROPAGE */
+static int userfaultfd_zeropage_test(void)
+{
+        struct uffdio_register uffdio_register;
+        unsigned long expected_ioctls;
+
+        printf("testing UFFDIO_ZEROPAGE: ");
+        fflush(stdout);
+
+        if (release_pages(area_dst))
+                return 1;
+
+        if (userfaultfd_open(0) < 0)
+                return 1;
+        uffdio_register.range.start = (unsigned long) area_dst;
+        uffdio_register.range.len = nr_pages * page_size;
+        uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
+        if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
+                fprintf(stderr, "register failure\n"), exit(1);
+
+        expected_ioctls = EXPECTED_IOCTLS;
+        if ((uffdio_register.ioctls & expected_ioctls) !=
+            expected_ioctls)
+                fprintf(stderr,
+                        "unexpected missing ioctl for anon memory\n"),
+                        exit(1);
+
+        if (uffdio_zeropage(uffd, 0)) {
+                if (my_bcmp(area_dst, zeropage, page_size))
+                        fprintf(stderr, "zeropage is not zero\n"), exit(1);
+        }
+
+        close(uffd);
+        printf("done.\n");
+        return 0;
+}
+
+static int userfaultfd_events_test(void)
+{
+        struct uffdio_register uffdio_register;
+        unsigned long expected_ioctls;
+        unsigned long userfaults;
+        pthread_t uffd_mon;
+        int err, features;
+        pid_t pid;
+        char c;
+
+        printf("testing events (fork, remap, remove): ");
+        fflush(stdout);
+
+        if (release_pages(area_dst))
+                return 1;
+
+        features = UFFD_FEATURE_EVENT_FORK | UFFD_FEATURE_EVENT_REMAP |
+                UFFD_FEATURE_EVENT_REMOVE;
+        if (userfaultfd_open(features) < 0)
+                return 1;
+        fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
+
+        uffdio_register.range.start = (unsigned long) area_dst;
+        uffdio_register.range.len = nr_pages * page_size;
+        uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
+        if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
+                fprintf(stderr, "register failure\n"), exit(1);
+
+        expected_ioctls = EXPECTED_IOCTLS;
+        if ((uffdio_register.ioctls & expected_ioctls) !=
+            expected_ioctls)
+                fprintf(stderr,
+                        "unexpected missing ioctl for anon memory\n"),
+                        exit(1);
+
+        if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, NULL))
+                perror("uffd_poll_thread create"), exit(1);
+
+        pid = fork();
+        if (pid < 0)
+                perror("fork"), exit(1);
+
+        if (!pid)
+                return faulting_process();
+
+        waitpid(pid, &err, 0);
+        if (err)
+                fprintf(stderr, "faulting process failed\n"), exit(1);
+
+        if (write(pipefd[1], &c, sizeof(c)) != sizeof(c))
+                perror("pipe write"), exit(1);
+        if (pthread_join(uffd_mon, (void **)&userfaults))
+                return 1;
+
+        close(uffd);
+        printf("userfaults: %ld\n", userfaults);
+
+        return userfaults != nr_pages;
+}
+
+static int userfaultfd_stress(void)
+{
+        void *area;
+        char *tmp_area;
+        unsigned long nr;
+        struct uffdio_register uffdio_register;
+        unsigned long cpu;
+        int err;
+        unsigned long userfaults[nr_cpus];
+
+        allocate_area((void **)&area_src);
+        if (!area_src)
+                return 1;
+        allocate_area((void **)&area_dst);
+        if (!area_dst)
+                return 1;
+
+        if (userfaultfd_open(0) < 0)
+                return 1;
+
         count_verify = malloc(nr_pages * sizeof(unsigned long long));
         if (!count_verify) {
                 perror("count_verify");
@@ -528,9 +856,7 @@ static int userfaultfd_stress(void)
                         fprintf(stderr, "register failure\n");
                         return 1;
                 }
-                expected_ioctls = (1 << _UFFDIO_WAKE) |
-                                  (1 << _UFFDIO_COPY) |
-                                  (1 << _UFFDIO_ZEROPAGE);
+                expected_ioctls = EXPECTED_IOCTLS;
                 if ((uffdio_register.ioctls & expected_ioctls) !=
                     expected_ioctls) {
                         fprintf(stderr,
@@ -562,10 +888,8 @@ static int userfaultfd_stress(void)
                  * MADV_DONTNEED only after the UFFDIO_REGISTER, so it's
                  * required to MADV_DONTNEED here.
                  */
-                if (madvise(area_dst, nr_pages * page_size, MADV_DONTNEED)) {
-                        perror("madvise 2");
+                if (release_pages(area_dst))
                         return 1;
-                }
 
                 /* bounce pass */
                 if (stress(userfaults))
@@ -603,9 +927,15 @@ static int userfaultfd_stress(void)
                 printf("\n");
         }
 
-        return err;
+        if (err)
+                return err;
+
+        close(uffd);
+        return userfaultfd_zeropage_test() || userfaultfd_events_test();
 }
 
+#ifndef HUGETLB_TEST
+
 int main(int argc, char **argv)
 {
         if (argc < 3)
@@ -632,6 +962,74 @@ int main(int argc, char **argv)
         return userfaultfd_stress();
 }
 
+#else /* HUGETLB_TEST */
+
+/*
+ * Copied from mlock2-tests.c
+ */
+unsigned long default_huge_page_size(void)
+{
+        unsigned long hps = 0;
+        char *line = NULL;
+        size_t linelen = 0;
+        FILE *f = fopen("/proc/meminfo", "r");
+
+        if (!f)
+                return 0;
+        while (getline(&line, &linelen, f) > 0) {
+                if (sscanf(line, "Hugepagesize:       %lu kB", &hps) == 1) {
+                        hps <<= 10;
+                        break;
+                }
+        }
+
+        free(line);
+        fclose(f);
+        return hps;
+}
+
+int main(int argc, char **argv)
+{
+        if (argc < 4)
+                fprintf(stderr, "Usage: <MiB> <bounces> <hugetlbfs_file>\n"),
+                                exit(1);
+        nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
+        page_size = default_huge_page_size();
+        if (!page_size)
+                fprintf(stderr, "Unable to determine huge page size\n"),
+                                exit(2);
+        if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2
+            > page_size)
+                fprintf(stderr, "Impossible to run this test\n"), exit(2);
+        nr_pages_per_cpu = atol(argv[1]) * 1024*1024 / page_size /
+                nr_cpus;
+        if (!nr_pages_per_cpu) {
+                fprintf(stderr, "invalid MiB\n");
+                fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1);
+        }
+        bounces = atoi(argv[2]);
+        if (bounces <= 0) {
+                fprintf(stderr, "invalid bounces\n");
+                fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1);
+        }
+        nr_pages = nr_pages_per_cpu * nr_cpus;
+        huge_fd = open(argv[3], O_CREAT | O_RDWR, 0755);
+        if (huge_fd < 0) {
+                fprintf(stderr, "Open of %s failed", argv[3]);
+                perror("open");
+                exit(1);
+        }
+        if (ftruncate(huge_fd, 0)) {
+                fprintf(stderr, "ftruncate %s to size 0 failed", argv[3]);
+                perror("ftruncate");
+                exit(1);
+        }
+        printf("nr_pages: %lu, nr_pages_per_cpu: %lu\n",
+               nr_pages, nr_pages_per_cpu);
+        return userfaultfd_stress();
+}
+
+#endif
 #else /* __NR_userfaultfd */
 
 #warning "missing __NR_userfaultfd definition"
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 83d8b1c6cb0e..38e0a9ca5d71 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -5,7 +5,7 @@ include ../lib.mk
 .PHONY: all all_32 all_64 warn_32bit_failure clean
 
 TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall test_mremap_vdso \
-                        check_initial_reg_state sigreturn ldt_gdt iopl mpx-mini-test \
+                        check_initial_reg_state sigreturn ldt_gdt iopl mpx-mini-test ioperm \
                         protection_keys test_vdso
 TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
                         test_FCMOV test_FCOMI test_FISTTP \
@@ -17,6 +17,9 @@ TARGETS_C_64BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_64BIT_ONLY)
 BINARIES_32 := $(TARGETS_C_32BIT_ALL:%=%_32)
 BINARIES_64 := $(TARGETS_C_64BIT_ALL:%=%_64)
 
+BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32))
+BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64))
+
 CFLAGS := -O2 -g -std=gnu99 -pthread -Wall
 
 UNAME_M := $(shell uname -m)
@@ -40,10 +43,10 @@ all_64: $(BINARIES_64)
 clean:
         $(RM) $(BINARIES_32) $(BINARIES_64)
 
-$(TARGETS_C_32BIT_ALL:%=%_32): %_32: %.c
+$(BINARIES_32): $(OUTPUT)/%_32: %.c
         $(CC) -m32 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl -lm
 
-$(TARGETS_C_64BIT_ALL:%=%_64): %_64: %.c
+$(BINARIES_64): $(OUTPUT)/%_64: %.c
         $(CC) -m64 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl
 
 # x86_64 users should be encouraged to install 32-bit libraries
@@ -65,12 +68,12 @@ warn_32bit_failure:
 endif
 
 # Some tests have additional dependencies.
-sysret_ss_attrs_64: thunks.S
-ptrace_syscall_32: raw_syscall_helper_32.S
-test_syscall_vdso_32: thunks_32.S
+$(OUTPUT)/sysret_ss_attrs_64: thunks.S
+$(OUTPUT)/ptrace_syscall_32: raw_syscall_helper_32.S
+$(OUTPUT)/test_syscall_vdso_32: thunks_32.S
 
 # check_initial_reg_state is special: it needs a custom entry, and it
 # needs to be static so that its interpreter doesn't destroy its initial
 # state.
-check_initial_reg_state_32: CFLAGS += -Wl,-ereal_start -static
-check_initial_reg_state_64: CFLAGS += -Wl,-ereal_start -static
+$(OUTPUT)/check_initial_reg_state_32: CFLAGS += -Wl,-ereal_start -static
+$(OUTPUT)/check_initial_reg_state_64: CFLAGS += -Wl,-ereal_start -static
diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c
index 5b2b4b3c634c..b4967d875236 100644
--- a/tools/testing/selftests/x86/fsgsbase.c
+++ b/tools/testing/selftests/x86/fsgsbase.c
@@ -245,7 +245,7 @@ void do_unexpected_base(void)
                 long ret;
                 asm volatile ("int $0x80"
                               : "=a" (ret) : "a" (243), "b" (low_desc)
-                              : "flags");
+                              : "r8", "r9", "r10", "r11");
                 memcpy(&desc, low_desc, sizeof(desc));
                 munmap(low_desc, sizeof(desc));
 
diff --git a/tools/testing/selftests/x86/ioperm.c b/tools/testing/selftests/x86/ioperm.c
new file mode 100644
index 000000000000..b77313ba2ab1
--- /dev/null
+++ b/tools/testing/selftests/x86/ioperm.c
@@ -0,0 +1,170 @@
+/*
+ * ioperm.c - Test case for ioperm(2)
+ * Copyright (c) 2015 Andrew Lutomirski
+ */
+
+#define _GNU_SOURCE
+#include <err.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <signal.h>
+#include <setjmp.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <stdbool.h>
+#include <sched.h>
+#include <sys/io.h>
+
+static int nerrs = 0;
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+                       int flags)
+{
+        struct sigaction sa;
+        memset(&sa, 0, sizeof(sa));
+        sa.sa_sigaction = handler;
+        sa.sa_flags = SA_SIGINFO | flags;
+        sigemptyset(&sa.sa_mask);
+        if (sigaction(sig, &sa, 0))
+                err(1, "sigaction");
+
+}
+
+static void clearhandler(int sig)
+{
+        struct sigaction sa;
+        memset(&sa, 0, sizeof(sa));
+        sa.sa_handler = SIG_DFL;
+        sigemptyset(&sa.sa_mask);
+        if (sigaction(sig, &sa, 0))
+                err(1, "sigaction");
+}
+
+static jmp_buf jmpbuf;
+
+static void sigsegv(int sig, siginfo_t *si, void *ctx_void)
+{
+        siglongjmp(jmpbuf, 1);
+}
+
+static bool try_outb(unsigned short port)
+{
+        sethandler(SIGSEGV, sigsegv, SA_RESETHAND);
+        if (sigsetjmp(jmpbuf, 1) != 0) {
+                return false;
+        } else {
+                asm volatile ("outb %%al, %w[port]"
+                              : : [port] "Nd" (port), "a" (0));
+                return true;
+        }
+        clearhandler(SIGSEGV);
+}
+
+static void expect_ok(unsigned short port)
+{
+        if (!try_outb(port)) {
+                printf("[FAIL]\toutb to 0x%02hx failed\n", port);
+                exit(1);
+        }
+
+        printf("[OK]\toutb to 0x%02hx worked\n", port);
+}
+
+static void expect_gp(unsigned short port)
+{
+        if (try_outb(port)) {
+                printf("[FAIL]\toutb to 0x%02hx worked\n", port);
+                exit(1);
+        }
+
+        printf("[OK]\toutb to 0x%02hx failed\n", port);
+}
+
+int main(void)
+{
+        cpu_set_t cpuset;
+        CPU_ZERO(&cpuset);
+        CPU_SET(0, &cpuset);
+        if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0)
+                err(1, "sched_setaffinity to CPU 0");
+
+        expect_gp(0x80);
+        expect_gp(0xed);
+
+        /*
+         * Probe for ioperm support.  Note that clearing ioperm bits
+         * works even as nonroot.
+         */
+        printf("[RUN]\tenable 0x80\n");
+        if (ioperm(0x80, 1, 1) != 0) {
+                printf("[OK]\tioperm(0x80, 1, 1) failed (%d) -- try running as root\n",
+                       errno);
+                return 0;
+        }
+        expect_ok(0x80);
+        expect_gp(0xed);
+
+        printf("[RUN]\tdisable 0x80\n");
+        if (ioperm(0x80, 1, 0) != 0) {
+                printf("[FAIL]\tioperm(0x80, 1, 0) failed (%d)", errno);
+                return 1;
+        }
+        expect_gp(0x80);
+        expect_gp(0xed);
+
+        /* Make sure that fork() preserves ioperm. */
+        if (ioperm(0x80, 1, 1) != 0) {
+                printf("[FAIL]\tioperm(0x80, 1, 0) failed (%d)", errno);
+                return 1;
+        }
+
+        pid_t child = fork();
+        if (child == -1)
+                err(1, "fork");
+
+        if (child == 0) {
+                printf("[RUN]\tchild: check that we inherited permissions\n");
+                expect_ok(0x80);
+                expect_gp(0xed);
+                return 0;
+        } else {
+                int status;
+                if (waitpid(child, &status, 0) != child ||
+                    !WIFEXITED(status)) {
+                        printf("[FAIL]\tChild died\n");
+                        nerrs++;
+                } else if (WEXITSTATUS(status) != 0) {
+                        printf("[FAIL]\tChild failed\n");
+                        nerrs++;
+                } else {
+                        printf("[OK]\tChild succeeded\n");
+                }
+        }
+
+        /* Test the capability checks. */
+
+        printf("\tDrop privileges\n");
+        if (setresuid(1, 1, 1) != 0) {
+                printf("[WARN]\tDropping privileges failed\n");
+                return 0;
+        }
+
+        printf("[RUN]\tdisable 0x80\n");
+        if (ioperm(0x80, 1, 0) != 0) {
+                printf("[FAIL]\tioperm(0x80, 1, 0) failed (%d)", errno);
+                return 1;
+        }
+        printf("[OK]\tit worked\n");
+
+        printf("[RUN]\tenable 0x80 again\n");
+        if (ioperm(0x80, 1, 1) == 0) {
+                printf("[FAIL]\tit succeeded but should have failed.\n");
+                return 1;
+        }
+        printf("[OK]\tit failed\n");
+        return 0;
+}
diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c
index 4af47079cf04..f6121612e769 100644
--- a/tools/testing/selftests/x86/ldt_gdt.c
+++ b/tools/testing/selftests/x86/ldt_gdt.c
@@ -45,6 +45,12 @@
 #define AR_DB                   (1 << 22)
 #define AR_G                    (1 << 23)
 
+#ifdef __x86_64__
+# define INT80_CLOBBERS "r8", "r9", "r10", "r11"
+#else
+# define INT80_CLOBBERS
+#endif
+
 static int nerrs;
 
 /* Points to an array of 1024 ints, each holding its own index. */
@@ -588,7 +594,7 @@ static int invoke_set_thread_area(void)
         asm volatile ("int $0x80"
                       : "=a" (ret), "+m" (low_user_desc) :
                         "a" (243), "b" (low_user_desc)
-                      : "flags");
+                      : INT80_CLOBBERS);
         return ret;
 }
 
@@ -657,7 +663,7 @@ static void test_gdt_invalidation(void)
                         "+a" (eax)
                       : "m" (low_user_desc_clear),
                         [arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear)
-                      : "flags");
+                      : INT80_CLOBBERS);
 
         if (sel != 0) {
                 result = "FAIL";
@@ -688,7 +694,7 @@ static void test_gdt_invalidation(void)
                         "+a" (eax)
                       : "m" (low_user_desc_clear),
                         [arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear)
-                      : "flags");
+                      : INT80_CLOBBERS);
 
         if (sel != 0) {
                 result = "FAIL";
@@ -721,7 +727,7 @@ static void test_gdt_invalidation(void)
                         "+a" (eax)
                       : "m" (low_user_desc_clear),
                         [arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear)
-                      : "flags");
+                      : INT80_CLOBBERS);
 
 #ifdef __x86_64__
         syscall(SYS_arch_prctl, ARCH_GET_FS, &new_base);
@@ -774,7 +780,7 @@ static void test_gdt_invalidation(void)
                         "+a" (eax)
                       : "m" (low_user_desc_clear),
                         [arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear)
-                      : "flags");
+                      : INT80_CLOBBERS);
 
 #ifdef __x86_64__
         syscall(SYS_arch_prctl, ARCH_GET_GS, &new_base);
diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c
index df9e0a0cdf29..3237bc010e1c 100644
--- a/tools/testing/selftests/x86/protection_keys.c
+++ b/tools/testing/selftests/x86/protection_keys.c
@@ -192,7 +192,7 @@ void lots_o_noops_around_write(int *write_to_me)
 #define SYS_pkey_alloc   381
 #define SYS_pkey_free    382
 #define REG_IP_IDX REG_EIP
-#define si_pkey_offset 0x18
+#define si_pkey_offset 0x14
 #else
 #define SYS_mprotect_key 329
 #define SYS_pkey_alloc   330
@@ -462,7 +462,7 @@ void pkey_disable_set(int pkey, int flags)
         unsigned long syscall_flags = 0;
         int ret;
         int pkey_rights;
-        u32 orig_pkru;
+        u32 orig_pkru = rdpkru();
 
         dprintf1("START->%s(%d, 0x%x)\n", __func__,
                 pkey, flags);
@@ -812,8 +812,6 @@ void setup_hugetlbfs(void)
 {
         int err;
         int fd;
-        int validated_nr_pages;
-        int i;
         char buf[] = "123";
 
         if (geteuid() != 0) {
@@ -1116,11 +1114,6 @@ void test_pkey_syscalls_on_non_allocated_pkey(int *ptr, u16 pkey)
                 err = sys_pkey_free(i);
                 pkey_assert(err);
 
-                /* not enforced when pkey_get() is not a syscall
-                err = pkey_get(i, 0);
-                pkey_assert(err < 0);
-                */
-
                 err = sys_pkey_free(i);
                 pkey_assert(err);
 
@@ -1133,14 +1126,8 @@ void test_pkey_syscalls_on_non_allocated_pkey(int *ptr, u16 pkey)
 void test_pkey_syscalls_bad_args(int *ptr, u16 pkey)
 {
         int err;
-        int bad_flag = (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE) + 1;
         int bad_pkey = NR_PKEYS+99;
 
-        /* not enforced when pkey_get() is not a syscall
-        err = pkey_get(bad_pkey, bad_flag);
-        pkey_assert(err < 0);
-        */
-
         /* pass a known-invalid pkey in: */
         err = sys_mprotect_pkey(ptr, PAGE_SIZE, PROT_READ, bad_pkey);
         pkey_assert(err);
@@ -1149,8 +1136,6 @@ void test_pkey_syscalls_bad_args(int *ptr, u16 pkey)
 /* Assumes that all pkeys other than 'pkey' are unallocated */
 void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
 {
-        unsigned long flags;
-        unsigned long init_val;
         int err;
         int allocated_pkeys[NR_PKEYS] = {0};
         int nr_allocated_pkeys = 0;
diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c
index b037ce9cf116..eaea92439708 100644
--- a/tools/testing/selftests/x86/ptrace_syscall.c
+++ b/tools/testing/selftests/x86/ptrace_syscall.c
@@ -58,7 +58,8 @@ static void do_full_int80(struct syscall_args32 *args)
         asm volatile ("int $0x80"
                       : "+a" (args->nr),
                         "+b" (args->arg0), "+c" (args->arg1), "+d" (args->arg2),
-                        "+S" (args->arg3), "+D" (args->arg4), "+r" (bp));
+                        "+S" (args->arg3), "+D" (args->arg4), "+r" (bp)
+                        : : "r8", "r9", "r10", "r11");
         args->arg5 = bp;
 #else
         sys32_helper(args, int80_and_ret);
diff --git a/tools/testing/selftests/x86/single_step_syscall.c b/tools/testing/selftests/x86/single_step_syscall.c
index 50c26358e8b7..a48da95c18fd 100644
--- a/tools/testing/selftests/x86/single_step_syscall.c
+++ b/tools/testing/selftests/x86/single_step_syscall.c
@@ -56,9 +56,11 @@ static volatile sig_atomic_t sig_traps;
 #ifdef __x86_64__
 # define REG_IP REG_RIP
 # define WIDTH "q"
+# define INT80_CLOBBERS "r8", "r9", "r10", "r11"
 #else
 # define REG_IP REG_EIP
 # define WIDTH "l"
+# define INT80_CLOBBERS
 #endif
 
 static unsigned long get_eflags(void)
@@ -140,7 +142,8 @@ int main()
 
         printf("[RUN]\tSet TF and check int80\n");
         set_eflags(get_eflags() | X86_EFLAGS_TF);
-        asm volatile ("int $0x80" : "=a" (tmp) : "a" (SYS_getpid));
+        asm volatile ("int $0x80" : "=a" (tmp) : "a" (SYS_getpid)
+                        : INT80_CLOBBERS);
         check_result();
 
         /*
diff --git a/tools/testing/selftests/zram/Makefile b/tools/testing/selftests/zram/Makefile
index 29d80346e3eb..c3a87e5f9d36 100644
--- a/tools/testing/selftests/zram/Makefile
+++ b/tools/testing/selftests/zram/Makefile
@@ -2,8 +2,7 @@ all:
 
 TEST_PROGS := zram.sh
 TEST_FILES := zram01.sh zram02.sh zram_lib.sh
+EXTRA_CLEAN := err.log
 
 include ../lib.mk
 
-clean:
-        $(RM) err.log
diff --git a/tools/usb/ffs-test.c b/tools/usb/ffs-test.c
index 88d5e71be044..95dd14648ba5 100644
--- a/tools/usb/ffs-test.c
+++ b/tools/usb/ffs-test.c
@@ -22,7 +22,7 @@
 /* $(CROSS_COMPILE)cc -Wall -Wextra -g -o ffs-test ffs-test.c -lpthread */
 
 
-#define _BSD_SOURCE /* for endian.h */
+#define _DEFAULT_SOURCE /* for endian.h */
 
 #include <endian.h>
 #include <errno.h>
@@ -110,16 +110,25 @@ static const struct {
         struct usb_functionfs_descs_head_v2 header;
         __le32 fs_count;
         __le32 hs_count;
+        __le32 ss_count;
         struct {
                 struct usb_interface_descriptor intf;
                 struct usb_endpoint_descriptor_no_audio sink;
                 struct usb_endpoint_descriptor_no_audio source;
         } __attribute__((packed)) fs_descs, hs_descs;
+        struct {
+                struct usb_interface_descriptor intf;
+                struct usb_endpoint_descriptor_no_audio sink;
+                struct usb_ss_ep_comp_descriptor sink_comp;
+                struct usb_endpoint_descriptor_no_audio source;
+                struct usb_ss_ep_comp_descriptor source_comp;
+        } ss_descs;
 } __attribute__((packed)) descriptors = {
         .header = {
                 .magic = cpu_to_le32(FUNCTIONFS_DESCRIPTORS_MAGIC_V2),
                 .flags = cpu_to_le32(FUNCTIONFS_HAS_FS_DESC |
-                                     FUNCTIONFS_HAS_HS_DESC),
+                                     FUNCTIONFS_HAS_HS_DESC |
+                                     FUNCTIONFS_HAS_SS_DESC),
                 .length = cpu_to_le32(sizeof descriptors),
         },
         .fs_count = cpu_to_le32(3),
@@ -171,6 +180,45 @@ static const struct {
                         .bInterval = 1, /* NAK every 1 uframe */
                 },
         },
+        .ss_count = cpu_to_le32(5),
+        .ss_descs = {
+                .intf = {
+                        .bLength = sizeof descriptors.fs_descs.intf,
+                        .bDescriptorType = USB_DT_INTERFACE,
+                        .bNumEndpoints = 2,
+                        .bInterfaceClass = USB_CLASS_VENDOR_SPEC,
+                        .iInterface = 1,
+                },
+                .sink = {
+                        .bLength = sizeof descriptors.hs_descs.sink,
+                        .bDescriptorType = USB_DT_ENDPOINT,
+                        .bEndpointAddress = 1 | USB_DIR_IN,
+                        .bmAttributes = USB_ENDPOINT_XFER_BULK,
+                        .wMaxPacketSize = cpu_to_le16(1024),
+                },
+                .sink_comp = {
+                        .bLength = USB_DT_SS_EP_COMP_SIZE,
+                        .bDescriptorType = USB_DT_SS_ENDPOINT_COMP,
+                        .bMaxBurst = 0,
+                        .bmAttributes = 0,
+                        .wBytesPerInterval = 0,
+                },
+                .source = {
+                        .bLength = sizeof descriptors.hs_descs.source,
+                        .bDescriptorType = USB_DT_ENDPOINT,
+                        .bEndpointAddress = 2 | USB_DIR_OUT,
+                        .bmAttributes = USB_ENDPOINT_XFER_BULK,
+                        .wMaxPacketSize = cpu_to_le16(1024),
+                        .bInterval = 1, /* NAK every 1 uframe */
+                },
+                .source_comp = {
+                        .bLength = USB_DT_SS_EP_COMP_SIZE,
+                        .bDescriptorType = USB_DT_SS_ENDPOINT_COMP,
+                        .bMaxBurst = 0,
+                        .bmAttributes = 0,
+                        .wBytesPerInterval = 0,
+                },
+        },
 };
 
 static size_t descs_to_legacy(void **legacy, const void *descriptors_v2)
diff --git a/tools/usb/usbip/README b/tools/usb/usbip/README
index 831f49fea3ce..5eb2b6c7722b 100644
--- a/tools/usb/usbip/README
+++ b/tools/usb/usbip/README
@@ -4,10 +4,33 @@
 # Copyright (C) 2011 matt mooney <mfm@muteddisk.com>
 #               2005-2008 Takahiro Hirofuchi
 
+[Overview]
+USB/IP protocol allows to pass USB device from server to client over the
+network. Server is a machine which provides (shares) a USB device. Client is
+a machine which uses USB device provided by server over the network.
+The USB device may be either physical device connected to a server or
+software entity created on a server using USB gadget subsystem.
+Whole project consists of four parts:
+
+    - usbip-vhci
+        A client side kernel module which provides a virtual USB Host Controller
+        and allows to import a USB device from a remote machine.
+
+    - usbip-host (stub driver)
+        A server side module which provides a USB device driver which can be
+        bound to a physical USB device to make it exportable.
+
+    - usbip-vudc
+        A server side module which provides a virtual USB Device Controller and allows
+        to export a USB device created using USB Gadget Subsystem.
+
+    - usbip-utils
+        A set of userspace tools used to handle connection and management.
+        Used on both sides.
 
 [Requirements]
     - USB/IP device drivers
-        Found in the staging directory of the Linux kernel.
+        Found in the drivers/usb/usbip/ directory of the Linux kernel tree.
 
     - libudev >= 2.0
         libudev library
@@ -36,6 +59,10 @@
 
 
 [Usage]
+On a server side there are two entities which can be shared.
+First of them is physical usb device connected to the machine.
+To make it available below steps should be executed:
+
     server:# (Physically attach your USB device.)
 
     server:# insmod usbip-core.ko
@@ -52,6 +79,30 @@
         - The USB device 1-2 is now exportable to other hosts!
         - Use `usbip unbind --busid 1-2' to stop exporting the device.
 
+Second of shareable entities is USB Gadget created using USB Gadget Subsystem
+on a server machine. To make it available below steps should be executed:
+
+    server:# (Create your USB gadget)
+        - Currently the most preferable way of creating a new USB gadget
+          is ConfigFS Composite Gadget. Please refer to its documentation
+          for details.
+        - See vudc_server_example.sh for a short example of USB gadget creation
+
+    server:# insmod usbip-core.ko
+    server:# insmod usbip-vudc.ko
+        - To create more than one instance of vudc use num module param
+
+    server:# (Bind gadget to one of available vudc)
+        - Assign your new gadget to USB/IP UDC
+        - Using ConfigFS interface you may do this simply by:
+            server:# cd /sys/kernel/config/usb_gadget/<gadget_name>
+            server:# echo "usbip-vudc.0" > UDC
+
+    server:# usbipd -D --device
+        - Start usbip daemon.
+
+To attach new device to client machine below commands should be used:
+
     client:# insmod usbip-core.ko
     client:# insmod vhci-hcd.ko
 
@@ -60,6 +111,8 @@
 
     client:# usbip attach --remote <host> --busid 1-2
         - Connect the remote USB device.
+        - When using vudc on a server side busid is really vudc instance name.
+          For example: usbip-vudc.0
 
     client:# usbip port
         - Show virtual port status.
@@ -192,6 +245,8 @@ Detach the imported device:
         - http://usbip.wiki.sourceforge.net/how-to-debug-usbip
     - usbip-host.ko must be bound to the target device.
         - See /proc/bus/usb/devices and find "Driver=..." lines of the device.
+    - Target USB gadget must be bound to vudc
+      (using USB gadget susbsys, not usbip bind command)
     - Shutdown firewall.
         - usbip now uses TCP port 3240.
     - Disable SELinux.
diff --git a/tools/usb/usbip/vudc/vudc_server_example.sh b/tools/usb/usbip/vudc/vudc_server_example.sh
new file mode 100755
index 000000000000..2736be64f203
--- /dev/null
+++ b/tools/usb/usbip/vudc/vudc_server_example.sh
@@ -0,0 +1,107 @@
+#!/bin/bash
+
+################################################################################
+# This is free and unencumbered software released into the public domain.
+#
+# Anyone is free to copy, modify, publish, use, compile, sell, or
+# distribute this software, either in source code form or as a compiled
+# binary, for any purpose, commercial or non-commercial, and by any
+# means.
+#
+# In jurisdictions that recognize copyright laws, the author or authors
+# of this software dedicate any and all copyright interest in the
+# software to the public domain. We make this dedication for the benefit
+# of the public at large and to the detriment of our heirs and
+# successors. We intend this dedication to be an overt act of
+# relinquishment in perpetuity of all present and future rights to this
+# software under copyright law.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+# IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+# For more information, please refer to <http://unlicense.org/>
+################################################################################
+
+################################################################################
+# This is a sample script which shows how to use vUDC with ConfigFS gadgets
+################################################################################
+
+# Stop script on error
+set -e
+
+################################################################################
+# Create your USB gadget
+# You may use bare ConfigFS interface (as below)
+# or libusbgx or gt toool
+# Instead of ConfigFS gadgets you may use any of legacy gadgets.
+################################################################################
+CONFIGFS_MOUNT_POINT="/sys/kernel/config"
+GADGET_NAME="g1"
+ID_VENDOR="0x1d6b"
+ID_PRODUCT="0x0104"
+
+cd ${CONFIGFS_MOUNT_POINT}/usb_gadget
+# Create a new USB gadget
+mkdir ${GADGET_NAME}
+cd ${GADGET_NAME}
+
+# This gadget contains one function - ACM (serial port over USB)
+FUNC_DIR="functions/acm.ser0"
+mkdir ${FUNC_DIR}
+
+# Just one configuration
+mkdir configs/c.1
+ln -s ${FUNC_DIR} configs/c.1
+
+# Set our gadget identity
+echo ${ID_VENDOR} > idVendor
+echo ${ID_PRODUCT} > idProduct
+
+################################################################################
+# Load vudc-module if vudc is not available
+# You may change value of num param to get more than one vUDC instance
+################################################################################
+[[ -d /sys/class/udc/usbip-vudc.0 ]] || modprobe usbip-vudc num=1
+
+################################################################################
+# Bind gadget to our vUDC
+# By default we bind to first one but you may change this if you would like
+# to use more than one instance
+################################################################################
+echo "usbip-vudc.0" > UDC
+
+################################################################################
+# Let's now run our usbip daemon in a USB device mode
+################################################################################
+usbipd --device &
+
+################################################################################
+# Now your USB gadget is available using USB/IP protocol.
+# To prepare your client, you should ensure that usbip-vhci module is inside
+# your kernel. If it's not then you can load it:
+#
+# $ modprobe usbip-vhci
+#
+# To check availability of your gadget you may try to list devices exported
+# on a remote server:
+#
+# $ modprobe usbip-vhci
+# $ usbip list -r $SERVER_IP
+# Exportable USB devices
+# ======================
+# usbipd: info: request 0x8005(6): complete
+#  - 127.0.0.1
+# usbip-vudc.0: Linux Foundation : unknown product (1d6b:0104)
+#            : /sys/devices/platform/usbip-vudc.0
+#            : (Defined at Interface level) (00/00/00)
+#
+# To attach this device to your client you may use:
+#
+# $ usbip attach -r $SERVER_IP -d usbip-vudc.0
+#
+################################################################################
diff --git a/tools/vm/Makefile b/tools/vm/Makefile
index 93aadaf7ff63..006029456988 100644
--- a/tools/vm/Makefile
+++ b/tools/vm/Makefile
@@ -9,6 +9,8 @@ CC = $(CROSS_COMPILE)gcc
 CFLAGS = -Wall -Wextra -I../lib/
 LDFLAGS = $(LIBS)
 
+all: $(TARGETS)
+
 $(TARGETS): $(LIBS)
 
 $(LIBS):
@@ -20,3 +22,9 @@ $(LIBS):
 clean:
         $(RM) page-types slabinfo page_owner_sort
         make -C $(LIB_DIR) clean
+
+sbindir ?= /usr/sbin
+
+install: all
+        install -d $(DESTDIR)$(sbindir)
+        install -m 755 -p $(TARGETS) $(DESTDIR)$(sbindir)