Merge branch 'linus' into sched/core, to resolve conflicts

Conflicts:
	kernel/sysctl.c

Signed-off-by: Ingo Molnar <mingo@kernel.org>

27 files changed, 2599 insertions, 42 deletions

diff --git a/tools/Makefile b/tools/Makefile
index 927cd46d36dc..feec3ad5fd09 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -3,6 +3,7 @@ include scripts/Makefile.include
 help:
 	@echo 'Possible targets:'
 	@echo ''
+	@echo '  acpi       - ACPI tools'
 	@echo '  cgroup     - cgroup tools'
 	@echo '  cpupower   - a tool for all things x86 CPU power'
 	@echo '  firewire   - the userspace part of nosy, an IEEE-1394 traffic sniffer'
@@ -33,6 +34,9 @@ help:
 	@echo '    the respective build directory.'
 	@echo '  clean: a summary clean target to clean _all_ folders'
 
+acpi: FORCE
+	$(call descend,power/$@)
+
 cpupower: FORCE
 	$(call descend,power/$@)
 
@@ -54,6 +58,9 @@ turbostat x86_energy_perf_policy: FORCE
 tmon: FORCE
 	$(call descend,thermal/$@)
 
+acpi_install:
+	$(call descend,power/$(@:_install=),install)
+
 cpupower_install:
 	$(call descend,power/$(@:_install=),install)
 
@@ -69,11 +76,14 @@ turbostat_install x86_energy_perf_policy_install:
 tmon_install:
 	$(call descend,thermal/$(@:_install=),install)
 
-install: cgroup_install cpupower_install firewire_install lguest_install \
+install: acpi_install cgroup_install cpupower_install firewire_install lguest_install \
 		perf_install selftests_install turbostat_install usb_install \
 		virtio_install vm_install net_install x86_energy_perf_policy_install \
 	tmon
 
+acpi_clean:
+	$(call descend,power/acpi,clean)
+
 cpupower_clean:
 	$(call descend,power/cpupower,clean)
 
@@ -95,8 +105,8 @@ turbostat_clean x86_energy_perf_policy_clean:
 tmon_clean:
 	$(call descend,thermal/tmon,clean)
 
-clean: cgroup_clean cpupower_clean firewire_clean lguest_clean perf_clean \
-		selftests_clean turbostat_clean usb_clean virtio_clean \
+clean: acpi_clean cgroup_clean cpupower_clean firewire_clean lguest_clean \
+		perf_clean selftests_clean turbostat_clean usb_clean virtio_clean \
 		vm_clean net_clean x86_energy_perf_policy_clean tmon_clean
 
 .PHONY: FORCE
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index b8d6d541d854..4088b816a3ee 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -26,7 +26,6 @@
 #include <sys/socket.h>
 #include <sys/poll.h>
 #include <sys/utsname.h>
-#include <linux/types.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <unistd.h>
diff --git a/tools/hv/hv_vss_daemon.c b/tools/hv/hv_vss_daemon.c
index 8bcb04096eb2..520de3304571 100644
--- a/tools/hv/hv_vss_daemon.c
+++ b/tools/hv/hv_vss_daemon.c
@@ -22,7 +22,6 @@
 #include <sys/socket.h>
 #include <sys/poll.h>
 #include <sys/ioctl.h>
-#include <linux/types.h>
 #include <fcntl.h>
 #include <stdio.h>
 #include <mntent.h>
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 56d52a33a3df..005c9cc06935 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -63,7 +63,7 @@ endif
 endif
 
 ifeq ($(set_plugin_dir),1)
-PLUGIN_DIR = -DPLUGIN_DIR="$(DESTDIR)/$(plugin_dir)"
+PLUGIN_DIR = -DPLUGIN_DIR="$(plugin_dir)"
 PLUGIN_DIR_SQ = '$(subst ','\'',$(PLUGIN_DIR))'
 endif
 
diff --git a/tools/net/Makefile b/tools/net/Makefile
index b4444d53b73f..004cd74734b6 100644
--- a/tools/net/Makefile
+++ b/tools/net/Makefile
@@ -1,15 +1,34 @@
 prefix = /usr
 
 CC = gcc
+LEX = flex
+YACC = bison
 
-all : bpf_jit_disasm
+%.yacc.c: %.y
+	$(YACC) -o $@ -d $<
+
+%.lex.c: %.l
+	$(LEX) -o $@ $<
+
+all : bpf_jit_disasm bpf_dbg bpf_asm
 
 bpf_jit_disasm : CFLAGS = -Wall -O2
 bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl
 bpf_jit_disasm : bpf_jit_disasm.o
 
+bpf_dbg : CFLAGS = -Wall -O2
+bpf_dbg : LDLIBS = -lreadline
+bpf_dbg : bpf_dbg.o
+
+bpf_asm : CFLAGS = -Wall -O2 -I.
+bpf_asm : LDLIBS =
+bpf_asm : bpf_asm.o bpf_exp.yacc.o bpf_exp.lex.o
+bpf_exp.lex.o : bpf_exp.yacc.c
+
 clean :
-	rm -rf *.o bpf_jit_disasm
+	rm -rf *.o bpf_jit_disasm bpf_dbg bpf_asm bpf_exp.yacc.* bpf_exp.lex.*
 
 install :
 	install bpf_jit_disasm $(prefix)/bin/bpf_jit_disasm
+	install bpf_dbg $(prefix)/bin/bpf_dbg
+	install bpf_asm $(prefix)/bin/bpf_asm
diff --git a/tools/net/bpf_asm.c b/tools/net/bpf_asm.c
new file mode 100644
index 000000000000..c15aef097b04
--- /dev/null
+++ b/tools/net/bpf_asm.c
@@ -0,0 +1,52 @@
+/*
+ * Minimal BPF assembler
+ *
+ * Instead of libpcap high-level filter expressions, it can be quite
+ * useful to define filters in low-level BPF assembler (that is kept
+ * close to Steven McCanne and Van Jacobson's original BPF paper).
+ * In particular for BPF JIT implementors, JIT security auditors, or
+ * just for defining BPF expressions that contain extensions which are
+ * not supported by compilers.
+ *
+ * How to get into it:
+ *
+ * 1) read Documentation/networking/filter.txt
+ * 2) Run `bpf_asm [-c] <filter-prog file>` to translate into binary
+ *    blob that is loadable with xt_bpf, cls_bpf et al. Note: -c will
+ *    pretty print a C-like construct.
+ *
+ * Copyright 2013 Daniel Borkmann <borkmann@redhat.com>
+ * Licensed under the GNU General Public License, version 2.0 (GPLv2)
+ */
+
+#include <stdbool.h>
+#include <stdio.h>
+#include <string.h>
+
+extern void bpf_asm_compile(FILE *fp, bool cstyle);
+
+int main(int argc, char **argv)
+{
+	FILE *fp = stdin;
+	bool cstyle = false;
+	int i;
+
+	for (i = 1; i < argc; i++) {
+		if (!strncmp("-c", argv[i], 2)) {
+			cstyle = true;
+			continue;
+		}
+
+		fp = fopen(argv[i], "r");
+		if (!fp) {
+			fp = stdin;
+			continue;
+		}
+
+		break;
+	}
+
+	bpf_asm_compile(fp, cstyle);
+
+	return 0;
+}
diff --git a/tools/net/bpf_dbg.c b/tools/net/bpf_dbg.c
new file mode 100644
index 000000000000..65dc757f7f7b
--- /dev/null
+++ b/tools/net/bpf_dbg.c
@@ -0,0 +1,1404 @@
+/*
+ * Minimal BPF debugger
+ *
+ * Minimal BPF debugger that mimics the kernel's engine (w/o extensions)
+ * and allows for single stepping through selected packets from a pcap
+ * with a provided user filter in order to facilitate verification of a
+ * BPF program. Besides others, this is useful to verify BPF programs
+ * before attaching to a live system, and can be used in socket filters,
+ * cls_bpf, xt_bpf, team driver and e.g. PTP code; in particular when a
+ * single more complex BPF program is being used. Reasons for a more
+ * complex BPF program are likely primarily to optimize execution time
+ * for making a verdict when multiple simple BPF programs are combined
+ * into one in order to prevent parsing same headers multiple times.
+ *
+ * More on how to debug BPF opcodes see Documentation/networking/filter.txt
+ * which is the main document on BPF. Mini howto for getting started:
+ *
+ *  1) `./bpf_dbg` to enter the shell (shell cmds denoted with '>'):
+ *  2) > load bpf 6,40 0 0 12,21 0 3 20... (output from `bpf_asm` or
+ *     `tcpdump -iem1 -ddd port 22 | tr '\n' ','` to load as filter)
+ *  3) > load pcap foo.pcap
+ *  4) > run <n>/disassemble/dump/quit (self-explanatory)
+ *  5) > breakpoint 2 (sets bp at loaded BPF insns 2, do `run` then;
+ *       multiple bps can be set, of course, a call to `breakpoint`
+ *       w/o args shows currently loaded bps, `breakpoint reset` for
+ *       resetting all breakpoints)
+ *  6) > select 3 (`run` etc will start from the 3rd packet in the pcap)
+ *  7) > step [-<n>, +<n>] (performs single stepping through the BPF)
+ *
+ * Copyright 2013 Daniel Borkmann <borkmann@redhat.com>
+ * Licensed under the GNU General Public License, version 2.0 (GPLv2)
+ */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <ctype.h>
+#include <stdbool.h>
+#include <stdarg.h>
+#include <setjmp.h>
+#include <linux/filter.h>
+#include <linux/if_packet.h>
+#include <readline/readline.h>
+#include <readline/history.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <signal.h>
+#include <arpa/inet.h>
+#include <net/ethernet.h>
+
+#define TCPDUMP_MAGIC	0xa1b2c3d4
+
+#define BPF_LDX_B	(BPF_LDX | BPF_B)
+#define BPF_LDX_W	(BPF_LDX | BPF_W)
+#define BPF_JMP_JA	(BPF_JMP | BPF_JA)
+#define BPF_JMP_JEQ	(BPF_JMP | BPF_JEQ)
+#define BPF_JMP_JGT	(BPF_JMP | BPF_JGT)
+#define BPF_JMP_JGE	(BPF_JMP | BPF_JGE)
+#define BPF_JMP_JSET	(BPF_JMP | BPF_JSET)
+#define BPF_ALU_ADD	(BPF_ALU | BPF_ADD)
+#define BPF_ALU_SUB	(BPF_ALU | BPF_SUB)
+#define BPF_ALU_MUL	(BPF_ALU | BPF_MUL)
+#define BPF_ALU_DIV	(BPF_ALU | BPF_DIV)
+#define BPF_ALU_MOD	(BPF_ALU | BPF_MOD)
+#define BPF_ALU_NEG	(BPF_ALU | BPF_NEG)
+#define BPF_ALU_AND	(BPF_ALU | BPF_AND)
+#define BPF_ALU_OR	(BPF_ALU | BPF_OR)
+#define BPF_ALU_XOR	(BPF_ALU | BPF_XOR)
+#define BPF_ALU_LSH	(BPF_ALU | BPF_LSH)
+#define BPF_ALU_RSH	(BPF_ALU | BPF_RSH)
+#define BPF_MISC_TAX	(BPF_MISC | BPF_TAX)
+#define BPF_MISC_TXA	(BPF_MISC | BPF_TXA)
+#define BPF_LD_B	(BPF_LD | BPF_B)
+#define BPF_LD_H	(BPF_LD | BPF_H)
+#define BPF_LD_W	(BPF_LD | BPF_W)
+
+#ifndef array_size
+# define array_size(x)	(sizeof(x) / sizeof((x)[0]))
+#endif
+
+#ifndef __check_format_printf
+# define __check_format_printf(pos_fmtstr, pos_fmtargs) \
+	__attribute__ ((format (printf, (pos_fmtstr), (pos_fmtargs))))
+#endif
+
+#define CMD(_name, _func) { .name = _name, .func = _func, }
+#define OP(_op, _name)      [_op] = _name
+
+enum {
+	CMD_OK,
+	CMD_ERR,
+	CMD_EX,
+};
+
+struct shell_cmd {
+	const char *name;
+	int (*func)(char *args);
+};
+
+struct pcap_filehdr {
+	uint32_t magic;
+	uint16_t version_major;
+	uint16_t version_minor;
+	int32_t  thiszone;
+	uint32_t sigfigs;
+	uint32_t snaplen;
+	uint32_t linktype;
+};
+
+struct pcap_timeval {
+	int32_t tv_sec;
+	int32_t tv_usec;
+};
+
+struct pcap_pkthdr {
+	struct pcap_timeval ts;
+	uint32_t caplen;
+	uint32_t len;
+};
+
+struct bpf_regs {
+	uint32_t A;
+	uint32_t X;
+	uint32_t M[BPF_MEMWORDS];
+	uint32_t R;
+	bool     Rs;
+	uint16_t Pc;
+};
+
+static struct sock_filter bpf_image[BPF_MAXINSNS + 1];
+static unsigned int bpf_prog_len = 0;
+
+static int bpf_breakpoints[64];
+static struct bpf_regs bpf_regs[BPF_MAXINSNS + 1];
+static struct bpf_regs bpf_curr;
+static unsigned int bpf_regs_len = 0;
+
+static int pcap_fd = -1;
+static unsigned int pcap_packet = 0;
+static size_t pcap_map_size = 0;
+static char *pcap_ptr_va_start, *pcap_ptr_va_curr;
+
+static const char * const op_table[] = {
+	OP(BPF_ST, "st"),
+	OP(BPF_STX, "stx"),
+	OP(BPF_LD_B, "ldb"),
+	OP(BPF_LD_H, "ldh"),
+	OP(BPF_LD_W, "ld"),
+	OP(BPF_LDX, "ldx"),
+	OP(BPF_LDX_B, "ldxb"),
+	OP(BPF_JMP_JA, "ja"),
+	OP(BPF_JMP_JEQ, "jeq"),
+	OP(BPF_JMP_JGT, "jgt"),
+	OP(BPF_JMP_JGE, "jge"),
+	OP(BPF_JMP_JSET, "jset"),
+	OP(BPF_ALU_ADD, "add"),
+	OP(BPF_ALU_SUB, "sub"),
+	OP(BPF_ALU_MUL, "mul"),
+	OP(BPF_ALU_DIV, "div"),
+	OP(BPF_ALU_MOD, "mod"),
+	OP(BPF_ALU_NEG, "neg"),
+	OP(BPF_ALU_AND, "and"),
+	OP(BPF_ALU_OR, "or"),
+	OP(BPF_ALU_XOR, "xor"),
+	OP(BPF_ALU_LSH, "lsh"),
+	OP(BPF_ALU_RSH, "rsh"),
+	OP(BPF_MISC_TAX, "tax"),
+	OP(BPF_MISC_TXA, "txa"),
+	OP(BPF_RET, "ret"),
+};
+
+static __check_format_printf(1, 2) int rl_printf(const char *fmt, ...)
+{
+	int ret;
+	va_list vl;
+
+	va_start(vl, fmt);
+	ret = vfprintf(rl_outstream, fmt, vl);
+	va_end(vl);
+
+	return ret;
+}
+
+static int matches(const char *cmd, const char *pattern)
+{
+	int len = strlen(cmd);
+
+	if (len > strlen(pattern))
+		return -1;
+
+	return memcmp(pattern, cmd, len);
+}
+
+static void hex_dump(const uint8_t *buf, size_t len)
+{
+	int i;
+
+	rl_printf("%3u: ", 0);
+	for (i = 0; i < len; i++) {
+		if (i && !(i % 16))
+			rl_printf("\n%3u: ", i);
+		rl_printf("%02x ", buf[i]);
+	}
+	rl_printf("\n");
+}
+
+static bool bpf_prog_loaded(void)
+{
+	if (bpf_prog_len == 0)
+		rl_printf("no bpf program loaded!\n");
+
+	return bpf_prog_len > 0;
+}
+
+static void bpf_disasm(const struct sock_filter f, unsigned int i)
+{
+	const char *op, *fmt;
+	int val = f.k;
+	char buf[256];
+
+	switch (f.code) {
+	case BPF_RET | BPF_K:
+		op = op_table[BPF_RET];
+		fmt = "#%#x";
+		break;
+	case BPF_RET | BPF_A:
+		op = op_table[BPF_RET];
+		fmt = "a";
+		break;
+	case BPF_RET | BPF_X:
+		op = op_table[BPF_RET];
+		fmt = "x";
+		break;
+	case BPF_MISC_TAX:
+		op = op_table[BPF_MISC_TAX];
+		fmt = "";
+		break;
+	case BPF_MISC_TXA:
+		op = op_table[BPF_MISC_TXA];
+		fmt = "";
+		break;
+	case BPF_ST:
+		op = op_table[BPF_ST];
+		fmt = "M[%d]";
+		break;
+	case BPF_STX:
+		op = op_table[BPF_STX];
+		fmt = "M[%d]";
+		break;
+	case BPF_LD_W | BPF_ABS:
+		op = op_table[BPF_LD_W];
+		fmt = "[%d]";
+		break;
+	case BPF_LD_H | BPF_ABS:
+		op = op_table[BPF_LD_H];
+		fmt = "[%d]";
+		break;
+	case BPF_LD_B | BPF_ABS:
+		op = op_table[BPF_LD_B];
+		fmt = "[%d]";
+		break;
+	case BPF_LD_W | BPF_LEN:
+		op = op_table[BPF_LD_W];
+		fmt = "#len";
+		break;
+	case BPF_LD_W | BPF_IND:
+		op = op_table[BPF_LD_W];
+		fmt = "[x+%d]";
+		break;
+	case BPF_LD_H | BPF_IND:
+		op = op_table[BPF_LD_H];
+		fmt = "[x+%d]";
+		break;
+	case BPF_LD_B | BPF_IND:
+		op = op_table[BPF_LD_B];
+		fmt = "[x+%d]";
+		break;
+	case BPF_LD | BPF_IMM:
+		op = op_table[BPF_LD_W];
+		fmt = "#%#x";
+		break;
+	case BPF_LDX | BPF_IMM:
+		op = op_table[BPF_LDX];
+		fmt = "#%#x";
+		break;
+	case BPF_LDX_B | BPF_MSH:
+		op = op_table[BPF_LDX_B];
+		fmt = "4*([%d]&0xf)";
+		break;
+	case BPF_LD | BPF_MEM:
+		op = op_table[BPF_LD_W];
+		fmt = "M[%d]";
+		break;
+	case BPF_LDX | BPF_MEM:
+		op = op_table[BPF_LDX];
+		fmt = "M[%d]";
+		break;
+	case BPF_JMP_JA:
+		op = op_table[BPF_JMP_JA];
+		fmt = "%d";
+		val = i + 1 + f.k;
+		break;
+	case BPF_JMP_JGT | BPF_X:
+		op = op_table[BPF_JMP_JGT];
+		fmt = "x";
+		break;
+	case BPF_JMP_JGT | BPF_K:
+		op = op_table[BPF_JMP_JGT];
+		fmt = "#%#x";
+		break;
+	case BPF_JMP_JGE | BPF_X:
+		op = op_table[BPF_JMP_JGE];
+		fmt = "x";
+		break;
+	case BPF_JMP_JGE | BPF_K:
+		op = op_table[BPF_JMP_JGE];
+		fmt = "#%#x";
+		break;
+	case BPF_JMP_JEQ | BPF_X:
+		op = op_table[BPF_JMP_JEQ];
+		fmt = "x";
+		break;
+	case BPF_JMP_JEQ | BPF_K:
+		op = op_table[BPF_JMP_JEQ];
+		fmt = "#%#x";
+		break;
+	case BPF_JMP_JSET | BPF_X:
+		op = op_table[BPF_JMP_JSET];
+		fmt = "x";
+		break;
+	case BPF_JMP_JSET | BPF_K:
+		op = op_table[BPF_JMP_JSET];
+		fmt = "#%#x";
+		break;
+	case BPF_ALU_NEG:
+		op = op_table[BPF_ALU_NEG];
+		fmt = "";
+		break;
+	case BPF_ALU_LSH | BPF_X:
+		op = op_table[BPF_ALU_LSH];
+		fmt = "x";
+		break;
+	case BPF_ALU_LSH | BPF_K:
+		op = op_table[BPF_ALU_LSH];
+		fmt = "#%d";
+		break;
+	case BPF_ALU_RSH | BPF_X:
+		op = op_table[BPF_ALU_RSH];
+		fmt = "x";
+		break;
+	case BPF_ALU_RSH | BPF_K:
+		op = op_table[BPF_ALU_RSH];
+		fmt = "#%d";
+		break;
+	case BPF_ALU_ADD | BPF_X:
+		op = op_table[BPF_ALU_ADD];
+		fmt = "x";
+		break;
+	case BPF_ALU_ADD | BPF_K:
+		op = op_table[BPF_ALU_ADD];
+		fmt = "#%d";
+		break;
+	case BPF_ALU_SUB | BPF_X:
+		op = op_table[BPF_ALU_SUB];
+		fmt = "x";
+		break;
+	case BPF_ALU_SUB | BPF_K:
+		op = op_table[BPF_ALU_SUB];
+		fmt = "#%d";
+		break;
+	case BPF_ALU_MUL | BPF_X:
+		op = op_table[BPF_ALU_MUL];
+		fmt = "x";
+		break;
+	case BPF_ALU_MUL | BPF_K:
+		op = op_table[BPF_ALU_MUL];
+		fmt = "#%d";
+		break;
+	case BPF_ALU_DIV | BPF_X:
+		op = op_table[BPF_ALU_DIV];
+		fmt = "x";
+		break;
+	case BPF_ALU_DIV | BPF_K:
+		op = op_table[BPF_ALU_DIV];
+		fmt = "#%d";
+		break;
+	case BPF_ALU_MOD | BPF_X:
+		op = op_table[BPF_ALU_MOD];
+		fmt = "x";
+		break;
+	case BPF_ALU_MOD | BPF_K:
+		op = op_table[BPF_ALU_MOD];
+		fmt = "#%d";
+		break;
+	case BPF_ALU_AND | BPF_X:
+		op = op_table[BPF_ALU_AND];
+		fmt = "x";
+		break;
+	case BPF_ALU_AND | BPF_K:
+		op = op_table[BPF_ALU_AND];
+		fmt = "#%#x";
+		break;
+	case BPF_ALU_OR | BPF_X:
+		op = op_table[BPF_ALU_OR];
+		fmt = "x";
+		break;
+	case BPF_ALU_OR | BPF_K:
+		op = op_table[BPF_ALU_OR];
+		fmt = "#%#x";
+		break;
+	case BPF_ALU_XOR | BPF_X:
+		op = op_table[BPF_ALU_XOR];
+		fmt = "x";
+		break;
+	case BPF_ALU_XOR | BPF_K:
+		op = op_table[BPF_ALU_XOR];
+		fmt = "#%#x";
+		break;
+	default:
+		op = "nosup";
+		fmt = "%#x";
+		val = f.code;
+		break;
+	}
+
+	memset(buf, 0, sizeof(buf));
+	snprintf(buf, sizeof(buf), fmt, val);
+	buf[sizeof(buf) - 1] = 0;
+
+	if ((BPF_CLASS(f.code) == BPF_JMP && BPF_OP(f.code) != BPF_JA))
+		rl_printf("l%d:\t%s %s, l%d, l%d\n", i, op, buf,
+			  i + 1 + f.jt, i + 1 + f.jf);
+	else
+		rl_printf("l%d:\t%s %s\n", i, op, buf);
+}
+
+static void bpf_dump_curr(struct bpf_regs *r, struct sock_filter *f)
+{
+	int i, m = 0;
+
+	rl_printf("pc:       [%u]\n", r->Pc);
+	rl_printf("code:     [%u] jt[%u] jf[%u] k[%u]\n",
+		  f->code, f->jt, f->jf, f->k);
+	rl_printf("curr:     ");
+	bpf_disasm(*f, r->Pc);
+
+	if (f->jt || f->jf) {
+		rl_printf("jt:       ");
+		bpf_disasm(*(f + f->jt + 1), r->Pc + f->jt + 1);
+		rl_printf("jf:       ");
+		bpf_disasm(*(f + f->jf + 1), r->Pc + f->jf + 1);
+	}
+
+	rl_printf("A:        [%#08x][%u]\n", r->A, r->A);
+	rl_printf("X:        [%#08x][%u]\n", r->X, r->X);
+	if (r->Rs)
+		rl_printf("ret:      [%#08x][%u]!\n", r->R, r->R);
+
+	for (i = 0; i < BPF_MEMWORDS; i++) {
+		if (r->M[i]) {
+			m++;
+			rl_printf("M[%d]: [%#08x][%u]\n", i, r->M[i], r->M[i]);
+		}
+	}
+	if (m == 0)
+		rl_printf("M[0,%d]:  [%#08x][%u]\n", BPF_MEMWORDS - 1, 0, 0);
+}
+
+static void bpf_dump_pkt(uint8_t *pkt, uint32_t pkt_caplen, uint32_t pkt_len)
+{
+	if (pkt_caplen != pkt_len)
+		rl_printf("cap: %u, len: %u\n", pkt_caplen, pkt_len);
+	else
+		rl_printf("len: %u\n", pkt_len);
+
+	hex_dump(pkt, pkt_caplen);
+}
+
+static void bpf_disasm_all(const struct sock_filter *f, unsigned int len)
+{
+	unsigned int i;
+
+	for (i = 0; i < len; i++)
+		bpf_disasm(f[i], i);
+}
+
+static void bpf_dump_all(const struct sock_filter *f, unsigned int len)
+{
+	unsigned int i;
+
+	rl_printf("/* { op, jt, jf, k }, */\n");
+	for (i = 0; i < len; i++)
+		rl_printf("{ %#04x, %2u, %2u, %#010x },\n",
+			  f[i].code, f[i].jt, f[i].jf, f[i].k);
+}
+
+static bool bpf_runnable(struct sock_filter *f, unsigned int len)
+{
+	int sock, ret, i;
+	struct sock_fprog bpf = {
+		.filter = f,
+		.len = len,
+	};
+
+	sock = socket(AF_INET, SOCK_DGRAM, 0);
+	if (sock < 0) {
+		rl_printf("cannot open socket!\n");
+		return false;
+	}
+	ret = setsockopt(sock, SOL_SOCKET, SO_ATTACH_FILTER, &bpf, sizeof(bpf));
+	close(sock);
+	if (ret < 0) {
+		rl_printf("program not allowed to run by kernel!\n");
+		return false;
+	}
+	for (i = 0; i < len; i++) {
+		if (BPF_CLASS(f[i].code) == BPF_LD &&
+		    f[i].k > SKF_AD_OFF) {
+			rl_printf("extensions currently not supported!\n");
+			return false;
+		}
+	}
+
+	return true;
+}
+
+static void bpf_reset_breakpoints(void)
+{
+	int i;
+
+	for (i = 0; i < array_size(bpf_breakpoints); i++)
+		bpf_breakpoints[i] = -1;
+}
+
+static void bpf_set_breakpoints(unsigned int where)
+{
+	int i;
+	bool set = false;
+
+	for (i = 0; i < array_size(bpf_breakpoints); i++) {
+		if (bpf_breakpoints[i] == (int) where) {
+			rl_printf("breakpoint already set!\n");
+			set = true;
+			break;
+		}
+
+		if (bpf_breakpoints[i] == -1 && set == false) {
+			bpf_breakpoints[i] = where;
+			set = true;
+		}
+	}
+
+	if (!set)
+		rl_printf("too many breakpoints set, reset first!\n");
+}
+
+static void bpf_dump_breakpoints(void)
+{
+	int i;
+
+	rl_printf("breakpoints: ");
+
+	for (i = 0; i < array_size(bpf_breakpoints); i++) {
+		if (bpf_breakpoints[i] < 0)
+			continue;
+		rl_printf("%d ", bpf_breakpoints[i]);
+	}
+
+	rl_printf("\n");
+}
+
+static void bpf_reset(void)
+{
+	bpf_regs_len = 0;
+
+	memset(bpf_regs, 0, sizeof(bpf_regs));
+	memset(&bpf_curr, 0, sizeof(bpf_curr));
+}
+
+static void bpf_safe_regs(void)
+{
+	memcpy(&bpf_regs[bpf_regs_len++], &bpf_curr, sizeof(bpf_curr));
+}
+
+static bool bpf_restore_regs(int off)
+{
+	unsigned int index = bpf_regs_len - 1 + off;
+
+	if (index == 0) {
+		bpf_reset();
+		return true;
+	} else if (index < bpf_regs_len) {
+		memcpy(&bpf_curr, &bpf_regs[index], sizeof(bpf_curr));
+		bpf_regs_len = index;
+		return true;
+	} else {
+		rl_printf("reached bottom of register history stack!\n");
+		return false;
+	}
+}
+
+static uint32_t extract_u32(uint8_t *pkt, uint32_t off)
+{
+	uint32_t r;
+
+	memcpy(&r, &pkt[off], sizeof(r));
+
+	return ntohl(r);
+}
+
+static uint16_t extract_u16(uint8_t *pkt, uint32_t off)
+{
+	uint16_t r;
+
+	memcpy(&r, &pkt[off], sizeof(r));
+
+	return ntohs(r);
+}
+
+static uint8_t extract_u8(uint8_t *pkt, uint32_t off)
+{
+	return pkt[off];
+}
+
+static void set_return(struct bpf_regs *r)
+{
+	r->R = 0;
+	r->Rs = true;
+}
+
+static void bpf_single_step(struct bpf_regs *r, struct sock_filter *f,
+			    uint8_t *pkt, uint32_t pkt_caplen,
+			    uint32_t pkt_len)
+{
+	uint32_t K = f->k;
+	int d;
+
+	switch (f->code) {
+	case BPF_RET | BPF_K:
+		r->R = K;
+		r->Rs = true;
+		break;
+	case BPF_RET | BPF_A:
+		r->R = r->A;
+		r->Rs = true;
+		break;
+	case BPF_RET | BPF_X:
+		r->R = r->X;
+		r->Rs = true;
+		break;
+	case BPF_MISC_TAX:
+		r->X = r->A;
+		break;
+	case BPF_MISC_TXA:
+		r->A = r->X;
+		break;
+	case BPF_ST:
+		r->M[K] = r->A;
+		break;
+	case BPF_STX:
+		r->M[K] = r->X;
+		break;
+	case BPF_LD_W | BPF_ABS:
+		d = pkt_caplen - K;
+		if (d >= sizeof(uint32_t))
+			r->A = extract_u32(pkt, K);
+		else
+			set_return(r);
+		break;
+	case BPF_LD_H | BPF_ABS:
+		d = pkt_caplen - K;
+		if (d >= sizeof(uint16_t))
+			r->A = extract_u16(pkt, K);
+		else
+			set_return(r);
+		break;
+	case BPF_LD_B | BPF_ABS:
+		d = pkt_caplen - K;
+		if (d >= sizeof(uint8_t))
+			r->A = extract_u8(pkt, K);
+		else
+			set_return(r);
+		break;
+	case BPF_LD_W | BPF_IND:
+		d = pkt_caplen - (r->X + K);
+		if (d >= sizeof(uint32_t))
+			r->A = extract_u32(pkt, r->X + K);
+		break;
+	case BPF_LD_H | BPF_IND:
+		d = pkt_caplen - (r->X + K);
+		if (d >= sizeof(uint16_t))
+			r->A = extract_u16(pkt, r->X + K);
+		else
+			set_return(r);
+		break;
+	case BPF_LD_B | BPF_IND:
+		d = pkt_caplen - (r->X + K);
+		if (d >= sizeof(uint8_t))
+			r->A = extract_u8(pkt, r->X + K);
+		else
+			set_return(r);
+		break;
+	case BPF_LDX_B | BPF_MSH:
+		d = pkt_caplen - K;
+		if (d >= sizeof(uint8_t)) {
+			r->X = extract_u8(pkt, K);
+			r->X = (r->X & 0xf) << 2;
+		} else
+			set_return(r);
+		break;
+	case BPF_LD_W | BPF_LEN:
+		r->A = pkt_len;
+		break;
+	case BPF_LDX_W | BPF_LEN:
+		r->A = pkt_len;
+		break;
+	case BPF_LD | BPF_IMM:
+		r->A = K;
+		break;
+	case BPF_LDX | BPF_IMM:
+		r->X = K;
+		break;
+	case BPF_LD | BPF_MEM:
+		r->A = r->M[K];
+		break;
+	case BPF_LDX | BPF_MEM:
+		r->X = r->M[K];
+		break;
+	case BPF_JMP_JA:
+		r->Pc += K;
+		break;
+	case BPF_JMP_JGT | BPF_X:
+		r->Pc += r->A > r->X ? f->jt : f->jf;
+		break;
+	case BPF_JMP_JGT | BPF_K:
+		r->Pc += r->A > K ? f->jt : f->jf;
+		break;
+	case BPF_JMP_JGE | BPF_X:
+		r->Pc += r->A >= r->X ? f->jt : f->jf;
+		break;
+	case BPF_JMP_JGE | BPF_K:
+		r->Pc += r->A >= K ? f->jt : f->jf;
+		break;
+	case BPF_JMP_JEQ | BPF_X:
+		r->Pc += r->A == r->X ? f->jt : f->jf;
+		break;
+	case BPF_JMP_JEQ | BPF_K:
+		r->Pc += r->A == K ? f->jt : f->jf;
+		break;
+	case BPF_JMP_JSET | BPF_X:
+		r->Pc += r->A & r->X ? f->jt : f->jf;
+		break;
+	case BPF_JMP_JSET | BPF_K:
+		r->Pc += r->A & K ? f->jt : f->jf;
+		break;
+	case BPF_ALU_NEG:
+		r->A = -r->A;
+		break;
+	case BPF_ALU_LSH | BPF_X:
+		r->A <<= r->X;
+		break;
+	case BPF_ALU_LSH | BPF_K:
+		r->A <<= K;
+		break;
+	case BPF_ALU_RSH | BPF_X:
+		r->A >>= r->X;
+		break;
+	case BPF_ALU_RSH | BPF_K:
+		r->A >>= K;
+		break;
+	case BPF_ALU_ADD | BPF_X:
+		r->A += r->X;
+		break;
+	case BPF_ALU_ADD | BPF_K:
+		r->A += K;
+		break;
+	case BPF_ALU_SUB | BPF_X:
+		r->A -= r->X;
+		break;
+	case BPF_ALU_SUB | BPF_K:
+		r->A -= K;
+		break;
+	case BPF_ALU_MUL | BPF_X:
+		r->A *= r->X;
+		break;
+	case BPF_ALU_MUL | BPF_K:
+		r->A *= K;
+		break;
+	case BPF_ALU_DIV | BPF_X:
+	case BPF_ALU_MOD | BPF_X:
+		if (r->X == 0) {
+			set_return(r);
+			break;
+		}
+		goto do_div;
+	case BPF_ALU_DIV | BPF_K:
+	case BPF_ALU_MOD | BPF_K:
+		if (K == 0) {
+			set_return(r);
+			break;
+		}
+do_div:
+		switch (f->code) {
+		case BPF_ALU_DIV | BPF_X:
+			r->A /= r->X;
+			break;
+		case BPF_ALU_DIV | BPF_K:
+			r->A /= K;
+			break;
+		case BPF_ALU_MOD | BPF_X:
+			r->A %= r->X;
+			break;
+		case BPF_ALU_MOD | BPF_K:
+			r->A %= K;
+			break;
+		}
+		break;
+	case BPF_ALU_AND | BPF_X:
+		r->A &= r->X;
+		break;
+	case BPF_ALU_AND | BPF_K:
+		r->A &= r->X;
+		break;
+	case BPF_ALU_OR | BPF_X:
+		r->A |= r->X;
+		break;
+	case BPF_ALU_OR | BPF_K:
+		r->A |= K;
+		break;
+	case BPF_ALU_XOR | BPF_X:
+		r->A ^= r->X;
+		break;
+	case BPF_ALU_XOR | BPF_K:
+		r->A ^= K;
+		break;
+	}
+}
+
+static bool bpf_pc_has_breakpoint(uint16_t pc)
+{
+	int i;
+
+	for (i = 0; i < array_size(bpf_breakpoints); i++) {
+		if (bpf_breakpoints[i] < 0)
+			continue;
+		if (bpf_breakpoints[i] == pc)
+			return true;
+	}
+
+	return false;
+}
+
+static bool bpf_handle_breakpoint(struct bpf_regs *r, struct sock_filter *f,
+				  uint8_t *pkt, uint32_t pkt_caplen,
+				  uint32_t pkt_len)
+{
+	rl_printf("-- register dump --\n");
+	bpf_dump_curr(r, &f[r->Pc]);
+	rl_printf("-- packet dump --\n");
+	bpf_dump_pkt(pkt, pkt_caplen, pkt_len);
+	rl_printf("(breakpoint)\n");
+	return true;
+}
+
+static int bpf_run_all(struct sock_filter *f, uint16_t bpf_len, uint8_t *pkt,
+		       uint32_t pkt_caplen, uint32_t pkt_len)
+{
+	bool stop = false;
+
+	while (bpf_curr.Rs == false && stop == false) {
+		bpf_safe_regs();
+
+		if (bpf_pc_has_breakpoint(bpf_curr.Pc))
+			stop = bpf_handle_breakpoint(&bpf_curr, f, pkt,
+						     pkt_caplen, pkt_len);
+
+		bpf_single_step(&bpf_curr, &f[bpf_curr.Pc], pkt, pkt_caplen,
+				pkt_len);
+		bpf_curr.Pc++;
+	}
+
+	return stop ? -1 : bpf_curr.R;
+}
+
+static int bpf_run_stepping(struct sock_filter *f, uint16_t bpf_len,
+			    uint8_t *pkt, uint32_t pkt_caplen,
+			    uint32_t pkt_len, int next)
+{
+	bool stop = false;
+	int i = 1;
+
+	while (bpf_curr.Rs == false && stop == false) {
+		bpf_safe_regs();
+
+		if (i++ == next)
+			stop = bpf_handle_breakpoint(&bpf_curr, f, pkt,
+						     pkt_caplen, pkt_len);
+
+		bpf_single_step(&bpf_curr, &f[bpf_curr.Pc], pkt, pkt_caplen,
+				pkt_len);
+		bpf_curr.Pc++;
+	}
+
+	return stop ? -1 : bpf_curr.R;
+}
+
+static bool pcap_loaded(void)
+{
+	if (pcap_fd < 0)
+		rl_printf("no pcap file loaded!\n");
+
+	return pcap_fd >= 0;
+}
+
+static struct pcap_pkthdr *pcap_curr_pkt(void)
+{
+	return (void *) pcap_ptr_va_curr;
+}
+
+static bool pcap_next_pkt(void)
+{
+	struct pcap_pkthdr *hdr = pcap_curr_pkt();
+
+	if (pcap_ptr_va_curr + sizeof(*hdr) -
+	    pcap_ptr_va_start >= pcap_map_size)
+		return false;
+	if (hdr->caplen == 0 || hdr->len == 0 || hdr->caplen > hdr->len)
+		return false;
+	if (pcap_ptr_va_curr + sizeof(*hdr) + hdr->caplen -
+	    pcap_ptr_va_start >= pcap_map_size)
+		return false;
+
+	pcap_ptr_va_curr += (sizeof(*hdr) + hdr->caplen);
+	return true;
+}
+
+static void pcap_reset_pkt(void)
+{
+	pcap_ptr_va_curr = pcap_ptr_va_start + sizeof(struct pcap_filehdr);
+}
+
+static int try_load_pcap(const char *file)
+{
+	struct pcap_filehdr *hdr;
+	struct stat sb;
+	int ret;
+
+	pcap_fd = open(file, O_RDONLY);
+	if (pcap_fd < 0) {
+		rl_printf("cannot open pcap [%s]!\n", strerror(errno));
+		return CMD_ERR;
+	}
+
+	ret = fstat(pcap_fd, &sb);
+	if (ret < 0) {
+		rl_printf("cannot fstat pcap file!\n");
+		return CMD_ERR;
+	}
+
+	if (!S_ISREG(sb.st_mode)) {
+		rl_printf("not a regular pcap file, duh!\n");
+		return CMD_ERR;
+	}
+
+	pcap_map_size = sb.st_size;
+	if (pcap_map_size <= sizeof(struct pcap_filehdr)) {
+		rl_printf("pcap file too small!\n");
+		return CMD_ERR;
+	}
+
+	pcap_ptr_va_start = mmap(NULL, pcap_map_size, PROT_READ,
+				 MAP_SHARED | MAP_LOCKED, pcap_fd, 0);
+	if (pcap_ptr_va_start == MAP_FAILED) {
+		rl_printf("mmap of file failed!");
+		return CMD_ERR;
+	}
+
+	hdr = (void *) pcap_ptr_va_start;
+	if (hdr->magic != TCPDUMP_MAGIC) {
+		rl_printf("wrong pcap magic!\n");
+		return CMD_ERR;
+	}
+
+	pcap_reset_pkt();
+
+	return CMD_OK;
+
+}
+
+static void try_close_pcap(void)
+{
+	if (pcap_fd >= 0) {
+		munmap(pcap_ptr_va_start, pcap_map_size);
+		close(pcap_fd);
+
+		pcap_ptr_va_start = pcap_ptr_va_curr = NULL;
+		pcap_map_size = 0;
+		pcap_packet = 0;
+		pcap_fd = -1;
+	}
+}
+
+static int cmd_load_bpf(char *bpf_string)
+{
+	char sp, *token, separator = ',';
+	unsigned short bpf_len, i = 0;
+	struct sock_filter tmp;
+
+	bpf_prog_len = 0;
+	memset(bpf_image, 0, sizeof(bpf_image));
+
+	if (sscanf(bpf_string, "%hu%c", &bpf_len, &sp) != 2 ||
+	    sp != separator || bpf_len > BPF_MAXINSNS || bpf_len == 0) {
+		rl_printf("syntax error in head length encoding!\n");
+		return CMD_ERR;
+	}
+
+	token = bpf_string;
+	while ((token = strchr(token, separator)) && (++token)[0]) {
+		if (i >= bpf_len) {
+			rl_printf("program exceeds encoded length!\n");
+			return CMD_ERR;
+		}
+
+		if (sscanf(token, "%hu %hhu %hhu %u,",
+			   &tmp.code, &tmp.jt, &tmp.jf, &tmp.k) != 4) {
+			rl_printf("syntax error at instruction %d!\n", i);
+			return CMD_ERR;
+		}
+
+		bpf_image[i].code = tmp.code;
+		bpf_image[i].jt = tmp.jt;
+		bpf_image[i].jf = tmp.jf;
+		bpf_image[i].k = tmp.k;
+
+		i++;
+	}
+
+	if (i != bpf_len) {
+		rl_printf("syntax error exceeding encoded length!\n");
+		return CMD_ERR;
+	} else
+		bpf_prog_len = bpf_len;
+	if (!bpf_runnable(bpf_image, bpf_prog_len))
+		bpf_prog_len = 0;
+
+	return CMD_OK;
+}
+
+static int cmd_load_pcap(char *file)
+{
+	char *file_trim, *tmp;
+
+	file_trim = strtok_r(file, " ", &tmp);
+	if (file_trim == NULL)
+		return CMD_ERR;
+
+	try_close_pcap();
+
+	return try_load_pcap(file_trim);
+}
+
+static int cmd_load(char *arg)
+{
+	char *subcmd, *cont, *tmp = strdup(arg);
+	int ret = CMD_OK;
+
+	subcmd = strtok_r(tmp, " ", &cont);
+	if (subcmd == NULL)
+		goto out;
+	if (matches(subcmd, "bpf") == 0) {
+		bpf_reset();
+		bpf_reset_breakpoints();
+
+		ret = cmd_load_bpf(cont);
+	} else if (matches(subcmd, "pcap") == 0) {
+		ret = cmd_load_pcap(cont);
+	} else {
+out:
+		rl_printf("bpf <code>:  load bpf code\n");
+		rl_printf("pcap <file>: load pcap file\n");
+		ret = CMD_ERR;
+	}
+
+	free(tmp);
+	return ret;
+}
+
+static int cmd_step(char *num)
+{
+	struct pcap_pkthdr *hdr;
+	int steps, ret;
+
+	if (!bpf_prog_loaded() || !pcap_loaded())
+		return CMD_ERR;
+
+	steps = strtol(num, NULL, 10);
+	if (steps == 0 || strlen(num) == 0)
+		steps = 1;
+	if (steps < 0) {
+		if (!bpf_restore_regs(steps))
+			return CMD_ERR;
+		steps = 1;
+	}
+
+	hdr = pcap_curr_pkt();
+	ret = bpf_run_stepping(bpf_image, bpf_prog_len,
+			       (uint8_t *) hdr + sizeof(*hdr),
+			       hdr->caplen, hdr->len, steps);
+	if (ret >= 0 || bpf_curr.Rs) {
+		bpf_reset();
+		if (!pcap_next_pkt()) {
+			rl_printf("(going back to first packet)\n");
+			pcap_reset_pkt();
+		} else {
+			rl_printf("(next packet)\n");
+		}
+	}
+
+	return CMD_OK;
+}
+
+static int cmd_select(char *num)
+{
+	unsigned int which, i;
+	struct pcap_pkthdr *hdr;
+	bool have_next = true;
+
+	if (!pcap_loaded() || strlen(num) == 0)
+		return CMD_ERR;
+
+	which = strtoul(num, NULL, 10);
+	if (which == 0) {
+		rl_printf("packet count starts with 1, clamping!\n");
+		which = 1;
+	}
+
+	pcap_reset_pkt();
+	bpf_reset();
+
+	for (i = 0; i < which && (have_next = pcap_next_pkt()); i++)
+		/* noop */;
+	if (!have_next || (hdr = pcap_curr_pkt()) == NULL) {
+		rl_printf("no packet #%u available!\n", which);
+		pcap_reset_pkt();
+		return CMD_ERR;
+	}
+
+	return CMD_OK;
+}
+
+static int cmd_breakpoint(char *subcmd)
+{
+	if (!bpf_prog_loaded())
+		return CMD_ERR;
+	if (strlen(subcmd) == 0)
+		bpf_dump_breakpoints();
+	else if (matches(subcmd, "reset") == 0)
+		bpf_reset_breakpoints();
+	else {
+		unsigned int where = strtoul(subcmd, NULL, 10);
+
+		if (where < bpf_prog_len) {
+			bpf_set_breakpoints(where);
+			rl_printf("breakpoint at: ");
+			bpf_disasm(bpf_image[where], where);
+		}
+	}
+
+	return CMD_OK;
+}
+
+static int cmd_run(char *num)
+{
+	static uint32_t pass = 0, fail = 0;
+	struct pcap_pkthdr *hdr;
+	bool has_limit = true;
+	int ret, pkts = 0, i = 0;
+
+	if (!bpf_prog_loaded() || !pcap_loaded())
+		return CMD_ERR;
+
+	pkts = strtol(num, NULL, 10);
+	if (pkts == 0 || strlen(num) == 0)
+		has_limit = false;
+
+	do {
+		hdr = pcap_curr_pkt();
+		ret = bpf_run_all(bpf_image, bpf_prog_len,
+				  (uint8_t *) hdr + sizeof(*hdr),
+				  hdr->caplen, hdr->len);
+		if (ret > 0)
+			pass++;
+		else if (ret == 0)
+			fail++;
+		else
+			return CMD_OK;
+		bpf_reset();
+	} while (pcap_next_pkt() && (!has_limit || (has_limit && ++i < pkts)));
+
+	rl_printf("bpf passes:%u fails:%u\n", pass, fail);
+
+	pcap_reset_pkt();
+	bpf_reset();
+
+	pass = fail = 0;
+	return CMD_OK;
+}
+
+static int cmd_disassemble(char *line_string)
+{
+	bool single_line = false;
+	unsigned long line;
+
+	if (!bpf_prog_loaded())
+		return CMD_ERR;
+	if (strlen(line_string) > 0 &&
+	    (line = strtoul(line_string, NULL, 10)) < bpf_prog_len)
+		single_line = true;
+	if (single_line)
+		bpf_disasm(bpf_image[line], line);
+	else
+		bpf_disasm_all(bpf_image, bpf_prog_len);
+
+	return CMD_OK;
+}
+
+static int cmd_dump(char *dontcare)
+{
+	if (!bpf_prog_loaded())
+		return CMD_ERR;
+
+	bpf_dump_all(bpf_image, bpf_prog_len);
+
+	return CMD_OK;
+}
+
+static int cmd_quit(char *dontcare)
+{
+	return CMD_EX;
+}
+
+static const struct shell_cmd cmds[] = {
+	CMD("load",		cmd_load),
+	CMD("select",		cmd_select),
+	CMD("step",		cmd_step),
+	CMD("run",		cmd_run),
+	CMD("breakpoint",	cmd_breakpoint),
+	CMD("disassemble",	cmd_disassemble),
+	CMD("dump",		cmd_dump),
+	CMD("quit",		cmd_quit),
+};
+
+static int execf(char *arg)
+{
+	char *cmd, *cont, *tmp = strdup(arg);
+	int i, ret = 0, len;
+
+	cmd = strtok_r(tmp, " ", &cont);
+	if (cmd == NULL)
+		goto out;
+	len = strlen(cmd);
+	for (i = 0; i < array_size(cmds); i++) {
+		if (len != strlen(cmds[i].name))
+			continue;
+		if (strncmp(cmds[i].name, cmd, len) == 0) {
+			ret = cmds[i].func(cont);
+			break;
+		}
+	}
+out:
+	free(tmp);
+	return ret;
+}
+
+static char *shell_comp_gen(const char *buf, int state)
+{
+	static int list_index, len;
+	const char *name;
+
+	if (!state) {
+		list_index = 0;
+		len = strlen(buf);
+	}
+
+	for (; list_index < array_size(cmds); ) {
+		name = cmds[list_index].name;
+		list_index++;
+
+		if (strncmp(name, buf, len) == 0)
+			return strdup(name);
+	}
+
+	return NULL;
+}
+
+static char **shell_completion(const char *buf, int start, int end)
+{
+	char **matches = NULL;
+
+	if (start == 0)
+		matches = rl_completion_matches(buf, shell_comp_gen);
+
+	return matches;
+}
+
+static void intr_shell(int sig)
+{
+	if (rl_end)
+		rl_kill_line(-1, 0);
+
+	rl_crlf();
+	rl_refresh_line(0, 0);
+	rl_free_line_state();
+}
+
+static void init_shell(FILE *fin, FILE *fout)
+{
+	char file[128];
+
+	memset(file, 0, sizeof(file));
+	snprintf(file, sizeof(file) - 1,
+		 "%s/.bpf_dbg_history", getenv("HOME"));
+
+	read_history(file);
+
+	memset(file, 0, sizeof(file));
+	snprintf(file, sizeof(file) - 1,
+		 "%s/.bpf_dbg_init", getenv("HOME"));
+
+	rl_instream = fin;
+	rl_outstream = fout;
+
+	rl_readline_name = "bpf_dbg";
+	rl_terminal_name = getenv("TERM");
+
+	rl_catch_signals = 0;
+	rl_catch_sigwinch = 1;
+
+	rl_attempted_completion_function = shell_completion;
+
+	rl_bind_key('\t', rl_complete);
+
+	rl_bind_key_in_map('\t', rl_complete, emacs_meta_keymap);
+	rl_bind_key_in_map('\033', rl_complete, emacs_meta_keymap);
+
+	rl_read_init_file(file);
+	rl_prep_terminal(0);
+	rl_set_signals();
+
+	signal(SIGINT, intr_shell);
+}
+
+static void exit_shell(void)
+{
+	char file[128];
+
+	memset(file, 0, sizeof(file));
+	snprintf(file, sizeof(file) - 1,
+		 "%s/.bpf_dbg_history", getenv("HOME"));
+
+	write_history(file);
+	clear_history();
+	rl_deprep_terminal();
+
+	try_close_pcap();
+}
+
+static int run_shell_loop(FILE *fin, FILE *fout)
+{
+	char *buf;
+	int ret;
+
+	init_shell(fin, fout);
+
+	while ((buf = readline("> ")) != NULL) {
+		ret = execf(buf);
+		if (ret == CMD_EX)
+			break;
+		if (ret == CMD_OK && strlen(buf) > 0)
+			add_history(buf);
+
+		free(buf);
+	}
+
+	exit_shell();
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	FILE *fin = NULL, *fout = NULL;
+
+	if (argc >= 2)
+		fin = fopen(argv[1], "r");
+	if (argc >= 3)
+		fout = fopen(argv[2], "w");
+
+	return run_shell_loop(fin ? : stdin, fout ? : stdout);
+}
diff --git a/tools/net/bpf_exp.l b/tools/net/bpf_exp.l
new file mode 100644
index 000000000000..bf7be77ddd62
--- /dev/null
+++ b/tools/net/bpf_exp.l
@@ -0,0 +1,143 @@
+/*
+ * BPF asm code lexer
+ *
+ * This program is free software; you can distribute it and/or modify
+ * it under the terms of the GNU General Public License as published
+ * by the Free Software Foundation; either version 2 of the License,
+ * or (at your option) any later version.
+ *
+ * Syntax kept close to:
+ *
+ * Steven McCanne and Van Jacobson. 1993. The BSD packet filter: a new
+ * architecture for user-level packet capture. In Proceedings of the
+ * USENIX Winter 1993 Conference Proceedings on USENIX Winter 1993
+ * Conference Proceedings (USENIX'93). USENIX Association, Berkeley,
+ * CA, USA, 2-2.
+ *
+ * Copyright 2013 Daniel Borkmann <borkmann@redhat.com>
+ * Licensed under the GNU General Public License, version 2.0 (GPLv2)
+ */
+
+%{
+
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+
+#include "bpf_exp.yacc.h"
+
+extern void yyerror(const char *str);
+
+%}
+
+%option align
+%option ecs
+
+%option nounput
+%option noreject
+%option noinput
+%option noyywrap
+
+%option 8bit
+%option caseless
+%option yylineno
+
+%%
+
+"ldb"		{ return OP_LDB; }
+"ldh"		{ return OP_LDH; }
+"ld"		{ return OP_LD; }
+"ldi"		{ return OP_LDI; }
+"ldx"		{ return OP_LDX; }
+"ldxi"		{ return OP_LDXI; }
+"ldxb"		{ return OP_LDXB; }
+"st"		{ return OP_ST; }
+"stx"		{ return OP_STX; }
+"jmp"		{ return OP_JMP; }
+"ja"		{ return OP_JMP; }
+"jeq"		{ return OP_JEQ; }
+"jneq"		{ return OP_JNEQ; }
+"jne"		{ return OP_JNEQ; }
+"jlt"		{ return OP_JLT; }
+"jle"		{ return OP_JLE; }
+"jgt"		{ return OP_JGT; }
+"jge"		{ return OP_JGE; }
+"jset"		{ return OP_JSET; }
+"add"		{ return OP_ADD; }
+"sub"		{ return OP_SUB; }
+"mul"		{ return OP_MUL; }
+"div"		{ return OP_DIV; }
+"mod"		{ return OP_MOD; }
+"neg"		{ return OP_NEG; }
+"and"		{ return OP_AND; }
+"xor"		{ return OP_XOR; }
+"or"		{ return OP_OR; }
+"lsh"		{ return OP_LSH; }
+"rsh"		{ return OP_RSH; }
+"ret"		{ return OP_RET; }
+"tax"		{ return OP_TAX; }
+"txa"		{ return OP_TXA; }
+
+"#"?("len")	{ return K_PKT_LEN; }
+"#"?("proto")	{ return K_PROTO; }
+"#"?("type")	{ return K_TYPE; }
+"#"?("poff")	{ return K_POFF; }
+"#"?("ifidx")	{ return K_IFIDX; }
+"#"?("nla")	{ return K_NLATTR; }
+"#"?("nlan")	{ return K_NLATTR_NEST; }
+"#"?("mark")	{ return K_MARK; }
+"#"?("queue")	{ return K_QUEUE; }
+"#"?("hatype")	{ return K_HATYPE; }
+"#"?("rxhash")	{ return K_RXHASH; }
+"#"?("cpu")	{ return K_CPU; }
+"#"?("vlan_tci") { return K_VLANT; }
+"#"?("vlan_pr")	{ return K_VLANP; }
+
+":"		{ return ':'; }
+","		{ return ','; }
+"#"		{ return '#'; }
+"%"		{ return '%'; }
+"["		{ return '['; }
+"]"		{ return ']'; }
+"("		{ return '('; }
+")"		{ return ')'; }
+"x"		{ return 'x'; }
+"a"		{ return 'a'; }
+"+"		{ return '+'; }
+"M"		{ return 'M'; }
+"*"		{ return '*'; }
+"&"		{ return '&'; }
+
+([0][x][a-fA-F0-9]+) {
+			yylval.number = strtoul(yytext, NULL, 16);
+			return number;
+		}
+([0][b][0-1]+)	{
+			yylval.number = strtol(yytext + 2, NULL, 2);
+			return number;
+		}
+(([0])|([-+]?[1-9][0-9]*)) {
+			yylval.number = strtol(yytext, NULL, 10);
+			return number;
+		}
+([0][0-9]+)	{
+			yylval.number = strtol(yytext + 1, NULL, 8);
+			return number;
+		}
+[a-zA-Z_][a-zA-Z0-9_]+ {
+			yylval.label = strdup(yytext);
+			return label;
+		}
+
+"/*"([^\*]|\*[^/])*"*/"		{ /* NOP */ }
+";"[^\n]*			{ /* NOP */ }
+^#.*				{ /* NOP */ }
+[ \t]+				{ /* NOP */ }
+[ \n]+				{ /* NOP */ }
+
+.		{
+			printf("unknown character \'%s\'", yytext);
+			yyerror("lex unknown character");
+		}
+
+%%
diff --git a/tools/net/bpf_exp.y b/tools/net/bpf_exp.y
new file mode 100644
index 000000000000..d15efc989ef5
--- /dev/null
+++ b/tools/net/bpf_exp.y
@@ -0,0 +1,762 @@
+/*
+ * BPF asm code parser
+ *
+ * This program is free software; you can distribute it and/or modify
+ * it under the terms of the GNU General Public License as published
+ * by the Free Software Foundation; either version 2 of the License,
+ * or (at your option) any later version.
+ *
+ * Syntax kept close to:
+ *
+ * Steven McCanne and Van Jacobson. 1993. The BSD packet filter: a new
+ * architecture for user-level packet capture. In Proceedings of the
+ * USENIX Winter 1993 Conference Proceedings on USENIX Winter 1993
+ * Conference Proceedings (USENIX'93). USENIX Association, Berkeley,
+ * CA, USA, 2-2.
+ *
+ * Copyright 2013 Daniel Borkmann <borkmann@redhat.com>
+ * Licensed under the GNU General Public License, version 2.0 (GPLv2)
+ */
+
+%{
+
+#include <stdio.h>
+#include <string.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <unistd.h>
+#include <errno.h>
+#include <assert.h>
+#include <linux/filter.h>
+
+#include "bpf_exp.yacc.h"
+
+enum jmp_type { JTL, JFL, JKL };
+
+extern FILE *yyin;
+extern int yylex(void);
+extern void yyerror(const char *str);
+
+extern void bpf_asm_compile(FILE *fp, bool cstyle);
+static void bpf_set_curr_instr(uint16_t op, uint8_t jt, uint8_t jf, uint32_t k);
+static void bpf_set_curr_label(char *label);
+static void bpf_set_jmp_label(char *label, enum jmp_type type);
+
+%}
+
+%union {
+	char *label;
+	uint32_t number;
+}
+
+%token OP_LDB OP_LDH OP_LD OP_LDX OP_ST OP_STX OP_JMP OP_JEQ OP_JGT OP_JGE
+%token OP_JSET OP_ADD OP_SUB OP_MUL OP_DIV OP_AND OP_OR OP_XOR OP_LSH OP_RSH
+%token OP_RET OP_TAX OP_TXA OP_LDXB OP_MOD OP_NEG OP_JNEQ OP_JLT OP_JLE OP_LDI
+%token OP_LDXI
+
+%token K_PKT_LEN K_PROTO K_TYPE K_NLATTR K_NLATTR_NEST K_MARK K_QUEUE K_HATYPE
+%token K_RXHASH K_CPU K_IFIDX K_VLANT K_VLANP K_POFF
+
+%token ':' ',' '[' ']' '(' ')' 'x' 'a' '+' 'M' '*' '&' '#' '%'
+
+%token number label
+
+%type <label> label
+%type <number> number
+
+%%
+
+prog
+	: line
+	| prog line
+	;
+
+line
+	: instr
+	| labelled_instr
+	;
+
+labelled_instr
+	: labelled instr
+	;
+
+instr
+	: ldb
+	| ldh
+	| ld
+	| ldi
+	| ldx
+	| ldxi
+	| st
+	| stx
+	| jmp
+	| jeq
+	| jneq
+	| jlt
+	| jle
+	| jgt
+	| jge
+	| jset
+	| add
+	| sub
+	| mul
+	| div
+	| mod
+	| neg
+	| and
+	| or
+	| xor
+	| lsh
+	| rsh
+	| ret
+	| tax
+	| txa
+	;
+
+labelled
+	: label ':' { bpf_set_curr_label($1); }
+	;
+
+ldb
+	: OP_LDB '[' 'x' '+' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_IND, 0, 0, $5); }
+	| OP_LDB '[' '%' 'x' '+' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_IND, 0, 0, $6); }
+	| OP_LDB '[' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0, $3); }
+	| OP_LDB K_PROTO {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_PROTOCOL); }
+	| OP_LDB K_TYPE {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_PKTTYPE); }
+	| OP_LDB K_IFIDX {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_IFINDEX); }
+	| OP_LDB K_NLATTR {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_NLATTR); }
+	| OP_LDB K_NLATTR_NEST {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_NLATTR_NEST); }
+	| OP_LDB K_MARK {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_MARK); }
+	| OP_LDB K_QUEUE {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_QUEUE); }
+	| OP_LDB K_HATYPE {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_HATYPE); }
+	| OP_LDB K_RXHASH {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_RXHASH); }
+	| OP_LDB K_CPU {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_CPU); }
+	| OP_LDB K_VLANT {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_VLAN_TAG); }
+	| OP_LDB K_VLANP {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT); }
+	| OP_LDB K_POFF {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_PAY_OFFSET); }
+	;
+
+ldh
+	: OP_LDH '[' 'x' '+' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_IND, 0, 0, $5); }
+	| OP_LDH '[' '%' 'x' '+' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_IND, 0, 0, $6); }
+	| OP_LDH '[' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0, $3); }
+	| OP_LDH K_PROTO {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_PROTOCOL); }
+	| OP_LDH K_TYPE {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_PKTTYPE); }
+	| OP_LDH K_IFIDX {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_IFINDEX); }
+	| OP_LDH K_NLATTR {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_NLATTR); }
+	| OP_LDH K_NLATTR_NEST {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_NLATTR_NEST); }
+	| OP_LDH K_MARK {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_MARK); }
+	| OP_LDH K_QUEUE {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_QUEUE); }
+	| OP_LDH K_HATYPE {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_HATYPE); }
+	| OP_LDH K_RXHASH {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_RXHASH); }
+	| OP_LDH K_CPU {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_CPU); }
+	| OP_LDH K_VLANT {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_VLAN_TAG); }
+	| OP_LDH K_VLANP {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT); }
+	| OP_LDH K_POFF {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_PAY_OFFSET); }
+	;
+
+ldi
+	: OP_LDI '#' number {
+		bpf_set_curr_instr(BPF_LD | BPF_IMM, 0, 0, $3); }
+	| OP_LDI number {
+		bpf_set_curr_instr(BPF_LD | BPF_IMM, 0, 0, $2); }
+	;
+
+ld
+	: OP_LD '#' number {
+		bpf_set_curr_instr(BPF_LD | BPF_IMM, 0, 0, $3); }
+	| OP_LD K_PKT_LEN {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_LEN, 0, 0, 0); }
+	| OP_LD K_PROTO {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_PROTOCOL); }
+	| OP_LD K_TYPE {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_PKTTYPE); }
+	| OP_LD K_IFIDX {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_IFINDEX); }
+	| OP_LD K_NLATTR {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_NLATTR); }
+	| OP_LD K_NLATTR_NEST {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_NLATTR_NEST); }
+	| OP_LD K_MARK {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_MARK); }
+	| OP_LD K_QUEUE {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_QUEUE); }
+	| OP_LD K_HATYPE {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_HATYPE); }
+	| OP_LD K_RXHASH {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_RXHASH); }
+	| OP_LD K_CPU {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_CPU); }
+	| OP_LD K_VLANT {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_VLAN_TAG); }
+	| OP_LD K_VLANP {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT); }
+	| OP_LD K_POFF {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_PAY_OFFSET); }
+	| OP_LD 'M' '[' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_MEM, 0, 0, $4); }
+	| OP_LD '[' 'x' '+' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_IND, 0, 0, $5); }
+	| OP_LD '[' '%' 'x' '+' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_IND, 0, 0, $6); }
+	| OP_LD '[' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0, $3); }
+	;
+
+ldxi
+	: OP_LDXI '#' number {
+		bpf_set_curr_instr(BPF_LDX | BPF_IMM, 0, 0, $3); }
+	| OP_LDXI number {
+		bpf_set_curr_instr(BPF_LDX | BPF_IMM, 0, 0, $2); }
+	;
+
+ldx
+	: OP_LDX '#' number {
+		bpf_set_curr_instr(BPF_LDX | BPF_IMM, 0, 0, $3); }
+	| OP_LDX K_PKT_LEN {
+		bpf_set_curr_instr(BPF_LDX | BPF_W | BPF_LEN, 0, 0, 0); }
+	| OP_LDX 'M' '[' number ']' {
+		bpf_set_curr_instr(BPF_LDX | BPF_MEM, 0, 0, $4); }
+	| OP_LDXB number '*' '(' '[' number ']' '&' number ')' {
+		if ($2 != 4 || $9 != 0xf) {
+			fprintf(stderr, "ldxb offset not supported!\n");
+			exit(0);
+		} else {
+			bpf_set_curr_instr(BPF_LDX | BPF_MSH | BPF_B, 0, 0, $6); } }
+	| OP_LDX number '*' '(' '[' number ']' '&' number ')' {
+		if ($2 != 4 || $9 != 0xf) {
+			fprintf(stderr, "ldxb offset not supported!\n");
+			exit(0);
+		} else {
+			bpf_set_curr_instr(BPF_LDX | BPF_MSH | BPF_B, 0, 0, $6); } }
+	;
+
+st
+	: OP_ST 'M' '[' number ']' {
+		bpf_set_curr_instr(BPF_ST, 0, 0, $4); }
+	;
+
+stx
+	: OP_STX 'M' '[' number ']' {
+		bpf_set_curr_instr(BPF_STX, 0, 0, $4); }
+	;
+
+jmp
+	: OP_JMP label {
+		bpf_set_jmp_label($2, JKL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JA, 0, 0, 0); }
+	;
+
+jeq
+	: OP_JEQ '#' number ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_K, 0, 0, $3); }
+	| OP_JEQ 'x' ',' label ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_jmp_label($6, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
+	| OP_JEQ '%' 'x' ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
+	| OP_JEQ '#' number ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_K, 0, 0, $3); }
+	| OP_JEQ 'x' ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
+	| OP_JEQ '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
+	;
+
+jneq
+	: OP_JNEQ '#' number ',' label {
+		bpf_set_jmp_label($5, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_K, 0, 0, $3); }
+	| OP_JNEQ 'x' ',' label {
+		bpf_set_jmp_label($4, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
+	| OP_JNEQ '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
+	;
+
+jlt
+	: OP_JLT '#' number ',' label {
+		bpf_set_jmp_label($5, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_K, 0, 0, $3); }
+	| OP_JLT 'x' ',' label {
+		bpf_set_jmp_label($4, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
+	| OP_JLT '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
+	;
+
+jle
+	: OP_JLE '#' number ',' label {
+		bpf_set_jmp_label($5, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_K, 0, 0, $3); }
+	| OP_JLE 'x' ',' label {
+		bpf_set_jmp_label($4, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
+	| OP_JLE '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
+	;
+
+jgt
+	: OP_JGT '#' number ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_K, 0, 0, $3); }
+	| OP_JGT 'x' ',' label ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_jmp_label($6, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
+	| OP_JGT '%' 'x' ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
+	| OP_JGT '#' number ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_K, 0, 0, $3); }
+	| OP_JGT 'x' ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
+	| OP_JGT '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
+	;
+
+jge
+	: OP_JGE '#' number ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_K, 0, 0, $3); }
+	| OP_JGE 'x' ',' label ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_jmp_label($6, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
+	| OP_JGE '%' 'x' ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
+	| OP_JGE '#' number ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_K, 0, 0, $3); }
+	| OP_JGE 'x' ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
+	| OP_JGE '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
+	;
+
+jset
+	: OP_JSET '#' number ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_K, 0, 0, $3); }
+	| OP_JSET 'x' ',' label ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_jmp_label($6, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_X, 0, 0, 0); }
+	| OP_JSET '%' 'x' ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_X, 0, 0, 0); }
+	| OP_JSET '#' number ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_K, 0, 0, $3); }
+	| OP_JSET 'x' ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_X, 0, 0, 0); }
+	| OP_JSET '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_X, 0, 0, 0); }
+	;
+
+add
+	: OP_ADD '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_ADD | BPF_K, 0, 0, $3); }
+	| OP_ADD 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_ADD | BPF_X, 0, 0, 0); }
+	| OP_ADD '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_ADD | BPF_X, 0, 0, 0); }
+	;
+
+sub
+	: OP_SUB '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_SUB | BPF_K, 0, 0, $3); }
+	| OP_SUB 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_SUB | BPF_X, 0, 0, 0); }
+	| OP_SUB '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_SUB | BPF_X, 0, 0, 0); }
+	;
+
+mul
+	: OP_MUL '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_MUL | BPF_K, 0, 0, $3); }
+	| OP_MUL 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_MUL | BPF_X, 0, 0, 0); }
+	| OP_MUL '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_MUL | BPF_X, 0, 0, 0); }
+	;
+
+div
+	: OP_DIV '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_DIV | BPF_K, 0, 0, $3); }
+	| OP_DIV 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_DIV | BPF_X, 0, 0, 0); }
+	| OP_DIV '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_DIV | BPF_X, 0, 0, 0); }
+	;
+
+mod
+	: OP_MOD '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_MOD | BPF_K, 0, 0, $3); }
+	| OP_MOD 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_MOD | BPF_X, 0, 0, 0); }
+	| OP_MOD '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_MOD | BPF_X, 0, 0, 0); }
+	;
+
+neg
+	: OP_NEG {
+		bpf_set_curr_instr(BPF_ALU | BPF_NEG, 0, 0, 0); }
+	;
+
+and
+	: OP_AND '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_AND | BPF_K, 0, 0, $3); }
+	| OP_AND 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_AND | BPF_X, 0, 0, 0); }
+	| OP_AND '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_AND | BPF_X, 0, 0, 0); }
+	;
+
+or
+	: OP_OR '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_OR | BPF_K, 0, 0, $3); }
+	| OP_OR 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_OR | BPF_X, 0, 0, 0); }
+	| OP_OR '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_OR | BPF_X, 0, 0, 0); }
+	;
+
+xor
+	: OP_XOR '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_XOR | BPF_K, 0, 0, $3); }
+	| OP_XOR 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_XOR | BPF_X, 0, 0, 0); }
+	| OP_XOR '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_XOR | BPF_X, 0, 0, 0); }
+	;
+
+lsh
+	: OP_LSH '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_LSH | BPF_K, 0, 0, $3); }
+	| OP_LSH 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_LSH | BPF_X, 0, 0, 0); }
+	| OP_LSH '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_LSH | BPF_X, 0, 0, 0); }
+	;
+
+rsh
+	: OP_RSH '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_RSH | BPF_K, 0, 0, $3); }
+	| OP_RSH 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_RSH | BPF_X, 0, 0, 0); }
+	| OP_RSH '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_RSH | BPF_X, 0, 0, 0); }
+	;
+
+ret
+	: OP_RET 'a' {
+		bpf_set_curr_instr(BPF_RET | BPF_A, 0, 0, 0); }
+	| OP_RET '%' 'a' {
+		bpf_set_curr_instr(BPF_RET | BPF_A, 0, 0, 0); }
+	| OP_RET 'x' {
+		bpf_set_curr_instr(BPF_RET | BPF_X, 0, 0, 0); }
+	| OP_RET '%' 'x' {
+		bpf_set_curr_instr(BPF_RET | BPF_X, 0, 0, 0); }
+	| OP_RET '#' number {
+		bpf_set_curr_instr(BPF_RET | BPF_K, 0, 0, $3); }
+	;
+
+tax
+	: OP_TAX {
+		bpf_set_curr_instr(BPF_MISC | BPF_TAX, 0, 0, 0); }
+	;
+
+txa
+	: OP_TXA {
+		bpf_set_curr_instr(BPF_MISC | BPF_TXA, 0, 0, 0); }
+	;
+
+%%
+
+static int curr_instr = 0;
+static struct sock_filter out[BPF_MAXINSNS];
+static char **labels, **labels_jt, **labels_jf, **labels_k;
+
+static void bpf_assert_max(void)
+{
+	if (curr_instr >= BPF_MAXINSNS) {
+		fprintf(stderr, "only max %u insns allowed!\n", BPF_MAXINSNS);
+		exit(0);
+	}
+}
+
+static void bpf_set_curr_instr(uint16_t code, uint8_t jt, uint8_t jf,
+			       uint32_t k)
+{
+	bpf_assert_max();
+	out[curr_instr].code = code;
+	out[curr_instr].jt = jt;
+	out[curr_instr].jf = jf;
+	out[curr_instr].k = k;
+	curr_instr++;
+}
+
+static void bpf_set_curr_label(char *label)
+{
+	bpf_assert_max();
+	labels[curr_instr] = label;
+}
+
+static void bpf_set_jmp_label(char *label, enum jmp_type type)
+{
+	bpf_assert_max();
+	switch (type) {
+	case JTL:
+		labels_jt[curr_instr] = label;
+		break;
+	case JFL:
+		labels_jf[curr_instr] = label;
+		break;
+	case JKL:
+		labels_k[curr_instr] = label;
+		break;
+	}
+}
+
+static int bpf_find_insns_offset(const char *label)
+{
+	int i, max = curr_instr, ret = -ENOENT;
+
+	for (i = 0; i < max; i++) {
+		if (labels[i] && !strcmp(label, labels[i])) {
+			ret = i;
+			break;
+		}
+	}
+
+	if (ret == -ENOENT) {
+		fprintf(stderr, "no such label \'%s\'!\n", label);
+		exit(0);
+	}
+
+	return ret;
+}
+
+static void bpf_stage_1_insert_insns(void)
+{
+	yyparse();
+}
+
+static void bpf_reduce_k_jumps(void)
+{
+	int i;
+
+	for (i = 0; i < curr_instr; i++) {
+		if (labels_k[i]) {
+			int off = bpf_find_insns_offset(labels_k[i]);
+			out[i].k = (uint32_t) (off - i - 1);
+		}
+	}
+}
+
+static void bpf_reduce_jt_jumps(void)
+{
+	int i;
+
+	for (i = 0; i < curr_instr; i++) {
+		if (labels_jt[i]) {
+			int off = bpf_find_insns_offset(labels_jt[i]);
+			out[i].jt = (uint8_t) (off - i -1);
+		}
+	}
+}
+
+static void bpf_reduce_jf_jumps(void)
+{
+	int i;
+
+	for (i = 0; i < curr_instr; i++) {
+		if (labels_jf[i]) {
+			int off = bpf_find_insns_offset(labels_jf[i]);
+			out[i].jf = (uint8_t) (off - i - 1);
+		}
+	}
+}
+
+static void bpf_stage_2_reduce_labels(void)
+{
+	bpf_reduce_k_jumps();
+	bpf_reduce_jt_jumps();
+	bpf_reduce_jf_jumps();
+}
+
+static void bpf_pretty_print_c(void)
+{
+	int i;
+
+	for (i = 0; i < curr_instr; i++)
+		printf("{ %#04x, %2u, %2u, %#010x },\n", out[i].code,
+		       out[i].jt, out[i].jf, out[i].k);
+}
+
+static void bpf_pretty_print(void)
+{
+	int i;
+
+	printf("%u,", curr_instr);
+	for (i = 0; i < curr_instr; i++)
+		printf("%u %u %u %u,", out[i].code,
+		       out[i].jt, out[i].jf, out[i].k);
+	printf("\n");
+}
+
+static void bpf_init(void)
+{
+	memset(out, 0, sizeof(out));
+
+	labels = calloc(BPF_MAXINSNS, sizeof(*labels));
+	assert(labels);
+	labels_jt = calloc(BPF_MAXINSNS, sizeof(*labels_jt));
+	assert(labels_jt);
+	labels_jf = calloc(BPF_MAXINSNS, sizeof(*labels_jf));
+	assert(labels_jf);
+	labels_k = calloc(BPF_MAXINSNS, sizeof(*labels_k));
+	assert(labels_k);
+}
+
+static void bpf_destroy_labels(void)
+{
+	int i;
+
+	for (i = 0; i < curr_instr; i++) {
+		free(labels_jf[i]);
+		free(labels_jt[i]);
+		free(labels_k[i]);
+		free(labels[i]);
+	}
+}
+
+static void bpf_destroy(void)
+{
+	bpf_destroy_labels();
+	free(labels_jt);
+	free(labels_jf);
+	free(labels_k);
+	free(labels);
+}
+
+void bpf_asm_compile(FILE *fp, bool cstyle)
+{
+	yyin = fp;
+
+	bpf_init();
+	bpf_stage_1_insert_insns();
+	bpf_stage_2_reduce_labels();
+	bpf_destroy();
+
+	if (cstyle)
+		bpf_pretty_print_c();
+	else
+		bpf_pretty_print();
+
+	if (fp != stdin)
+		fclose(yyin);
+}
+
+void yyerror(const char *str)
+{
+	exit(1);
+}
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 652af0b66a62..25526d6eae59 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -1045,6 +1045,9 @@ static void write_svg_file(struct timechart *tchart, const char *filename)
 		thresh /= 10;
 	} while (!process_filter && thresh && count < tchart->proc_num);
 
+	if (!tchart->proc_num)
+		count = 0;
+
 	open_svg(filename, tchart->numcpus, count, tchart->first_time, tchart->last_time);
 
 	svg_time_grid();
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index d604e50fc167..c48d44958172 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -600,5 +600,5 @@ perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
 # Otherwise we install plugins into the global $(libdir).
 ifdef DESTDIR
 plugindir=$(libdir)/traceevent/plugins
-plugindir_SQ= $(subst ','\'',$(prefix)/$(plugindir))
+plugindir_SQ= $(subst ','\'',$(plugindir))
 endif
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 3c2f213e979d..7daa806d9050 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -132,6 +132,13 @@
 #define CPUINFO_PROC	"CPU"
 #endif
 
+#ifdef __xtensa__
+#define mb()		asm volatile("memw" ::: "memory")
+#define wmb()		asm volatile("memw" ::: "memory")
+#define rmb()		asm volatile("" ::: "memory")
+#define CPUINFO_PROC	"core ID"
+#endif
+
 #define barrier() asm volatile ("" ::: "memory")
 
 #ifndef cpu_relax
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 40bd2c04df8a..59ef2802fcf6 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1003,9 +1003,12 @@ void perf_evlist__close(struct perf_evlist *evlist)
 	struct perf_evsel *evsel;
 	int ncpus = cpu_map__nr(evlist->cpus);
 	int nthreads = thread_map__nr(evlist->threads);
+	int n;
 
-	evlist__for_each_reverse(evlist, evsel)
-		perf_evsel__close(evsel, ncpus, nthreads);
+	evlist__for_each_reverse(evlist, evsel) {
+		n = evsel->cpus ? evsel->cpus->nr : ncpus;
+		perf_evsel__close(evsel, n, nthreads);
+	}
 }
 
 int perf_evlist__open(struct perf_evlist *evlist)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 22e18a26b7e6..55407c594b87 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1081,7 +1081,6 @@ void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads)
 
 	perf_evsel__close_fd(evsel, ncpus, nthreads);
 	perf_evsel__free_fd(evsel);
-	evsel->fd = NULL;
 }
 
 static struct {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index bb3e0ede6183..893f8e2df928 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -930,7 +930,7 @@ static int write_topo_node(int fd, int node)
 		/* skip over invalid lines */
 		if (!strchr(buf, ':'))
 			continue;
-		if (sscanf(buf, "%*s %*d %s %"PRIu64, field, &mem) != 2)
+		if (sscanf(buf, "%*s %*d %31s %"PRIu64, field, &mem) != 2)
 			goto done;
 		if (!strcmp(field, "MemTotal:"))
 			mem_total = mem;
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 9b9bd719aa19..3b97513f0e77 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -69,7 +69,7 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		map->ino = ino;
 		map->ino_generation = ino_gen;
 
-		if (anon) {
+		if ((anon || no_dso) && type == MAP__FUNCTION) {
 			snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid);
 			filename = newfilename;
 		}
@@ -93,7 +93,7 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 			 * functions still return NULL, and we avoid the
 			 * unnecessary map__load warning.
 			 */
-			if (no_dso)
+			if (type != MAP__FUNCTION)
 				dso__set_loaded(dso, map->type);
 		}
 	}
@@ -386,7 +386,8 @@ struct symbol *map_groups__find_symbol(struct map_groups *mg,
 {
 	struct map *map = map_groups__find(mg, type, addr);
 
-	if (map != NULL) {
+	/* Ensure map is loaded before using map->map_ip */
+	if (map != NULL && map__load(map, filter) >= 0) {
 		if (mapp != NULL)
 			*mapp = map;
 		return map__find_symbol(map, map->map_ip(map, addr), filter);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index a7f1b6a91fdd..d248fca6d7ed 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -635,7 +635,7 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 	struct perf_event_attr attr;
 	struct perf_pmu *pmu;
 	struct perf_evsel *evsel;
-	char *unit;
+	const char *unit;
 	double scale;
 
 	pmu = perf_pmu__find(name);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index d9cab4d27192..b752ecb40d86 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -105,7 +105,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	char scale[128];
 	int fd, ret = -1;
 	char path[PATH_MAX];
-	char *lc;
+	const char *lc;
 
 	snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
 
@@ -609,7 +609,7 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 
 
 static int check_unit_scale(struct perf_pmu_alias *alias,
-			    char **unit, double *scale)
+			    const char **unit, double *scale)
 {
 	/*
 	 * Only one term in event definition can
@@ -634,14 +634,18 @@ static int check_unit_scale(struct perf_pmu_alias *alias,
  * defined for the alias
  */
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
-			  char **unit, double *scale)
+			  const char **unit, double *scale)
 {
 	struct parse_events_term *term, *h;
 	struct perf_pmu_alias *alias;
 	int ret;
 
+	/*
+	 * Mark unit and scale as not set
+	 * (different from default values, see below)
+	 */
 	*unit   = NULL;
-	*scale  = 0;
+	*scale  = 0.0;
 
 	list_for_each_entry_safe(term, h, head_terms, list) {
 		alias = pmu_find_alias(pmu, term);
@@ -658,6 +662,18 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 		list_del(&term->list);
 		free(term);
 	}
+
+	/*
+	 * if no unit or scale foundin aliases, then
+	 * set defaults as for evsel
+	 * unit cannot left to NULL
+	 */
+	if (*unit == NULL)
+		*unit   = "";
+
+	if (*scale == 0.0)
+		*scale  = 1.0;
+
 	return 0;
 }
 
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 9183380e2038..8b64125a9281 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -29,7 +29,7 @@ int perf_pmu__config_terms(struct list_head *formats,
 			   struct perf_event_attr *attr,
 			   struct list_head *head_terms);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
-			  char **unit, double *scale);
+			  const char **unit, double *scale);
 struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
 				  struct list_head *head_terms);
 int perf_pmu_wrap(void);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 7acc03e8f3b2..0b39a48e5110 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1573,7 +1573,7 @@ next:
 int perf_session__cpu_bitmap(struct perf_session *session,
 			     const char *cpu_list, unsigned long *cpu_bitmap)
 {
-	int i;
+	int i, err = -1;
 	struct cpu_map *map;
 
 	for (i = 0; i < PERF_TYPE_MAX; ++i) {
@@ -1602,13 +1602,17 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 		if (cpu >= MAX_NR_CPUS) {
 			pr_err("Requested CPU %d too large. "
 			       "Consider raising MAX_NR_CPUS\n", cpu);
-			return -1;
+			goto out_delete_map;
 		}
 
 		set_bit(cpu, cpu_bitmap);
 	}
 
-	return 0;
+	err = 0;
+
+out_delete_map:
+	cpu_map__delete(map);
+	return err;
 }
 
 void perf_session__fprintf_info(struct perf_session *session, FILE *fp,
diff --git a/tools/power/acpi/Makefile b/tools/power/acpi/Makefile
index bafeb8d662a3..d9186a2fdf06 100644
--- a/tools/power/acpi/Makefile
+++ b/tools/power/acpi/Makefile
@@ -1,18 +1,143 @@
-PROG= acpidump
-SRCS=	acpidump.c
+# tools/power/acpi/Makefile - ACPI tool Makefile
+#
+# Copyright (c) 2013, Intel Corporation
+#   Author: Lv Zheng <lv.zheng@intel.com>
+#
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License
+# as published by the Free Software Foundation; version 2
+# of the License.
+
+OUTPUT=./
+ifeq ("$(origin O)", "command line")
+	OUTPUT := $(O)/
+endif
+
+ifneq ($(OUTPUT),)
+# check that the output directory actually exists
+OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
+$(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
+endif
+
+# --- CONFIGURATION BEGIN ---
+
+# Set the following to `true' to make a unstripped, unoptimized
+# binary. Leave this set to `false' for production use.
+DEBUG ?=	true
+
+# make the build silent. Set this to something else to make it noisy again.
+V ?=		false
+
+# Prefix to the directories we're installing to
+DESTDIR ?=
+
+# --- CONFIGURATION END ---
+
+# Directory definitions. These are default and most probably
+# do not need to be changed. Please note that DESTDIR is
+# added in front of any of them
+
+bindir ?=	/usr/bin
+sbindir ?=	/usr/sbin
+mandir ?=	/usr/man
+
+# Toolchain: what tools do we use, and what options do they need:
+
+INSTALL = /usr/bin/install -c
+INSTALL_PROGRAM = ${INSTALL}
+INSTALL_DATA  = ${INSTALL} -m 644
+INSTALL_SCRIPT = ${INSTALL_PROGRAM}
+
+# If you are running a cross compiler, you may want to set this
+# to something more interesting, like "arm-linux-".  If you want
+# to compile vs uClibc, that can be done here as well.
+CROSS = #/usr/i386-linux-uclibc/usr/bin/i386-uclibc-
+CC = $(CROSS)gcc
+LD = $(CROSS)gcc
+STRIP = $(CROSS)strip
+HOSTCC = gcc
+
+# check if compiler option is supported
+cc-supports = ${shell if $(CC) ${1} -S -o /dev/null -x c /dev/null > /dev/null 2>&1; then echo "$(1)"; fi;}
+
+# use '-Os' optimization if available, else use -O2
+OPTIMIZATION := $(call cc-supports,-Os,-O2)
+
+WARNINGS := -Wall
+WARNINGS += $(call cc-supports,-Wstrict-prototypes)
+WARNINGS += $(call cc-supports,-Wdeclaration-after-statement)
+
 KERNEL_INCLUDE := ../../../include
-CFLAGS += -Wall -Wstrict-prototypes -Wdeclaration-after-statement -Os -s -D_LINUX -DDEFINE_ALTERNATE_TYPES -I$(KERNEL_INCLUDE) 
+CFLAGS += -D_LINUX -DDEFINE_ALTERNATE_TYPES -I$(KERNEL_INCLUDE)
+CFLAGS += $(WARNINGS)
+
+ifeq ($(strip $(V)),false)
+	QUIET=@
+	ECHO=@echo
+else
+	QUIET=
+	ECHO=@\#
+endif
+export QUIET ECHO
+
+# if DEBUG is enabled, then we do not strip or optimize
+ifeq ($(strip $(DEBUG)),true)
+	CFLAGS += -O1 -g -DDEBUG
+	STRIPCMD = /bin/true -Since_we_are_debugging
+else
+	CFLAGS += $(OPTIMIZATION) -fomit-frame-pointer
+	STRIPCMD = $(STRIP) -s --remove-section=.note --remove-section=.comment
+endif
+
+# if DEBUG is enabled, then we do not strip or optimize
+ifeq ($(strip $(DEBUG)),true)
+	CFLAGS += -O1 -g -DDEBUG
+	STRIPCMD = /bin/true -Since_we_are_debugging
+else
+	CFLAGS += $(OPTIMIZATION) -fomit-frame-pointer
+	STRIPCMD = $(STRIP) -s --remove-section=.note --remove-section=.comment
+endif
+
+# --- ACPIDUMP BEGIN ---
+
+vpath %.c \
+	tools/acpidump
+
+DUMP_OBJS = \
+	acpidump.o
+
+DUMP_OBJS := $(addprefix $(OUTPUT)tools/acpidump/,$(DUMP_OBJS))
+
+$(OUTPUT)acpidump: $(DUMP_OBJS)
+	$(ECHO) "  LD      " $@
+	$(QUIET) $(LD) $(CFLAGS) $(LDFLAGS) $(DUMP_OBJS) -L$(OUTPUT) -o $@
+	$(QUIET) $(STRIPCMD) $@
+
+$(OUTPUT)tools/acpidump/%.o: %.c
+	$(ECHO) "  CC      " $@
+	$(QUIET) $(CC) -c $(CFLAGS) -o $@ $<
+
+# --- ACPIDUMP END ---
+
+all: $(OUTPUT)acpidump
+	echo $(OUTPUT)
+
+clean:
+	-find $(OUTPUT) \( -not -type d \) -and \( -name '*~' -o -name '*.[oas]' \) -type f -print \
+	 | xargs rm -f
+	-rm -f $(OUTPUT)acpidump
 
-all: acpidump
-$(PROG) : $(SRCS)
-	$(CC) $(CFLAGS) $(SRCS) -o $(PROG)
+install-tools:
+	$(INSTALL) -d $(DESTDIR)${bindir}
+	$(INSTALL_PROGRAM) $(OUTPUT)acpidump $(DESTDIR)${sbindir}
 
-CLEANFILES= $(PROG)
+install-man:
+	$(INSTALL_DATA) -D man/acpidump.8 $(DESTDIR)${mandir}/man8/acpidump.8
 
-clean : 
-	rm -f $(CLEANFILES) $(patsubst %.c,%.o, $(SRCS)) *~
+install: all install-tools install-man
 
-install :
-	install acpidump /usr/sbin/acpidump
-	install acpidump.8 /usr/share/man/man8
+uninstall:
+	- rm -f $(DESTDIR)${sbindir}/acpidump
+	- rm -f $(DESTDIR)${mandir}/man8/acpidump.8
 
+.PHONY: all utils install-tools install-man install uninstall clean
diff --git a/tools/power/acpi/acpidump.8 b/tools/power/acpi/man/acpidump.8
index adfa99166e5e..adfa99166e5e 100644
--- a/tools/power/acpi/acpidump.8
+++ b/tools/power/acpi/man/acpidump.8
diff --git a/tools/power/acpi/acpidump.c b/tools/power/acpi/tools/acpidump/acpidump.c
index a84553a0e0df..a84553a0e0df 100644
--- a/tools/power/acpi/acpidump.c
+++ b/tools/power/acpi/tools/acpidump/acpidump.c
diff --git a/tools/power/cpupower/debug/kernel/cpufreq-test_tsc.c b/tools/power/cpupower/debug/kernel/cpufreq-test_tsc.c
index 66cace601e57..0f10b81e3322 100644
--- a/tools/power/cpupower/debug/kernel/cpufreq-test_tsc.c
+++ b/tools/power/cpupower/debug/kernel/cpufreq-test_tsc.c
@@ -25,12 +25,9 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/delay.h>
-
+#include <linux/acpi.h>
 #include <asm/io.h>
 
-#include <acpi/acpi_bus.h>
-#include <acpi/acpi_drivers.h>
-
 static int pm_tmr_ioport = 0;
 
 /*helper function to safely read acpi pm timesource*/
diff --git a/tools/power/cpupower/utils/cpufreq-set.c b/tools/power/cpupower/utils/cpufreq-set.c
index dd1539eb8c63..a416de80c55e 100644
--- a/tools/power/cpupower/utils/cpufreq-set.c
+++ b/tools/power/cpupower/utils/cpufreq-set.c
@@ -257,7 +257,7 @@ int cmd_freq_set(int argc, char **argv)
 				print_unknown_arg();
 				return -EINVAL;
 			}
-			if ((sscanf(optarg, "%s", gov)) != 1) {
+			if ((sscanf(optarg, "%19s", gov)) != 1) {
 				print_unknown_arg();
 				return -EINVAL;
 			}
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 9f3eae290900..32487ed18354 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -9,6 +9,7 @@ TARGETS += ptrace
 TARGETS += timers
 TARGETS += vm
 TARGETS += powerpc
+TARGETS += user
 
 all:
 	for TARGET in $(TARGETS); do \
diff --git a/tools/testing/selftests/user/Makefile b/tools/testing/selftests/user/Makefile
new file mode 100644
index 000000000000..396255bd720e
--- /dev/null
+++ b/tools/testing/selftests/user/Makefile
@@ -0,0 +1,13 @@
+# Makefile for user memory selftests
+
+# No binaries, but make sure arg-less "make" doesn't trigger "run_tests"
+all:
+
+run_tests: all
+	@if /sbin/modprobe test_user_copy ; then \
+		rmmod test_user_copy; \
+		echo "user_copy: ok"; \
+	else \
+		echo "user_copy: [FAIL]"; \
+		exit 1; \
+	fi