diff options
Diffstat (limited to 'tools')
54 files changed, 3124 insertions, 338 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: $(call descend,thermal/tmon,clean) -clean: cgroup_clean cpupower_clean firewire_clean lguest_clean perf_clean \ - selftests_clean turbostat_clean usb_clean virtio_clean \ +clean: acpi_clean cgroup_clean cpupower_clean firewire_clean lguest_clean \ + perf_clean selftests_clean turbostat_clean usb_clean virtio_clean \ vm_clean net_clean x86_energy_perf_policy_clean tmon_clean .PHONY: FORCE diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile index da8b7aa3d351..07b0b7542511 100644 --- a/tools/lib/lockdep/Makefile +++ b/tools/lib/lockdep/Makefile @@ -87,8 +87,8 @@ endif # BUILD_SRC # We process the rest of the Makefile if this is the final invocation of make ifeq ($(skip-makefile),) -srctree := $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR)) -objtree := $(CURDIR) +srctree := $(realpath $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR))) +objtree := $(realpath $(CURDIR)) src := $(srctree) obj := $(objtree) @@ -112,7 +112,7 @@ export Q VERBOSE LIBLOCKDEP_VERSION = $(LL_VERSION).$(LL_PATCHLEVEL).$(LL_EXTRAVERSION) -INCLUDES = -I. -I/usr/local/include -I./uinclude $(CONFIG_INCLUDES) +INCLUDES = -I. -I/usr/local/include -I./uinclude -I./include $(CONFIG_INCLUDES) # Set compile option CFLAGS if not set elsewhere CFLAGS ?= -g -DCONFIG_LOCKDEP -DCONFIG_STACKTRACE -DCONFIG_PROVE_LOCKING -DBITS_PER_LONG=__WORDSIZE -DLIBLOCKDEP_VERSION='"$(LIBLOCKDEP_VERSION)"' -rdynamic -O0 -g diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c index f8465a811aa5..23bd69cb5ade 100644 --- a/tools/lib/lockdep/preload.c +++ b/tools/lib/lockdep/preload.c @@ -418,7 +418,7 @@ int pthread_rwlock_unlock(pthread_rwlock_t *rwlock) __attribute__((constructor)) static void init_preload(void) { - if (__init_state != done) + if (__init_state == done) return; #ifndef __GLIBC__ diff --git a/tools/lib/lockdep/run_tests.sh b/tools/lib/lockdep/run_tests.sh index 5334ad9d39b7..5334ad9d39b7 100644..100755 --- a/tools/lib/lockdep/run_tests.sh +++ b/tools/lib/lockdep/run_tests.sh diff --git a/tools/lib/lockdep/uinclude/asm/hash.h b/tools/lib/lockdep/uinclude/asm/hash.h new file mode 100644 index 000000000000..d82b170bb216 --- /dev/null +++ b/tools/lib/lockdep/uinclude/asm/hash.h @@ -0,0 +1,6 @@ +#ifndef __ASM_GENERIC_HASH_H +#define __ASM_GENERIC_HASH_H + +/* Stub */ + +#endif /* __ASM_GENERIC_HASH_H */ diff --git a/tools/lib/lockdep/uinclude/linux/rcu.h b/tools/lib/lockdep/uinclude/linux/rcu.h index 4c99fcb5da27..042ee8e463c9 100644 --- a/tools/lib/lockdep/uinclude/linux/rcu.h +++ b/tools/lib/lockdep/uinclude/linux/rcu.h @@ -13,4 +13,9 @@ static inline int rcu_is_cpu_idle(void) return 1; } +static inline bool rcu_is_watching(void) +{ + return false; +} + #endif 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..ee577ea03ba5 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 $< -bpf_jit_disasm : CFLAGS = -Wall -O2 +%.lex.c: %.l + $(LEX) -o $@ $< + +all : bpf_jit_disasm bpf_dbg bpf_asm + +bpf_jit_disasm : CFLAGS = -Wall -O2 -DPACKAGE='bpf_jit_disasm' 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-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index cfede86161d8..b22dbb16f877 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -63,11 +63,35 @@ static int build_id_cache__kcore_dir(char *dir, size_t sz) return 0; } +static bool same_kallsyms_reloc(const char *from_dir, char *to_dir) +{ + char from[PATH_MAX]; + char to[PATH_MAX]; + const char *name; + u64 addr1 = 0, addr2 = 0; + int i; + + scnprintf(from, sizeof(from), "%s/kallsyms", from_dir); + scnprintf(to, sizeof(to), "%s/kallsyms", to_dir); + + for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) { + addr1 = kallsyms__get_function_start(from, name); + if (addr1) + break; + } + + if (name) + addr2 = kallsyms__get_function_start(to, name); + + return addr1 == addr2; +} + static int build_id_cache__kcore_existing(const char *from_dir, char *to_dir, size_t to_dir_sz) { char from[PATH_MAX]; char to[PATH_MAX]; + char to_subdir[PATH_MAX]; struct dirent *dent; int ret = -1; DIR *d; @@ -86,10 +110,11 @@ static int build_id_cache__kcore_existing(const char *from_dir, char *to_dir, continue; scnprintf(to, sizeof(to), "%s/%s/modules", to_dir, dent->d_name); - if (!compare_proc_modules(from, to)) { - scnprintf(to, sizeof(to), "%s/%s", to_dir, - dent->d_name); - strlcpy(to_dir, to, to_dir_sz); + scnprintf(to_subdir, sizeof(to_subdir), "%s/%s", + to_dir, dent->d_name); + if (!compare_proc_modules(from, to) && + same_kallsyms_reloc(from_dir, to_subdir)) { + strlcpy(to_dir, to_subdir, to_dir_sz); ret = 0; break; } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 3c394bf16fa8..af47531b82ec 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -287,10 +287,7 @@ static void perf_event__synthesize_guest_os(struct machine *machine, void *data) * have no _text sometimes. */ err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event, - machine, "_text"); - if (err < 0) - err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event, - machine, "_stext"); + machine); if (err < 0) pr_err("Couldn't record guest kernel [%d]'s reference" " relocation symbol.\n", machine->pid); @@ -457,10 +454,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) } err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event, - machine, "_text"); - if (err < 0) - err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event, - machine, "_stext"); + machine); if (err < 0) pr_err("Couldn't record kernel reference relocation symbol\n" "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n" diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 3c53ec268fbc..02f985f3a396 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -113,14 +113,16 @@ static int report__add_mem_hist_entry(struct perf_tool *tool, struct addr_locati if (!he) return -ENOMEM; - err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); - if (err) - goto out; + if (ui__has_annotation()) { + err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); + if (err) + goto out; - mx = he->mem_info; - err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx); - if (err) - goto out; + mx = he->mem_info; + err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx); + if (err) + goto out; + } evsel->hists.stats.total_period += cost; hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); @@ -164,14 +166,18 @@ static int report__add_branch_hist_entry(struct perf_tool *tool, struct addr_loc he = __hists__add_entry(&evsel->hists, al, parent, &bi[i], NULL, 1, 1, 0); if (he) { - bx = he->branch_info; - err = addr_map_symbol__inc_samples(&bx->from, evsel->idx); - if (err) - goto out; - - err = addr_map_symbol__inc_samples(&bx->to, evsel->idx); - if (err) - goto out; + if (ui__has_annotation()) { + bx = he->branch_info; + err = addr_map_symbol__inc_samples(&bx->from, + evsel->idx); + if (err) + goto out; + + err = addr_map_symbol__inc_samples(&bx->to, + evsel->idx); + if (err) + goto out; + } evsel->hists.stats.total_period += 1; hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); @@ -205,7 +211,9 @@ static int report__add_hist_entry(struct perf_tool *tool, struct perf_evsel *evs if (err) goto out; - err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); + if (ui__has_annotation()) + err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); + evsel->hists.stats.total_period += sample->period; hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); out: 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/builtin-top.c b/tools/perf/builtin-top.c index 76cd510d34d0..5f989a7d8bc2 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -176,7 +176,7 @@ static void perf_top__record_precise_ip(struct perf_top *top, { struct annotation *notes; struct symbol *sym; - int err; + int err = 0; if (he == NULL || he->ms.sym == NULL || ((top->sym_filter_entry == NULL || @@ -190,7 +190,9 @@ static void perf_top__record_precise_ip(struct perf_top *top, return; ip = he->ms.map->map_ip(he->ms.map, ip); - err = hist_entry__inc_addr_samples(he, counter, ip); + + if (ui__has_annotation()) + err = hist_entry__inc_addr_samples(he, counter, ip); pthread_mutex_unlock(¬es->lock); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 896f27047ed6..f954c26de231 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -37,6 +37,10 @@ # define MADV_UNMERGEABLE 13 #endif +#ifndef EFD_SEMAPHORE +# define EFD_SEMAPHORE 1 +#endif + struct tp_field { int offset; union { @@ -279,6 +283,11 @@ static size_t syscall_arg__scnprintf_strarray(char *bf, size_t size, #define SCA_STRARRAY syscall_arg__scnprintf_strarray +#if defined(__i386__) || defined(__x86_64__) +/* + * FIXME: Make this available to all arches as soon as the ioctl beautifier + * gets rewritten to support all arches. + */ static size_t syscall_arg__scnprintf_strhexarray(char *bf, size_t size, struct syscall_arg *arg) { @@ -286,6 +295,7 @@ static size_t syscall_arg__scnprintf_strhexarray(char *bf, size_t size, } #define SCA_STRHEXARRAY syscall_arg__scnprintf_strhexarray +#endif /* defined(__i386__) || defined(__x86_64__) */ static size_t syscall_arg__scnprintf_fd(char *bf, size_t size, struct syscall_arg *arg); @@ -815,7 +825,6 @@ static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscal P_SIGNUM(PIPE); P_SIGNUM(ALRM); P_SIGNUM(TERM); - P_SIGNUM(STKFLT); P_SIGNUM(CHLD); P_SIGNUM(CONT); P_SIGNUM(STOP); @@ -831,6 +840,15 @@ static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscal P_SIGNUM(IO); P_SIGNUM(PWR); P_SIGNUM(SYS); +#ifdef SIGEMT + P_SIGNUM(EMT); +#endif +#ifdef SIGSTKFLT + P_SIGNUM(STKFLT); +#endif +#ifdef SIGSWI + P_SIGNUM(SWI); +#endif default: break; } @@ -839,6 +857,10 @@ static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscal #define SCA_SIGNUM syscall_arg__scnprintf_signum +#if defined(__i386__) || defined(__x86_64__) +/* + * FIXME: Make this available to all arches. + */ #define TCGETS 0x5401 static const char *tioctls[] = { @@ -860,6 +882,7 @@ static const char *tioctls[] = { }; static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401); +#endif /* defined(__i386__) || defined(__x86_64__) */ #define STRARRAY(arg, name, array) \ .arg_scnprintf = { [arg] = SCA_STRARRAY, }, \ @@ -941,9 +964,16 @@ static struct syscall_fmt { { .name = "getrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), }, { .name = "ioctl", .errmsg = true, .arg_scnprintf = { [0] = SCA_FD, /* fd */ +#if defined(__i386__) || defined(__x86_64__) +/* + * FIXME: Make this available to all arches. + */ [1] = SCA_STRHEXARRAY, /* cmd */ [2] = SCA_HEX, /* arg */ }, .arg_parm = { [1] = &strarray__tioctls, /* cmd */ }, }, +#else + [2] = SCA_HEX, /* arg */ }, }, +#endif { .name = "kill", .errmsg = true, .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, }, { .name = "linkat", .errmsg = true, diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index d604e50fc167..0331ea2701a3 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -478,7 +478,7 @@ else endif ifeq ($(feature-libbfd), 1) - EXTLIBS += -lbfd + EXTLIBS += -lbfd -lz -liberty endif ifdef NO_DEMANGLE @@ -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/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile index 12e551346fa6..523b7bc10553 100644 --- a/tools/perf/config/feature-checks/Makefile +++ b/tools/perf/config/feature-checks/Makefile @@ -121,7 +121,7 @@ test-libpython-version.bin: $(BUILD) $(FLAGS_PYTHON_EMBED) test-libbfd.bin: - $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl + $(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl test-liberty.bin: $(CC) -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty diff --git a/tools/perf/design.txt b/tools/perf/design.txt index 67e5d0cace85..63a0e6f04a01 100644 --- a/tools/perf/design.txt +++ b/tools/perf/design.txt @@ -454,7 +454,6 @@ So to start with, in order to add HAVE_PERF_EVENTS to your Kconfig, you will need at least this: - asm/perf_event.h - a basic stub will suffice at first - support for atomic64 types (and associated helper functions) - - set_perf_event_pending() implemented If your architecture does have hardware capabilities, you can override the weak stub hw_perf_event_init() to register hardware counters. diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 3c2f213e979d..e84fa26bc1be 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -100,8 +100,8 @@ #ifdef __aarch64__ #define mb() asm volatile("dmb ish" ::: "memory") -#define wmb() asm volatile("dmb ishld" ::: "memory") -#define rmb() asm volatile("dmb ishst" ::: "memory") +#define wmb() asm volatile("dmb ishst" ::: "memory") +#define rmb() asm volatile("dmb ishld" ::: "memory") #define cpu_relax() asm volatile("yield" ::: "memory") #endif @@ -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/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index 2bd13edcbc17..3d9088003a5b 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -26,7 +26,6 @@ int test__vmlinux_matches_kallsyms(void) struct map *kallsyms_map, *vmlinux_map; struct machine kallsyms, vmlinux; enum map_type type = MAP__FUNCTION; - struct ref_reloc_sym ref_reloc_sym = { .name = "_stext", }; u64 mem_start, mem_end; /* @@ -70,14 +69,6 @@ int test__vmlinux_matches_kallsyms(void) */ kallsyms_map = machine__kernel_map(&kallsyms, type); - sym = map__find_symbol_by_name(kallsyms_map, ref_reloc_sym.name, NULL); - if (sym == NULL) { - pr_debug("dso__find_symbol_by_name "); - goto out; - } - - ref_reloc_sym.addr = UM(sym->start); - /* * Step 5: * @@ -89,7 +80,6 @@ int test__vmlinux_matches_kallsyms(void) } vmlinux_map = machine__kernel_map(&vmlinux, type); - map__kmap(vmlinux_map)->ref_reloc_sym = &ref_reloc_sym; /* * Step 6: diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 469eb679fb9d..3aa555ff9d89 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -8,6 +8,8 @@ */ #include "util.h" +#include "ui/ui.h" +#include "sort.h" #include "build-id.h" #include "color.h" #include "cache.h" @@ -489,7 +491,7 @@ static int symbol__inc_addr_samples(struct symbol *sym, struct map *map, { struct annotation *notes; - if (sym == NULL || use_browser != 1 || !sort__has_sym) + if (sym == NULL) return 0; notes = symbol__annotation(sym); @@ -1399,3 +1401,8 @@ int hist_entry__annotate(struct hist_entry *he, size_t privsize) { return symbol__annotate(he->ms.sym, he->ms.map, privsize); } + +bool ui__has_annotation(void) +{ + return use_browser == 1 && sort__has_sym; +} diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index b2aef59d6bb2..56ad4f5287de 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -151,6 +151,8 @@ void symbol__annotate_zero_histogram(struct symbol *sym, int evidx); void symbol__annotate_decay_histogram(struct symbol *sym, int evidx); void disasm__purge(struct list_head *head); +bool ui__has_annotation(void); + int symbol__tty_annotate(struct symbol *sym, struct map *map, struct perf_evsel *evsel, bool print_lines, bool full_paths, int min_pcnt, int max_lines); diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 1fc1c2f04772..b0f3ca850e9e 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -470,23 +470,32 @@ static int find_symbol_cb(void *arg, const char *name, char type, return 1; } +u64 kallsyms__get_function_start(const char *kallsyms_filename, + const char *symbol_name) +{ + struct process_symbol_args args = { .name = symbol_name, }; + + if (kallsyms__parse(kallsyms_filename, &args, find_symbol_cb) <= 0) + return 0; + + return args.start; +} + int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, perf_event__handler_t process, - struct machine *machine, - const char *symbol_name) + struct machine *machine) { size_t size; - const char *filename, *mmap_name; - char path[PATH_MAX]; + const char *mmap_name; char name_buff[PATH_MAX]; struct map *map; + struct kmap *kmap; int err; /* * We should get this from /sys/kernel/sections/.text, but till that is * available use this, and after it is use this as a fallback for older * kernels. */ - struct process_symbol_args args = { .name = symbol_name, }; union perf_event *event = zalloc((sizeof(event->mmap) + machine->id_hdr_size)); if (event == NULL) { @@ -502,30 +511,19 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, * see kernel/perf_event.c __perf_event_mmap */ event->header.misc = PERF_RECORD_MISC_KERNEL; - filename = "/proc/kallsyms"; } else { event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; - if (machine__is_default_guest(machine)) - filename = (char *) symbol_conf.default_guest_kallsyms; - else { - sprintf(path, "%s/proc/kallsyms", machine->root_dir); - filename = path; - } - } - - if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0) { - free(event); - return -ENOENT; } map = machine->vmlinux_maps[MAP__FUNCTION]; + kmap = map__kmap(map); size = snprintf(event->mmap.filename, sizeof(event->mmap.filename), - "%s%s", mmap_name, symbol_name) + 1; + "%s%s", mmap_name, kmap->ref_reloc_sym->name) + 1; size = PERF_ALIGN(size, sizeof(u64)); event->mmap.header.type = PERF_RECORD_MMAP; event->mmap.header.size = (sizeof(event->mmap) - (sizeof(event->mmap.filename) - size) + machine->id_hdr_size); - event->mmap.pgoff = args.start; + event->mmap.pgoff = kmap->ref_reloc_sym->addr; event->mmap.start = map->start; event->mmap.len = map->end - event->mmap.start; event->mmap.pid = machine->pid; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index faf6e219be21..851fa06f4a42 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -214,8 +214,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool, struct machine *machine, bool mmap_data); int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, perf_event__handler_t process, - struct machine *machine, - const char *symbol_name); + struct machine *machine); int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process, @@ -279,4 +278,7 @@ size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp); size_t perf_event__fprintf_task(union perf_event *event, FILE *fp); size_t perf_event__fprintf(union perf_event *event, FILE *fp); +u64 kallsyms__get_function_start(const char *kallsyms_filename, + const char *symbol_name); + #endif /* __PERF_RECORD_H */ 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/include/asm/hash.h b/tools/perf/util/include/asm/hash.h new file mode 100644 index 000000000000..d82b170bb216 --- /dev/null +++ b/tools/perf/util/include/asm/hash.h @@ -0,0 +1,6 @@ +#ifndef __ASM_GENERIC_HASH_H +#define __ASM_GENERIC_HASH_H + +/* Stub */ + +#endif /* __ASM_GENERIC_HASH_H */ diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h index 45cf10a562bd..dadfa7e54287 100644 --- a/tools/perf/util/include/linux/bitops.h +++ b/tools/perf/util/include/linux/bitops.h @@ -87,13 +87,15 @@ static __always_inline unsigned long __ffs(unsigned long word) return num; } +typedef const unsigned long __attribute__((__may_alias__)) long_alias_t; + /* * Find the first set bit in a memory region. */ static inline unsigned long find_first_bit(const unsigned long *addr, unsigned long size) { - const unsigned long *p = addr; + long_alias_t *p = (long_alias_t *) addr; unsigned long result = 0; unsigned long tmp; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index ded74590b92f..620a1983b76b 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -496,19 +496,22 @@ static int symbol__in_kernel(void *arg, const char *name, return 1; } +static void machine__get_kallsyms_filename(struct machine *machine, char *buf, + size_t bufsz) +{ + if (machine__is_default_guest(machine)) + scnprintf(buf, bufsz, "%s", symbol_conf.default_guest_kallsyms); + else + scnprintf(buf, bufsz, "%s/proc/kallsyms", machine->root_dir); +} + /* Figure out the start address of kernel map from /proc/kallsyms */ static u64 machine__get_kernel_start_addr(struct machine *machine) { - const char *filename; - char path[PATH_MAX]; + char filename[PATH_MAX]; struct process_args args; - if (machine__is_default_guest(machine)) - filename = (char *)symbol_conf.default_guest_kallsyms; - else { - sprintf(path, "%s/proc/kallsyms", machine->root_dir); - filename = path; - } + machine__get_kallsyms_filename(machine, filename, PATH_MAX); if (symbol__restricted_filename(filename, "/proc/kallsyms")) return 0; @@ -829,9 +832,25 @@ static int machine__create_modules(struct machine *machine) return 0; } +const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL}; + int machine__create_kernel_maps(struct machine *machine) { struct dso *kernel = machine__get_kernel(machine); + char filename[PATH_MAX]; + const char *name; + u64 addr = 0; + int i; + + machine__get_kallsyms_filename(machine, filename, PATH_MAX); + + for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) { + addr = kallsyms__get_function_start(filename, name); + if (addr) + break; + } + if (!addr) + return -1; if (kernel == NULL || __machine__create_kernel_maps(machine, kernel) < 0) @@ -850,6 +869,13 @@ int machine__create_kernel_maps(struct machine *machine) * Now that we have all the maps created, just set the ->end of them: */ map_groups__fixup_end(&machine->kmaps); + + if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, + addr)) { + machine__destroy_kernel_maps(machine); + return -1; + } + return 0; } @@ -1187,7 +1213,7 @@ static void ip__resolve_ams(struct machine *machine, struct thread *thread, */ thread__find_addr_location(thread, machine, m, MAP__FUNCTION, ip, &al); - if (al.sym) + if (al.map) goto found; } found: diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 477133015440..f77e91e483dc 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -18,6 +18,8 @@ union perf_event; #define HOST_KERNEL_ID (-1) #define DEFAULT_GUEST_KERNEL_ID (0) +extern const char *ref_reloc_sym_names[]; + struct machine { struct rb_node rb_node; pid_t pid; diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 9b9bd719aa19..39cd2d0faff6 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -39,6 +39,7 @@ void map__init(struct map *map, enum map_type type, map->start = start; map->end = end; map->pgoff = pgoff; + map->reloc = 0; map->dso = dso; map->map_ip = map__map_ip; map->unmap_ip = map__unmap_ip; @@ -69,7 +70,7 @@ 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 +94,7 @@ 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); } } @@ -288,7 +289,7 @@ u64 map__rip_2objdump(struct map *map, u64 rip) if (map->dso->rel) return rip - map->pgoff; - return map->unmap_ip(map, rip); + return map->unmap_ip(map, rip) - map->reloc; } /** @@ -311,7 +312,7 @@ u64 map__objdump_2mem(struct map *map, u64 ip) if (map->dso->rel) return map->unmap_ip(map, ip + map->pgoff); - return ip; + return ip + map->reloc; } void map_groups__init(struct map_groups *mg) @@ -386,7 +387,8 @@ 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/map.h b/tools/perf/util/map.h index 18068c6b71c1..257e513205ce 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -36,6 +36,7 @@ struct map { bool erange_warned; u32 priv; u64 pgoff; + u64 reloc; u32 maj, min; /* only valid for MMAP2 record */ u64 ino; /* only valid for MMAP2 record */ u64 ino_generation;/* only valid for MMAP2 record */ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index a7f1b6a91fdd..1e15df10a88c 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); @@ -1091,12 +1091,12 @@ int is_valid_tracepoint(const char *event_string) static bool is_event_supported(u8 type, unsigned config) { bool ret = true; + int open_return; struct perf_evsel *evsel; struct perf_event_attr attr = { .type = type, .config = config, .disabled = 1, - .exclude_kernel = 1, }; struct { struct thread_map map; @@ -1108,7 +1108,20 @@ static bool is_event_supported(u8 type, unsigned config) evsel = perf_evsel__new(&attr); if (evsel) { - ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0; + open_return = perf_evsel__open(evsel, NULL, &tmap.map); + ret = open_return >= 0; + + if (open_return == -EACCES) { + /* + * This happens if the paranoid value + * /proc/sys/kernel/perf_event_paranoid is set to 2 + * Re-run with exclude_kernel set; we don't do that + * by default as some ARM machines do not support it. + * + */ + evsel->attr.exclude_kernel = 1; + ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0; + } perf_evsel__delete(evsel); } 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/probe-event.c b/tools/perf/util/probe-event.c index a8a9b6cd93a8..d8b048c20cde 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -336,8 +336,8 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs, return ret; for (i = 0; i < ntevs && ret >= 0; i++) { + /* point.address is the addres of point.symbol + point.offset */ offset = tevs[i].point.address - stext; - offset += tevs[i].point.offset; tevs[i].point.offset = 0; zfree(&tevs[i].point.symbol); ret = e_snprintf(buf, 32, "0x%lx", offset); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 7acc03e8f3b2..5da6ce74c676 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1008,6 +1008,12 @@ static int perf_session__process_user_event(struct perf_session *session, union if (err == 0) perf_session__set_id_hdr_size(session); return err; + case PERF_RECORD_HEADER_EVENT_TYPE: + /* + * Depreceated, but we need to handle it for sake + * of old data files create in pipe mode. + */ + return 0; case PERF_RECORD_HEADER_TRACING_DATA: /* setup for reading amidst mmap */ lseek(fd, file_offset, SEEK_SET); @@ -1573,7 +1579,7 @@ 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 +1608,17 @@ 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/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 759456728703..516d19fb999b 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -151,15 +151,15 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, gelf_getshdr(sec, shp); str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name); - if (!strcmp(name, str)) { + if (str && !strcmp(name, str)) { if (idx) *idx = cnt; - break; + return sec; } ++cnt; } - return sec; + return NULL; } #define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \ @@ -751,6 +751,8 @@ int dso__load_sym(struct dso *dso, struct map *map, if (strcmp(elf_name, kmap->ref_reloc_sym->name)) continue; kmap->ref_reloc_sym->unrelocated_addr = sym.st_value; + map->reloc = kmap->ref_reloc_sym->addr - + kmap->ref_reloc_sym->unrelocated_addr; break; } } @@ -922,6 +924,7 @@ int dso__load_sym(struct dso *dso, struct map *map, (u64)shdr.sh_offset); sym.st_value -= shdr.sh_addr - shdr.sh_offset; } +new_symbol: /* * We need to figure out if the object was created from C++ sources * DWARF DW_compile_unit has this, but we don't always have access @@ -933,7 +936,6 @@ int dso__load_sym(struct dso *dso, struct map *map, if (demangled != NULL) elf_name = demangled; } -new_symbol: f = symbol__new(sym.st_value, sym.st_size, GELF_ST_BIND(sym.st_info), elf_name); free(demangled); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 39ce9adbaaf0..e89afc097d8a 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -627,7 +627,7 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map, * kernel range is broken in several maps, named [kernel].N, as we don't have * the original ELF section names vmlinux have. */ -static int dso__split_kallsyms(struct dso *dso, struct map *map, +static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta, symbol_filter_t filter) { struct map_groups *kmaps = map__kmap(map)->kmaps; @@ -692,6 +692,12 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, char dso_name[PATH_MAX]; struct dso *ndso; + if (delta) { + /* Kernel was relocated at boot time */ + pos->start -= delta; + pos->end -= delta; + } + if (count == 0) { curr_map = map; goto filter_symbol; @@ -721,6 +727,10 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, curr_map->map_ip = curr_map->unmap_ip = identity__map_ip; map_groups__insert(kmaps, curr_map); ++kernel_range; + } else if (delta) { + /* Kernel was relocated at boot time */ + pos->start -= delta; + pos->end -= delta; } filter_symbol: if (filter && filter(curr_map, pos)) { @@ -976,6 +986,23 @@ static int validate_kcore_modules(const char *kallsyms_filename, return 0; } +static int validate_kcore_addresses(const char *kallsyms_filename, + struct map *map) +{ + struct kmap *kmap = map__kmap(map); + + if (kmap->ref_reloc_sym && kmap->ref_reloc_sym->name) { + u64 start; + + start = kallsyms__get_function_start(kallsyms_filename, + kmap->ref_reloc_sym->name); + if (start != kmap->ref_reloc_sym->addr) + return -EINVAL; + } + + return validate_kcore_modules(kallsyms_filename, map); +} + struct kcore_mapfn_data { struct dso *dso; enum map_type type; @@ -1019,8 +1046,8 @@ static int dso__load_kcore(struct dso *dso, struct map *map, kallsyms_filename)) return -EINVAL; - /* All modules must be present at their original addresses */ - if (validate_kcore_modules(kallsyms_filename, map)) + /* Modules and kernel must be present at their original addresses */ + if (validate_kcore_addresses(kallsyms_filename, map)) return -EINVAL; md.dso = dso; @@ -1113,15 +1140,41 @@ out_err: return -EINVAL; } +/* + * If the kernel is relocated at boot time, kallsyms won't match. Compute the + * delta based on the relocation reference symbol. + */ +static int kallsyms__delta(struct map *map, const char *filename, u64 *delta) +{ + struct kmap *kmap = map__kmap(map); + u64 addr; + + if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->name) + return 0; + + addr = kallsyms__get_function_start(filename, + kmap->ref_reloc_sym->name); + if (!addr) + return -1; + + *delta = addr - kmap->ref_reloc_sym->addr; + return 0; +} + int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map, symbol_filter_t filter) { + u64 delta = 0; + if (symbol__restricted_filename(filename, "/proc/kallsyms")) return -1; if (dso__load_all_kallsyms(dso, filename, map) < 0) return -1; + if (kallsyms__delta(map, filename, &delta)) + return -1; + symbols__fixup_duplicate(&dso->symbols[map->type]); symbols__fixup_end(&dso->symbols[map->type]); @@ -1133,7 +1186,7 @@ int dso__load_kallsyms(struct dso *dso, const char *filename, if (!dso__load_kcore(dso, map, filename)) return dso__split_kallsyms_for_kcore(dso, map, filter); else - return dso__split_kallsyms(dso, map, filter); + return dso__split_kallsyms(dso, map, delta, filter); } static int dso__load_perf_map(struct dso *dso, struct map *map, @@ -1283,6 +1336,8 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) if (syms_ss && runtime_ss) break; + } else { + symsrc__destroy(ss); } } @@ -1424,7 +1479,7 @@ static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz) continue; scnprintf(kallsyms_filename, sizeof(kallsyms_filename), "%s/%s/kallsyms", dir, dent->d_name); - if (!validate_kcore_modules(kallsyms_filename, map)) { + if (!validate_kcore_addresses(kallsyms_filename, map)) { strlcpy(dir, kallsyms_filename, dir_sz); ret = 0; break; @@ -1479,7 +1534,7 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map) if (fd != -1) { close(fd); /* If module maps match go with /proc/kallsyms */ - if (!validate_kcore_modules("/proc/kallsyms", map)) + if (!validate_kcore_addresses("/proc/kallsyms", map)) goto proc_kallsyms; } 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/power/x86/turbostat/.gitignore b/tools/power/x86/turbostat/.gitignore new file mode 100644 index 000000000000..7521370d3568 --- /dev/null +++ b/tools/power/x86/turbostat/.gitignore @@ -0,0 +1 @@ +turbostat diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile index f09641da40d4..d1b3a361e526 100644 --- a/tools/power/x86/turbostat/Makefile +++ b/tools/power/x86/turbostat/Makefile @@ -5,7 +5,7 @@ DESTDIR := turbostat : turbostat.c CFLAGS += -Wall -CFLAGS += -I../../../../arch/x86/include/uapi/ +CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/uapi/asm/msr-index.h"' %: %.c @mkdir -p $(BUILD_OUTPUT) diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 9d77f13c2d25..77eb130168da 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -20,8 +20,10 @@ */ #define _GNU_SOURCE -#include <asm/msr.h> +#include MSRHEADER +#include <stdarg.h> #include <stdio.h> +#include <err.h> #include <unistd.h> #include <sys/types.h> #include <sys/wait.h> @@ -35,13 +37,16 @@ #include <string.h> #include <ctype.h> #include <sched.h> +#include <cpuid.h> char *proc_stat = "/proc/stat"; unsigned int interval_sec = 5; /* set with -i interval_sec */ unsigned int verbose; /* set with -v */ unsigned int rapl_verbose; /* set with -R */ +unsigned int rapl_joules; /* set with -J */ unsigned int thermal_verbose; /* set with -T */ -unsigned int summary_only; /* set with -s */ +unsigned int summary_only; /* set with -S */ +unsigned int dump_only; /* set with -s */ unsigned int skip_c0; unsigned int skip_c1; unsigned int do_nhm_cstates; @@ -77,14 +82,32 @@ unsigned int tcc_activation_temp_override; double rapl_power_units, rapl_energy_units, rapl_time_units; double rapl_joule_counter_range; -#define RAPL_PKG (1 << 0) -#define RAPL_CORES (1 << 1) -#define RAPL_GFX (1 << 2) -#define RAPL_DRAM (1 << 3) -#define RAPL_PKG_PERF_STATUS (1 << 4) -#define RAPL_DRAM_PERF_STATUS (1 << 5) -#define RAPL_PKG_POWER_INFO (1 << 6) -#define RAPL_CORE_POLICY (1 << 7) +#define RAPL_PKG (1 << 0) + /* 0x610 MSR_PKG_POWER_LIMIT */ + /* 0x611 MSR_PKG_ENERGY_STATUS */ +#define RAPL_PKG_PERF_STATUS (1 << 1) + /* 0x613 MSR_PKG_PERF_STATUS */ +#define RAPL_PKG_POWER_INFO (1 << 2) + /* 0x614 MSR_PKG_POWER_INFO */ + +#define RAPL_DRAM (1 << 3) + /* 0x618 MSR_DRAM_POWER_LIMIT */ + /* 0x619 MSR_DRAM_ENERGY_STATUS */ + /* 0x61c MSR_DRAM_POWER_INFO */ +#define RAPL_DRAM_PERF_STATUS (1 << 4) + /* 0x61b MSR_DRAM_PERF_STATUS */ + +#define RAPL_CORES (1 << 5) + /* 0x638 MSR_PP0_POWER_LIMIT */ + /* 0x639 MSR_PP0_ENERGY_STATUS */ +#define RAPL_CORE_POLICY (1 << 6) + /* 0x63a MSR_PP0_POLICY */ + + +#define RAPL_GFX (1 << 7) + /* 0x640 MSR_PP1_POWER_LIMIT */ + /* 0x641 MSR_PP1_ENERGY_STATUS */ + /* 0x642 MSR_PP1_POLICY */ #define TJMAX_DEFAULT 100 #define MAX(a, b) ((a) > (b) ? (a) : (b)) @@ -234,7 +257,7 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr) close(fd); if (retval != sizeof *msr) { - fprintf(stderr, "%s offset 0x%zx read failed\n", pathname, offset); + fprintf(stderr, "%s offset 0x%llx read failed\n", pathname, (unsigned long long)offset); return -1; } @@ -296,70 +319,92 @@ void print_header(void) outp += sprintf(outp, " %%pc10"); } - if (do_rapl & RAPL_PKG) - outp += sprintf(outp, " Pkg_W"); - if (do_rapl & RAPL_CORES) - outp += sprintf(outp, " Cor_W"); - if (do_rapl & RAPL_GFX) - outp += sprintf(outp, " GFX_W"); - if (do_rapl & RAPL_DRAM) - outp += sprintf(outp, " RAM_W"); - if (do_rapl & RAPL_PKG_PERF_STATUS) - outp += sprintf(outp, " PKG_%%"); - if (do_rapl & RAPL_DRAM_PERF_STATUS) - outp += sprintf(outp, " RAM_%%"); + if (do_rapl && !rapl_joules) { + if (do_rapl & RAPL_PKG) + outp += sprintf(outp, " Pkg_W"); + if (do_rapl & RAPL_CORES) + outp += sprintf(outp, " Cor_W"); + if (do_rapl & RAPL_GFX) + outp += sprintf(outp, " GFX_W"); + if (do_rapl & RAPL_DRAM) + outp += sprintf(outp, " RAM_W"); + if (do_rapl & RAPL_PKG_PERF_STATUS) + outp += sprintf(outp, " PKG_%%"); + if (do_rapl & RAPL_DRAM_PERF_STATUS) + outp += sprintf(outp, " RAM_%%"); + } else { + if (do_rapl & RAPL_PKG) + outp += sprintf(outp, " Pkg_J"); + if (do_rapl & RAPL_CORES) + outp += sprintf(outp, " Cor_J"); + if (do_rapl & RAPL_GFX) + outp += sprintf(outp, " GFX_J"); + if (do_rapl & RAPL_DRAM) + outp += sprintf(outp, " RAM_W"); + if (do_rapl & RAPL_PKG_PERF_STATUS) + outp += sprintf(outp, " PKG_%%"); + if (do_rapl & RAPL_DRAM_PERF_STATUS) + outp += sprintf(outp, " RAM_%%"); + outp += sprintf(outp, " time"); + } outp += sprintf(outp, "\n"); } int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) { - fprintf(stderr, "t %p, c %p, p %p\n", t, c, p); + outp += sprintf(outp, "t %p, c %p, p %p\n", t, c, p); if (t) { - fprintf(stderr, "CPU: %d flags 0x%x\n", t->cpu_id, t->flags); - fprintf(stderr, "TSC: %016llX\n", t->tsc); - fprintf(stderr, "aperf: %016llX\n", t->aperf); - fprintf(stderr, "mperf: %016llX\n", t->mperf); - fprintf(stderr, "c1: %016llX\n", t->c1); - fprintf(stderr, "msr0x%x: %08llX\n", + outp += sprintf(outp, "CPU: %d flags 0x%x\n", + t->cpu_id, t->flags); + outp += sprintf(outp, "TSC: %016llX\n", t->tsc); + outp += sprintf(outp, "aperf: %016llX\n", t->aperf); + outp += sprintf(outp, "mperf: %016llX\n", t->mperf); + outp += sprintf(outp, "c1: %016llX\n", t->c1); + outp += sprintf(outp, "msr0x%x: %08llX\n", extra_delta_offset32, t->extra_delta32); - fprintf(stderr, "msr0x%x: %016llX\n", + outp += sprintf(outp, "msr0x%x: %016llX\n", extra_delta_offset64, t->extra_delta64); - fprintf(stderr, "msr0x%x: %08llX\n", + outp += sprintf(outp, "msr0x%x: %08llX\n", extra_msr_offset32, t->extra_msr32); - fprintf(stderr, "msr0x%x: %016llX\n", + outp += sprintf(outp, "msr0x%x: %016llX\n", extra_msr_offset64, t->extra_msr64); if (do_smi) - fprintf(stderr, "SMI: %08X\n", t->smi_count); + outp += sprintf(outp, "SMI: %08X\n", t->smi_count); } if (c) { - fprintf(stderr, "core: %d\n", c->core_id); - fprintf(stderr, "c3: %016llX\n", c->c3); - fprintf(stderr, "c6: %016llX\n", c->c6); - fprintf(stderr, "c7: %016llX\n", c->c7); - fprintf(stderr, "DTS: %dC\n", c->core_temp_c); + outp += sprintf(outp, "core: %d\n", c->core_id); + outp += sprintf(outp, "c3: %016llX\n", c->c3); + outp += sprintf(outp, "c6: %016llX\n", c->c6); + outp += sprintf(outp, "c7: %016llX\n", c->c7); + outp += sprintf(outp, "DTS: %dC\n", c->core_temp_c); } if (p) { - fprintf(stderr, "package: %d\n", p->package_id); - fprintf(stderr, "pc2: %016llX\n", p->pc2); - fprintf(stderr, "pc3: %016llX\n", p->pc3); - fprintf(stderr, "pc6: %016llX\n", p->pc6); - fprintf(stderr, "pc7: %016llX\n", p->pc7); - fprintf(stderr, "pc8: %016llX\n", p->pc8); - fprintf(stderr, "pc9: %016llX\n", p->pc9); - fprintf(stderr, "pc10: %016llX\n", p->pc10); - fprintf(stderr, "Joules PKG: %0X\n", p->energy_pkg); - fprintf(stderr, "Joules COR: %0X\n", p->energy_cores); - fprintf(stderr, "Joules GFX: %0X\n", p->energy_gfx); - fprintf(stderr, "Joules RAM: %0X\n", p->energy_dram); - fprintf(stderr, "Throttle PKG: %0X\n", p->rapl_pkg_perf_status); - fprintf(stderr, "Throttle RAM: %0X\n", p->rapl_dram_perf_status); - fprintf(stderr, "PTM: %dC\n", p->pkg_temp_c); + outp += sprintf(outp, "package: %d\n", p->package_id); + outp += sprintf(outp, "pc2: %016llX\n", p->pc2); + outp += sprintf(outp, "pc3: %016llX\n", p->pc3); + outp += sprintf(outp, "pc6: %016llX\n", p->pc6); + outp += sprintf(outp, "pc7: %016llX\n", p->pc7); + outp += sprintf(outp, "pc8: %016llX\n", p->pc8); + outp += sprintf(outp, "pc9: %016llX\n", p->pc9); + outp += sprintf(outp, "pc10: %016llX\n", p->pc10); + outp += sprintf(outp, "Joules PKG: %0X\n", p->energy_pkg); + outp += sprintf(outp, "Joules COR: %0X\n", p->energy_cores); + outp += sprintf(outp, "Joules GFX: %0X\n", p->energy_gfx); + outp += sprintf(outp, "Joules RAM: %0X\n", p->energy_dram); + outp += sprintf(outp, "Throttle PKG: %0X\n", + p->rapl_pkg_perf_status); + outp += sprintf(outp, "Throttle RAM: %0X\n", + p->rapl_dram_perf_status); + outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c); } + + outp += sprintf(outp, "\n"); + return 0; } @@ -527,19 +572,39 @@ int format_counters(struct thread_data *t, struct core_data *c, fmt6 = " %4.0f**"; } - if (do_rapl & RAPL_PKG) - outp += sprintf(outp, fmt6, p->energy_pkg * rapl_energy_units / interval_float); - if (do_rapl & RAPL_CORES) - outp += sprintf(outp, fmt6, p->energy_cores * rapl_energy_units / interval_float); - if (do_rapl & RAPL_GFX) - outp += sprintf(outp, fmt5, p->energy_gfx * rapl_energy_units / interval_float); - if (do_rapl & RAPL_DRAM) - outp += sprintf(outp, fmt5, p->energy_dram * rapl_energy_units / interval_float); - if (do_rapl & RAPL_PKG_PERF_STATUS ) - outp += sprintf(outp, fmt5, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float); - if (do_rapl & RAPL_DRAM_PERF_STATUS ) - outp += sprintf(outp, fmt5, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float); + if (do_rapl && !rapl_joules) { + if (do_rapl & RAPL_PKG) + outp += sprintf(outp, fmt6, p->energy_pkg * rapl_energy_units / interval_float); + if (do_rapl & RAPL_CORES) + outp += sprintf(outp, fmt6, p->energy_cores * rapl_energy_units / interval_float); + if (do_rapl & RAPL_GFX) + outp += sprintf(outp, fmt5, p->energy_gfx * rapl_energy_units / interval_float); + if (do_rapl & RAPL_DRAM) + outp += sprintf(outp, fmt5, p->energy_dram * rapl_energy_units / interval_float); + if (do_rapl & RAPL_PKG_PERF_STATUS) + outp += sprintf(outp, fmt5, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float); + if (do_rapl & RAPL_DRAM_PERF_STATUS) + outp += sprintf(outp, fmt5, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float); + } else { + if (do_rapl & RAPL_PKG) + outp += sprintf(outp, fmt6, + p->energy_pkg * rapl_energy_units); + if (do_rapl & RAPL_CORES) + outp += sprintf(outp, fmt6, + p->energy_cores * rapl_energy_units); + if (do_rapl & RAPL_GFX) + outp += sprintf(outp, fmt5, + p->energy_gfx * rapl_energy_units); + if (do_rapl & RAPL_DRAM) + outp += sprintf(outp, fmt5, + p->energy_dram * rapl_energy_units); + if (do_rapl & RAPL_PKG_PERF_STATUS) + outp += sprintf(outp, fmt5, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float); + if (do_rapl & RAPL_DRAM_PERF_STATUS) + outp += sprintf(outp, fmt5, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float); + outp += sprintf(outp, fmt5, interval_float); + } done: outp += sprintf(outp, "\n"); @@ -622,12 +687,10 @@ delta_thread(struct thread_data *new, struct thread_data *old, old->tsc = new->tsc - old->tsc; /* check for TSC < 1 Mcycles over interval */ - if (old->tsc < (1000 * 1000)) { - fprintf(stderr, "Insanely slow TSC rate, TSC stops in idle?\n"); - fprintf(stderr, "You can disable all c-states by booting with \"idle=poll\"\n"); - fprintf(stderr, "or just the deep ones with \"processor.max_cstate=1\"\n"); - exit(-3); - } + if (old->tsc < (1000 * 1000)) + errx(-3, "Insanely slow TSC rate, TSC stops in idle?\n" + "You can disable all c-states by booting with \"idle=poll\"\n" + "or just the deep ones with \"processor.max_cstate=1\""); old->c1 = new->c1 - old->c1; @@ -1173,24 +1236,43 @@ void free_all_buffers(void) } /* + * Open a file, and exit on failure + */ +FILE *fopen_or_die(const char *path, const char *mode) +{ + FILE *filep = fopen(path, "r"); + if (!filep) + err(1, "%s: open failed", path); + return filep; +} + +/* + * Parse a file containing a single int. + */ +int parse_int_file(const char *fmt, ...) +{ + va_list args; + char path[PATH_MAX]; + FILE *filep; + int value; + + va_start(args, fmt); + vsnprintf(path, sizeof(path), fmt, args); + va_end(args); + filep = fopen_or_die(path, "r"); + if (fscanf(filep, "%d", &value) != 1) + err(1, "%s: failed to parse number from file", path); + fclose(filep); + return value; +} + +/* * cpu_is_first_sibling_in_core(cpu) * return 1 if given CPU is 1st HT sibling in the core */ int cpu_is_first_sibling_in_core(int cpu) { - char path[64]; - FILE *filep; - int first_cpu; - - sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu); - filep = fopen(path, "r"); - if (filep == NULL) { - perror(path); - exit(1); - } - fscanf(filep, "%d", &first_cpu); - fclose(filep); - return (cpu == first_cpu); + return cpu == parse_int_file("/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu); } /* @@ -1199,53 +1281,17 @@ int cpu_is_first_sibling_in_core(int cpu) */ int cpu_is_first_core_in_package(int cpu) { - char path[64]; - FILE *filep; - int first_cpu; - - sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/core_siblings_list", cpu); - filep = fopen(path, "r"); - if (filep == NULL) { - perror(path); - exit(1); - } - fscanf(filep, "%d", &first_cpu); - fclose(filep); - return (cpu == first_cpu); + return cpu == parse_int_file("/sys/devices/system/cpu/cpu%d/topology/core_siblings_list", cpu); } int get_physical_package_id(int cpu) { - char path[80]; - FILE *filep; - int pkg; - - sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/physical_package_id", cpu); - filep = fopen(path, "r"); - if (filep == NULL) { - perror(path); - exit(1); - } - fscanf(filep, "%d", &pkg); - fclose(filep); - return pkg; + return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/physical_package_id", cpu); } int get_core_id(int cpu) { - char path[80]; - FILE *filep; - int core; - - sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/core_id", cpu); - filep = fopen(path, "r"); - if (filep == NULL) { - perror(path); - exit(1); - } - fscanf(filep, "%d", &core); - fclose(filep); - return core; + return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/core_id", cpu); } int get_num_ht_siblings(int cpu) @@ -1257,11 +1303,7 @@ int get_num_ht_siblings(int cpu) char character; sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu); - filep = fopen(path, "r"); - if (filep == NULL) { - perror(path); - exit(1); - } + filep = fopen_or_die(path, "r"); /* * file format: * if a pair of number with a character between: 2 siblings (eg. 1-2, or 1,4) @@ -1331,17 +1373,11 @@ int for_all_proc_cpus(int (func)(int)) int cpu_num; int retval; - fp = fopen(proc_stat, "r"); - if (fp == NULL) { - perror(proc_stat); - exit(1); - } + fp = fopen_or_die(proc_stat, "r"); retval = fscanf(fp, "cpu %*d %*d %*d %*d %*d %*d %*d %*d %*d %*d\n"); - if (retval != 0) { - perror("/proc/stat format"); - exit(1); - } + if (retval != 0) + err(1, "%s: failed to parse format", proc_stat); while (1) { retval = fscanf(fp, "cpu%u %*d %*d %*d %*d %*d %*d %*d %*d %*d %*d\n", &cpu_num); @@ -1445,19 +1481,15 @@ void check_dev_msr() { struct stat sb; - if (stat("/dev/cpu/0/msr", &sb)) { - fprintf(stderr, "no /dev/cpu/0/msr\n"); - fprintf(stderr, "Try \"# modprobe msr\"\n"); - exit(-5); - } + if (stat("/dev/cpu/0/msr", &sb)) + err(-5, "no /dev/cpu/0/msr\n" + "Try \"# modprobe msr\""); } void check_super_user() { - if (getuid() != 0) { - fprintf(stderr, "must be root\n"); - exit(-6); - } + if (getuid() != 0) + errx(-6, "must be root"); } int has_nehalem_turbo_ratio_limit(unsigned int family, unsigned int model) @@ -1479,7 +1511,7 @@ int has_nehalem_turbo_ratio_limit(unsigned int family, unsigned int model) case 0x3A: /* IVB */ case 0x3E: /* IVB Xeon */ case 0x3C: /* HSW */ - case 0x3F: /* HSW */ + case 0x3F: /* HSX */ case 0x45: /* HSW */ case 0x46: /* HSW */ case 0x37: /* BYT */ @@ -1595,11 +1627,13 @@ void rapl_probe(unsigned int family, unsigned int model) case 0x2A: case 0x3A: case 0x3C: /* HSW */ - case 0x3F: /* HSW */ case 0x45: /* HSW */ case 0x46: /* HSW */ do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_GFX | RAPL_PKG_POWER_INFO; break; + case 0x3F: /* HSX */ + do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO; + break; case 0x2D: case 0x3E: do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_PKG_PERF_STATUS | RAPL_DRAM_PERF_STATUS | RAPL_PKG_POWER_INFO; @@ -1978,7 +2012,7 @@ void check_cpuid() eax = ebx = ecx = edx = 0; - asm("cpuid" : "=a" (max_level), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0)); + __get_cpuid(0, &max_level, &ebx, &ecx, &edx); if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e) genuine_intel = 1; @@ -1987,7 +2021,7 @@ void check_cpuid() fprintf(stderr, "CPUID(0): %.4s%.4s%.4s ", (char *)&ebx, (char *)&edx, (char *)&ecx); - asm("cpuid" : "=a" (fms), "=c" (ecx), "=d" (edx) : "a" (1) : "ebx"); + __get_cpuid(1, &fms, &ebx, &ecx, &edx); family = (fms >> 8) & 0xf; model = (fms >> 4) & 0xf; stepping = fms & 0xf; @@ -1998,10 +2032,8 @@ void check_cpuid() fprintf(stderr, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n", max_level, family, model, stepping, family, model, stepping); - if (!(edx & (1 << 5))) { - fprintf(stderr, "CPUID: no MSR\n"); - exit(1); - } + if (!(edx & (1 << 5))) + errx(1, "CPUID: no MSR"); /* * check max extended function levels of CPUID. @@ -2009,31 +2041,27 @@ void check_cpuid() * This check is valid for both Intel and AMD. */ ebx = ecx = edx = 0; - asm("cpuid" : "=a" (max_level), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x80000000)); + __get_cpuid(0x80000000, &max_level, &ebx, &ecx, &edx); - if (max_level < 0x80000007) { - fprintf(stderr, "CPUID: no invariant TSC (max_level 0x%x)\n", max_level); - exit(1); - } + if (max_level < 0x80000007) + errx(1, "CPUID: no invariant TSC (max_level 0x%x)", max_level); /* * Non-Stop TSC is advertised by CPUID.EAX=0x80000007: EDX.bit8 * this check is valid for both Intel and AMD */ - asm("cpuid" : "=a" (eax), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x80000007)); + __get_cpuid(0x80000007, &eax, &ebx, &ecx, &edx); has_invariant_tsc = edx & (1 << 8); - if (!has_invariant_tsc) { - fprintf(stderr, "No invariant TSC\n"); - exit(1); - } + if (!has_invariant_tsc) + errx(1, "No invariant TSC"); /* * APERF/MPERF is advertised by CPUID.EAX=0x6: ECX.bit0 * this check is valid for both Intel and AMD */ - asm("cpuid" : "=a" (eax), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x6)); + __get_cpuid(0x6, &eax, &ebx, &ecx, &edx); has_aperf = ecx & (1 << 0); do_dts = eax & (1 << 0); do_ptm = eax & (1 << 6); @@ -2047,7 +2075,7 @@ void check_cpuid() has_epb ? ", EPB": ""); if (!has_aperf) - exit(-1); + errx(-1, "No APERF"); do_nehalem_platform_info = genuine_intel && has_invariant_tsc; do_nhm_cstates = genuine_intel; /* all Intel w/ non-stop TSC have NHM counters */ @@ -2067,9 +2095,8 @@ void check_cpuid() void usage() { - fprintf(stderr, "%s: [-v][-R][-T][-p|-P|-S][-c MSR# | -s]][-C MSR#][-m MSR#][-M MSR#][-i interval_sec | command ...]\n", - progname); - exit(1); + errx(1, "%s: [-v][-R][-T][-p|-P|-S][-c MSR#][-C MSR#][-m MSR#][-M MSR#][-i interval_sec | command ...]\n", + progname); } @@ -2112,19 +2139,15 @@ void topology_probe() fprintf(stderr, "num_cpus %d max_cpu_num %d\n", topo.num_cpus, topo.max_cpu_num); cpus = calloc(1, (topo.max_cpu_num + 1) * sizeof(struct cpu_topology)); - if (cpus == NULL) { - perror("calloc cpus"); - exit(1); - } + if (cpus == NULL) + err(1, "calloc cpus"); /* * Allocate and initialize cpu_present_set */ cpu_present_set = CPU_ALLOC((topo.max_cpu_num + 1)); - if (cpu_present_set == NULL) { - perror("CPU_ALLOC"); - exit(3); - } + if (cpu_present_set == NULL) + err(3, "CPU_ALLOC"); cpu_present_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1)); CPU_ZERO_S(cpu_present_setsize, cpu_present_set); for_all_proc_cpus(mark_cpu_present); @@ -2133,10 +2156,8 @@ void topology_probe() * Allocate and initialize cpu_affinity_set */ cpu_affinity_set = CPU_ALLOC((topo.max_cpu_num + 1)); - if (cpu_affinity_set == NULL) { - perror("CPU_ALLOC"); - exit(3); - } + if (cpu_affinity_set == NULL) + err(3, "CPU_ALLOC"); cpu_affinity_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1)); CPU_ZERO_S(cpu_affinity_setsize, cpu_affinity_set); @@ -2220,8 +2241,7 @@ allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_data return; error: - perror("calloc counters"); - exit(1); + err(1, "calloc counters"); } /* * init_counter() @@ -2276,12 +2296,10 @@ int initialize_counters(int cpu_id) void allocate_output_buffer() { - output_buffer = calloc(1, (1 + topo.num_cpus) * 256); + output_buffer = calloc(1, (1 + topo.num_cpus) * 1024); outp = output_buffer; - if (outp == NULL) { - perror("calloc"); - exit(-1); - } + if (outp == NULL) + err(-1, "calloc output buffer"); } void setup_all_buffers(void) @@ -2292,6 +2310,7 @@ void setup_all_buffers(void) allocate_output_buffer(); for_all_proc_cpus(initialize_counters); } + void turbostat_init() { check_cpuid(); @@ -2335,17 +2354,13 @@ int fork_it(char **argv) } else { /* parent */ - if (child_pid == -1) { - perror("fork"); - exit(1); - } + if (child_pid == -1) + err(1, "fork"); signal(SIGINT, SIG_IGN); signal(SIGQUIT, SIG_IGN); - if (waitpid(child_pid, &status, 0) == -1) { - perror("wait"); - exit(status); - } + if (waitpid(child_pid, &status, 0) == -1) + err(status, "waitpid"); } /* * n.b. fork_it() does not check for errors from for_all_cpus() @@ -2364,13 +2379,30 @@ int fork_it(char **argv) return status; } +int get_and_dump_counters(void) +{ + int status; + + status = for_all_cpus(get_counters, ODD_COUNTERS); + if (status) + return status; + + status = for_all_cpus(dump_counters, ODD_COUNTERS); + if (status) + return status; + + flush_stdout(); + + return status; +} + void cmdline(int argc, char **argv) { int opt; progname = argv[0]; - while ((opt = getopt(argc, argv, "+pPSvi:sc:sC:m:M:RT:")) != -1) { + while ((opt = getopt(argc, argv, "+pPsSvi:c:C:m:M:RJT:")) != -1) { switch (opt) { case 'p': show_core_only++; @@ -2378,6 +2410,9 @@ void cmdline(int argc, char **argv) case 'P': show_pkg_only++; break; + case 's': + dump_only++; + break; case 'S': summary_only++; break; @@ -2405,6 +2440,10 @@ void cmdline(int argc, char **argv) case 'T': tcc_activation_temp_override = atoi(optarg); break; + case 'J': + rapl_joules++; + break; + default: usage(); } @@ -2416,11 +2455,15 @@ int main(int argc, char **argv) cmdline(argc, argv); if (verbose) - fprintf(stderr, "turbostat v3.5 April 26, 2013" + fprintf(stderr, "turbostat v3.6 Dec 2, 2013" " - Len Brown <lenb@kernel.org>\n"); turbostat_init(); + /* dump counters and exit */ + if (dump_only) + return get_and_dump_counters(); + /* * if any params left, it must be a command to fork */ 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/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c index d66418237d21..aa290c0de6f5 100644 --- a/tools/testing/selftests/ipc/msgque.c +++ b/tools/testing/selftests/ipc/msgque.c @@ -201,6 +201,7 @@ int main(int argc, char **argv) msgque.msq_id = msgget(msgque.key, IPC_CREAT | IPC_EXCL | 0666); if (msgque.msq_id == -1) { + err = -errno; printf("Can't create queue\n"); goto err_out; } 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 |