* [Qemu-devel] [PATCH] Instruction counting instrumentation for ARM, 2nd version
@ 2009-06-12 10:56 Sami Kiminki
2009-06-12 15:41 ` Jamie Lokier
` (2 more replies)
0 siblings, 3 replies; 6+ messages in thread
From: Sami Kiminki @ 2009-06-12 10:56 UTC (permalink / raw)
To: qemu-devel
[-- Attachment #1: Type: text/plain, Size: 3235 bytes --]
Hi,
Attached is the second version of Timo Töyry's instruction counting
patch for arm-linux-user targets. Applies to QEMU 0.10.4. To try this,
just add -instrcount to your regular qemu-arm command line. See [1] for
description on how this is implemented.
The patch should now be complete for ARMv6, VFP and Thumb. However,
Thumb2, NEON, and more advanced VFP instrumentation is still missing due
to lacking public documentation from ARM. Measured overhead for
instruction counting using this approach is between 5-35%, and overhead
when the patch is applied but instruction counting disabled is very
close to 0%. See below for details.
Instruction counting can be used to choosing the most appropriate CPU
variant for an embedded application. It can also be used as a part of a
more detailed performance analysis, as instruction mix reflects the
performance of the code.
There are also other ways to implement instruction counting (see
responses to our previous patch [1]). As to our approach, I believe this
is the cleanest way to implement this specific instrumentation. However,
from the general point of view, I'm not so sure. I'd like to ask for
more comments and options.
Two main reasons for us for to construct this patch: First, we needed
the functionality. Second, we're considering using QEMU as a platform
for other instrumentation work too, so we thought to start with
something simple enough.
What we would really like to see is a more general instrumentation
framework, not just instruction counting and not just for ARM targets.
The reason for this is that many measurements are so much easier to do
in emulated/simulated environment than in real HW (e.g. instruction
counting) and doing them in QEMU is way faster than using an ISA
interpreter such as Valgrind. Some other instrumentation examples that
come to my mind are cache usage efficiency analysis, branch profiling,
and naturally instruction and memory access tracing.
A specific bonus of such framework would be that it could be used for
the profiling part of possible future optimizations in code translation.
Consider IA-32 EL (Intel's x86 emulator for Itanium).
Anyways, I'd like to know if there's a general interest in this kind of
framework, and if so, how we should proceed to get it implemented into
mainline.
Regards,
Sami Kiminki
Embedded Software Group / Helsinki University of Technology
References:
[1] http://lists.gnu.org/archive/html/qemu-devel/2009-05/msg00922.html
Overhead measurements
=====================
(Core 2 Q6600, QEMU compiled with gcc 4.3.3 and benchmarks with gcc
4.3.2 (arm1176jzf-s), average of 5 runs)
Vanilla QEMU:
- dhrystone: 1.709 s
- dhrystone thumb: 2.185 s
- mibench/jpeg/cjpeg: 0.453 s
- mibench/mad: 0.822 s
Patched QEMU, instruction counting disabled:
- dhrystone: 1.700 s (-0.5%)
- dhrystone thumb: 2.172 s (-0.6%)
- mibench/jpeg/cjpeg: 0.456 s (+0.7%)
- mibench/mad: 0.820 s (-0.2%)
Patched QEMU, instruction counting enabled:
- dhrystone: 1.882 s (+10%)
- dhrystone thumb: 2.300 s (+5%)
- mibench/jpeg/cjpeg: 0.513 s (+13%)
- mibench/mad: 1.078 s (+31%)
[-- Attachment #2: qemu-0.10.4-instrcount.patch --]
[-- Type: text/x-patch, Size: 95082 bytes --]
diff -urp qemu-0.10.4/Makefile qemu-0.10.4-instrcount/Makefile
--- qemu-0.10.4/Makefile 2009-05-12 17:56:04.000000000 +0300
+++ qemu-0.10.4-instrcount/Makefile 2009-06-12 13:48:01.823613522 +0300
@@ -179,6 +179,10 @@ libqemu_common.a: $(OBJS)
# USER_OBJS is code used by qemu userspace emulation
USER_OBJS=cutils.o cache-utils.o
+# instruction count instrumentation
+USER_OBJS+=instrumentation.o
+
+
libqemu_user.a: $(USER_OBJS)
######################################################################
diff -urp qemu-0.10.4/Makefile.target qemu-0.10.4-instrcount/Makefile.target
--- qemu-0.10.4/Makefile.target 2009-05-12 17:56:04.000000000 +0300
+++ qemu-0.10.4-instrcount/Makefile.target 2009-06-12 13:48:01.817392439 +0300
@@ -208,8 +208,10 @@ ifeq ($(findstring s390, $(TARGET_ARCH)
LIBOBJS+=s390-dis.o
endif
-# libqemu
+# instrumentation support
+LIBOBJS+=instrumentation.o
+# libqemu
libqemu.a: $(LIBOBJS)
translate.o: translate.c cpu.h
Only in qemu-0.10.4-instrcount: instrumentation.c
Only in qemu-0.10.4-instrcount: instrumentation.h
diff -urp qemu-0.10.4/linux-user/main.c qemu-0.10.4-instrcount/linux-user/main.c
--- qemu-0.10.4/linux-user/main.c 2009-05-12 17:56:03.000000000 +0300
+++ qemu-0.10.4-instrcount/linux-user/main.c 2009-06-12 13:48:01.823613522 +0300
@@ -35,6 +35,8 @@
#include "envlist.h"
+#include "instrumentation.h"
+
#define DEBUG_LOGFILE "/tmp/qemu.log"
char *exec_path;
@@ -2199,6 +2201,12 @@ static void usage(void)
"-p pagesize set the host page size to 'pagesize'\n"
"-strace log system calls\n"
"\n"
+#ifdef TARGET_ARM
+ "Other:\n"
+ "-instrcount Count instructions\n"
+ "-instrcountlog=qemu_log Output counters to qemu-log file\n"
+ "\n"
+#endif
"Environment variables:\n"
"QEMU_STRACE Print system calls and arguments similar to the\n"
" 'strace' program. Enable by setting to any value.\n"
@@ -2341,8 +2349,11 @@ int main(int argc, char **argv, char **e
(void) envlist_unsetenv(envlist, "LD_PRELOAD");
} else if (!strcmp(r, "strace")) {
do_strace = 1;
- } else
- {
+ } else if (!strcmp(r, "instrcount")) {
+ instrumentation_count_instructions = 1;
+ } else if (!strcmp(r, "instrcountlog=qemu_log")) {
+ instrumentation_count_instructions_log = 1;
+ } else {
usage();
}
}
diff -urp qemu-0.10.4/linux-user/syscall.c qemu-0.10.4-instrcount/linux-user/syscall.c
--- qemu-0.10.4/linux-user/syscall.c 2009-05-12 17:56:03.000000000 +0300
+++ qemu-0.10.4-instrcount/linux-user/syscall.c 2009-06-12 13:48:01.820280718 +0300
@@ -79,6 +79,9 @@
#include "qemu.h"
#include "qemu-common.h"
+#include "qemu-log.h"
+#include "instrumentation.h"
+
#if defined(USE_NPTL)
#include <linux/futex.h>
#define CLONE_NPTL_FLAGS2 (CLONE_SETTLS | \
@@ -300,6 +303,67 @@ extern int setfsuid(int);
extern int setfsgid(int);
extern int setgroups(int, gid_t *);
+
+inline static void print_counters(const char *buf)
+{
+ if (!instrumentation_count_instructions_log) {
+ fprintf(stderr, "%s", buf);
+ } else {
+ qemu_log("%s", buf);
+ }
+}
+
+inline static void print_instruction_counters_helper(
+ const char **instr_names, int no_instructions, const uint32_t *counters)
+{
+ char buf[256];
+ int i1;
+ uint32_t counted = 0;
+ for (i1 = 0; i1 < no_instructions; i1++) {
+ if (counters[i1] > 0) {
+ sprintf(buf, "%s: %d\n", instr_names[i1],
+ counters[i1]);
+ print_counters(buf);
+ if (i1 < (no_instructions - 2)) {
+ counted += counters[i1];
+ }
+ }
+ }
+ sprintf(buf, "Counted instructions: %d\n", counted);
+ print_counters(buf);
+}
+
+inline static void print_instruction_counters(CPUState *env)
+{
+ char buf[256];
+#ifdef TARGET_ARM
+ if (!instrumentation_count_instructions) return;
+ if (instrumentation_count_instructions_log && !logfile) {
+ fprintf(stderr, "Setting log file to \"qemu_instr_count.log\"\n");
+ cpu_set_log_filename("qemu_instr_count.log");
+ cpu_set_log(1);
+ }
+
+ sprintf(buf, "Arm instructions:\n");
+ print_counters(buf);
+ print_instruction_counters_helper(arm_instr_names, ARM_INSTRUCTIONS,
+ env->arm_instr_count);
+
+ sprintf(buf, "VFP instructions:\n");
+ print_counters(buf);
+ print_instruction_counters_helper(arm_vfp_instr_names,
+ ARM_VFP_INSTRUCTIONS, env->arm_vfp_instr_count);
+
+ sprintf(buf, "Thumb instructions:\n");
+ print_counters(buf);
+ print_instruction_counters_helper(arm_thumb_instr_names,
+ ARM_THUMB_INSTRUCTIONS, env->arm_thumb_instr_count);
+#else
+ sprintf(buf, "Instruction counting not supported in this platform.\n");
+ print_counters(buf);
+#endif
+}
+
#define ERRNO_TABLE_SIZE 1200
/* target_to_host_errno_table[] is initialized from
@@ -3431,6 +3495,7 @@ abi_long do_syscall(void *cpu_env, int n
#ifdef HAVE_GPROF
_mcleanup();
#endif
+ print_instruction_counters(cpu_env);
gdb_exit(cpu_env, arg1);
/* XXX: should free thread stack and CPU env */
sys_exit(arg1);
@@ -4923,6 +4988,7 @@ abi_long do_syscall(void *cpu_env, int n
#ifdef HAVE_GPROF
_mcleanup();
#endif
+ print_instruction_counters(cpu_env);
gdb_exit(cpu_env, arg1);
ret = get_errno(exit_group(arg1));
break;
diff -urp qemu-0.10.4/target-arm/cpu.h qemu-0.10.4-instrcount/target-arm/cpu.h
--- qemu-0.10.4/target-arm/cpu.h 2009-05-12 17:56:33.000000000 +0300
+++ qemu-0.10.4-instrcount/target-arm/cpu.h 2009-06-12 13:48:01.823613522 +0300
@@ -51,6 +51,340 @@
#define ARMV7M_EXCP_PENDSV 14
#define ARMV7M_EXCP_SYSTICK 15
+/* Do not change the order of the instructions in the blocks marked
+ * by - | -. */
+enum arm_instructions {
+ ARM_INSTRUCTION_B,
+ ARM_INSTRUCTION_BL,
+ ARM_INSTRUCTION_BLX,
+ ARM_INSTRUCTION_BX,
+ ARM_INSTRUCTION_BXJ,
+ ARM_INSTRUCTION_ADC,
+ ARM_INSTRUCTION_ADD,
+ ARM_INSTRUCTION_AND,
+ ARM_INSTRUCTION_BIC,
+ ARM_INSTRUCTION_CMN,
+ ARM_INSTRUCTION_CMP,
+ ARM_INSTRUCTION_EOR,
+ ARM_INSTRUCTION_MOV,
+ ARM_INSTRUCTION_MVN,
+ ARM_INSTRUCTION_ORR,
+ ARM_INSTRUCTION_RSB,
+ ARM_INSTRUCTION_RSC,
+ ARM_INSTRUCTION_SBC,
+ ARM_INSTRUCTION_SUB,
+ ARM_INSTRUCTION_TEQ,
+ ARM_INSTRUCTION_TST,
+ ARM_INSTRUCTION_MUL, /* - */
+ ARM_INSTRUCTION_MULS, /* - */
+ ARM_INSTRUCTION_MLA, /* - */
+ ARM_INSTRUCTION_MLAS, /* - */
+ ARM_INSTRUCTION_SMLAXY,
+ ARM_INSTRUCTION_SMLAL, /* - */
+ ARM_INSTRUCTION_SMLALS, /* - */
+ ARM_INSTRUCTION_SMLALXY,
+ ARM_INSTRUCTION_SMLAWY,
+ ARM_INSTRUCTION_SMUAD, /* - */
+ ARM_INSTRUCTION_SMUSD, /* | */
+ ARM_INSTRUCTION_SMLAD, /* | */
+ ARM_INSTRUCTION_SMLSD, /* - */
+ ARM_INSTRUCTION_SMLALD, /* - */
+ ARM_INSTRUCTION_SMLSLD, /* - */
+ ARM_INSTRUCTION_SMMLA,
+ ARM_INSTRUCTION_SMMLS,
+ ARM_INSTRUCTION_SMMUL,
+ ARM_INSTRUCTION_SMULXY,
+ ARM_INSTRUCTION_SMULL, /* - */
+ ARM_INSTRUCTION_SMULLS, /* - */
+ ARM_INSTRUCTION_SMULWY,
+ ARM_INSTRUCTION_UMAAL,
+ ARM_INSTRUCTION_UMLAL, /* - */
+ ARM_INSTRUCTION_UMLALS, /* - */
+ ARM_INSTRUCTION_UMULL, /* - */
+ ARM_INSTRUCTION_UMULLS, /* - */
+ ARM_INSTRUCTION_QADD,
+ ARM_INSTRUCTION_QDADD,
+ ARM_INSTRUCTION_QADD16, /* - */
+ ARM_INSTRUCTION_QADDSUBX, /* | */
+ ARM_INSTRUCTION_QSUBADDX, /* | */
+ ARM_INSTRUCTION_QSUB16, /* | */
+ ARM_INSTRUCTION_QADD8, /* | */
+ ARM_INSTRUCTION_QSUB8, /* - */
+ ARM_INSTRUCTION_QSUB,
+ ARM_INSTRUCTION_QDSUB,
+ ARM_INSTRUCTION_SADD16, /* - */
+ ARM_INSTRUCTION_SADDSUBX, /* | */
+ ARM_INSTRUCTION_SSUBADDX, /* | */
+ ARM_INSTRUCTION_SSUB16, /* | */
+ ARM_INSTRUCTION_SADD8, /* | */
+ ARM_INSTRUCTION_SSUB8, /* - */
+ ARM_INSTRUCTION_SHADD16, /* - */
+ ARM_INSTRUCTION_SHADDSUBX, /* | */
+ ARM_INSTRUCTION_SHSUBADDX, /* | */
+ ARM_INSTRUCTION_SHSUB16, /* | */
+ ARM_INSTRUCTION_SHADD8, /* | */
+ ARM_INSTRUCTION_SHSUB8, /* - */
+ ARM_INSTRUCTION_UADD16, /* - */
+ ARM_INSTRUCTION_UADDSUBX, /* | */
+ ARM_INSTRUCTION_USUBADDX, /* | */
+ ARM_INSTRUCTION_USUB16, /* | */
+ ARM_INSTRUCTION_UADD8, /* | */
+ ARM_INSTRUCTION_USUB8, /* - */
+ ARM_INSTRUCTION_UHADD16, /* - */
+ ARM_INSTRUCTION_UHADDSUBX, /* | */
+ ARM_INSTRUCTION_UHSUBADDX, /* | */
+ ARM_INSTRUCTION_UHSUB16, /* | */
+ ARM_INSTRUCTION_UHADD8, /* | */
+ ARM_INSTRUCTION_UHSUB8, /* - */
+ ARM_INSTRUCTION_UQADD16, /* - */
+ ARM_INSTRUCTION_UQADDSUBX, /* | */
+ ARM_INSTRUCTION_UQSUBADDX, /* | */
+ ARM_INSTRUCTION_UQSUB16, /* | */
+ ARM_INSTRUCTION_UQADD8, /* | */
+ ARM_INSTRUCTION_UQSUB8, /* - */
+ ARM_INSTRUCTION_SXTAB16, /* - */
+ ARM_INSTRUCTION_SXTAB, /* | */
+ ARM_INSTRUCTION_SXTAH, /* | */
+ ARM_INSTRUCTION_SXTB16, /* | */
+ ARM_INSTRUCTION_SXTB, /* | */
+ ARM_INSTRUCTION_SXTH, /* - */
+ ARM_INSTRUCTION_UXTAB16, /* - */
+ ARM_INSTRUCTION_UXTAB, /* | */
+ ARM_INSTRUCTION_UXTAH, /* | */
+ ARM_INSTRUCTION_UXTB16, /* | */
+ ARM_INSTRUCTION_UXTB, /* | */
+ ARM_INSTRUCTION_UXTH, /* - */
+ ARM_INSTRUCTION_CLZ,
+ ARM_INSTRUCTION_USAD8,
+ ARM_INSTRUCTION_USADA8,
+ ARM_INSTRUCTION_PKH,
+ ARM_INSTRUCTION_PKHBT,
+ ARM_INSTRUCTION_PKHTB,
+ ARM_INSTRUCTION_REV,
+ ARM_INSTRUCTION_REV16,
+ ARM_INSTRUCTION_REVSH,
+ ARM_INSTRUCTION_SEL,
+ ARM_INSTRUCTION_SSAT,
+ ARM_INSTRUCTION_SSAT16,
+ ARM_INSTRUCTION_USAT,
+ ARM_INSTRUCTION_USAT16,
+ ARM_INSTRUCTION_MRS,
+ ARM_INSTRUCTION_MSR,
+ ARM_INSTRUCTION_CPS,
+ ARM_INSTRUCTION_SETEND,
+ ARM_INSTRUCTION_LDR,
+ ARM_INSTRUCTION_LDRB,
+ ARM_INSTRUCTION_LDRBT,
+ ARM_INSTRUCTION_LDRD,
+ ARM_INSTRUCTION_LDREX,
+ ARM_INSTRUCTION_LDRH,
+ ARM_INSTRUCTION_LDRSB,
+ ARM_INSTRUCTION_LDRSH,
+ ARM_INSTRUCTION_LDRT,
+ ARM_INSTRUCTION_STR,
+ ARM_INSTRUCTION_STRB,
+ ARM_INSTRUCTION_STRBT,
+ ARM_INSTRUCTION_STRD,
+ ARM_INSTRUCTION_STREX,
+ ARM_INSTRUCTION_STRH,
+ ARM_INSTRUCTION_STRT,
+ ARM_INSTRUCTION_LDM1, //See Arm manual ARM DDI 0100I page A3-27
+ ARM_INSTRUCTION_LDM2,
+ ARM_INSTRUCTION_LDM3,
+ ARM_INSTRUCTION_STM1,
+ ARM_INSTRUCTION_STM2,
+ ARM_INSTRUCTION_SWP,
+ ARM_INSTRUCTION_SWPB,
+ ARM_INSTRUCTION_BKPT,
+ ARM_INSTRUCTION_SWI,
+ ARM_INSTRUCTION_CDP,
+ ARM_INSTRUCTION_LDC,
+ ARM_INSTRUCTION_MCR,
+ ARM_INSTRUCTION_MCRR,
+ ARM_INSTRUCTION_MRC,
+ ARM_INSTRUCTION_MRRC,
+ ARM_INSTRUCTION_STC,
+ ARM_INSTRUCTION_PLD,
+ ARM_INSTRUCTION_RFE,
+ ARM_INSTRUCTION_SRS,
+ ARM_INSTRUCTION_MCRR2,
+ ARM_INSTRUCTION_MRRC2,
+ ARM_INSTRUCTION_STC2,
+ ARM_INSTRUCTION_LDC2,
+ ARM_INSTRUCTION_CDP2,
+ ARM_INSTRUCTION_MCR2,
+ ARM_INSTRUCTION_MRC2,
+ ARM_INSTRUCTION_COPROCESSOR,
+ ARM_INSTRUCTION_UNKNOWN,
+ ARM_INSTRUCTION_NOT_INSTRUMENTED,
+ ARM_INSTRUCTION_TOTAL_COUNT,
+ ARM_INSTRUCTIONS
+};
+
+/* Do not change the order of the instructions in the blocks marked
+ * by - | -. */
+enum arm_vfp_instructions {
+ ARM_VFP_INSTRUCTION_FABSD, /* - */
+ ARM_VFP_INSTRUCTION_FABSS, /* - */
+ ARM_VFP_INSTRUCTION_FADDD, /* - */
+ ARM_VFP_INSTRUCTION_FADDS, /* - */
+ ARM_VFP_INSTRUCTION_FCMPD, /* - */
+ ARM_VFP_INSTRUCTION_FCMPS, /* - */
+ ARM_VFP_INSTRUCTION_FCMPED, /* - */
+ ARM_VFP_INSTRUCTION_FCMPES, /* - */
+ ARM_VFP_INSTRUCTION_FCMPEZD, /* - */
+ ARM_VFP_INSTRUCTION_FCMPEZS, /* - */
+ ARM_VFP_INSTRUCTION_FCMPZD, /* - */
+ ARM_VFP_INSTRUCTION_FCMPZS, /* - */
+ ARM_VFP_INSTRUCTION_FCPYD, /* - */
+ ARM_VFP_INSTRUCTION_FCPYS, /* - */
+ ARM_VFP_INSTRUCTION_FCVTDS, /* - */
+ ARM_VFP_INSTRUCTION_FCVTSD, /* - */
+ ARM_VFP_INSTRUCTION_FDIVD, /* - */
+ ARM_VFP_INSTRUCTION_FDIVS, /* - */
+ ARM_VFP_INSTRUCTION_FLDD, /* - */
+ ARM_VFP_INSTRUCTION_FLDS, /* - */
+ ARM_VFP_INSTRUCTION_FLDMD, /* - */
+ ARM_VFP_INSTRUCTION_FLDMS, /* - */
+ ARM_VFP_INSTRUCTION_FLDMX,
+ ARM_VFP_INSTRUCTION_FMACD,
+ ARM_VFP_INSTRUCTION_FMACS,
+ ARM_VFP_INSTRUCTION_FMDHR,
+ ARM_VFP_INSTRUCTION_FMDLR,
+ ARM_VFP_INSTRUCTION_FMDRR,
+ ARM_VFP_INSTRUCTION_FMRDH,
+ ARM_VFP_INSTRUCTION_FMRDL,
+ ARM_VFP_INSTRUCTION_FMRRD, /* - */
+ ARM_VFP_INSTRUCTION_FMRRS, /* - */
+ ARM_VFP_INSTRUCTION_FMRS,
+ ARM_VFP_INSTRUCTION_FMRX,
+ ARM_VFP_INSTRUCTION_FMSCD, /* - */
+ ARM_VFP_INSTRUCTION_FMSCS, /* - */
+ ARM_VFP_INSTRUCTION_FMSR,
+ ARM_VFP_INSTRUCTION_FMSRR,
+ ARM_VFP_INSTRUCTION_FMSTAT,
+ ARM_VFP_INSTRUCTION_FMULD, /* - */
+ ARM_VFP_INSTRUCTION_FMULS, /* - */
+ ARM_VFP_INSTRUCTION_FMXR,
+ ARM_VFP_INSTRUCTION_FNEGD, /* - */
+ ARM_VFP_INSTRUCTION_FNEGS, /* - */
+ ARM_VFP_INSTRUCTION_FNMACD, /* - */
+ ARM_VFP_INSTRUCTION_FNMACS, /* - */
+ ARM_VFP_INSTRUCTION_FNMSCD, /* - */
+ ARM_VFP_INSTRUCTION_FNMSCS, /* - */
+ ARM_VFP_INSTRUCTION_FNMULD, /* - */
+ ARM_VFP_INSTRUCTION_FNMULS, /* - */
+ ARM_VFP_INSTRUCTION_FSITOD, /* - */
+ ARM_VFP_INSTRUCTION_FSITOS, /* - */
+ ARM_VFP_INSTRUCTION_FSQRTD, /* - */
+ ARM_VFP_INSTRUCTION_FSQRTS, /* - */
+ ARM_VFP_INSTRUCTION_FSTD, /* - */
+ ARM_VFP_INSTRUCTION_FSTS, /* - */
+ ARM_VFP_INSTRUCTION_FSTMD,
+ ARM_VFP_INSTRUCTION_FSTMS,
+ ARM_VFP_INSTRUCTION_FSTMX,
+ ARM_VFP_INSTRUCTION_FSUBD, /* - */
+ ARM_VFP_INSTRUCTION_FSUBS, /* - */
+ ARM_VFP_INSTRUCTION_FTOSID, /* - */
+ ARM_VFP_INSTRUCTION_FTOSIS, /* - */
+ ARM_VFP_INSTRUCTION_FTOSIZD, /* - */
+ ARM_VFP_INSTRUCTION_FTOSIZS, /* - */
+ ARM_VFP_INSTRUCTION_FTOUID, /* - */
+ ARM_VFP_INSTRUCTION_FTOUIS, /* - */
+ ARM_VFP_INSTRUCTION_FTOUIZD, /* - */
+ ARM_VFP_INSTRUCTION_FTOUIZS, /* - */
+ ARM_VFP_INSTRUCTION_FUITOD, /* - */
+ ARM_VFP_INSTRUCTION_FUITOS, /* - */
+ ARM_VFP_INSTRUCTION_UNKNOWN,
+ ARM_VFP_INSTRUCTION_NOT_INSTRUMENTED,
+ ARM_VFP_INSTRUCTION_TOTAL_COUNT,
+ ARM_VFP_INSTRUCTIONS
+};
+
+/* Do not change the order of the instructions in the blocks marked
+ * by - | -. */
+enum arm_thumb_instructions {
+ ARM_THUMB_INSTRUCTION_ADC,
+ ARM_THUMB_INSTRUCTION_ADD1, /* - */
+ ARM_THUMB_INSTRUCTION_ADD2, /* | */
+ ARM_THUMB_INSTRUCTION_ADD3, /* - */
+ ARM_THUMB_INSTRUCTION_ADD4,
+ ARM_THUMB_INSTRUCTION_ADD5,
+ ARM_THUMB_INSTRUCTION_ADD6,
+ ARM_THUMB_INSTRUCTION_ADD7,
+ ARM_THUMB_INSTRUCTION_AND,
+ ARM_THUMB_INSTRUCTION_ASR1,
+ ARM_THUMB_INSTRUCTION_ASR2,
+ ARM_THUMB_INSTRUCTION_B1,
+ ARM_THUMB_INSTRUCTION_B2,
+ ARM_THUMB_INSTRUCTION_BIC,
+ ARM_THUMB_INSTRUCTION_BKPT,
+ ARM_THUMB_INSTRUCTION_BL,
+ ARM_THUMB_INSTRUCTION_BLX1,
+ ARM_THUMB_INSTRUCTION_BLX2,
+ ARM_THUMB_INSTRUCTION_BL_BLX_HIGH_PART,
+ ARM_THUMB_INSTRUCTION_BX,
+ ARM_THUMB_INSTRUCTION_CMN,
+ ARM_THUMB_INSTRUCTION_CMP1,
+ ARM_THUMB_INSTRUCTION_CMP2,
+ ARM_THUMB_INSTRUCTION_CMP3,
+ ARM_THUMB_INSTRUCTION_CPS,
+ ARM_THUMB_INSTRUCTION_CPY,
+ ARM_THUMB_INSTRUCTION_EOR,
+ ARM_THUMB_INSTRUCTION_LDMIA,
+ ARM_THUMB_INSTRUCTION_LDR1,
+ ARM_THUMB_INSTRUCTION_LDR2,
+ ARM_THUMB_INSTRUCTION_LDR3,
+ ARM_THUMB_INSTRUCTION_LDR4,
+ ARM_THUMB_INSTRUCTION_LDRB1,
+ ARM_THUMB_INSTRUCTION_LDRB2,
+ ARM_THUMB_INSTRUCTION_LDRH1,
+ ARM_THUMB_INSTRUCTION_LDRH2,
+ ARM_THUMB_INSTRUCTION_LDRSB,
+ ARM_THUMB_INSTRUCTION_LDRSH,
+ ARM_THUMB_INSTRUCTION_LSL1,
+ ARM_THUMB_INSTRUCTION_LSL2,
+ ARM_THUMB_INSTRUCTION_LSR1,
+ ARM_THUMB_INSTRUCTION_LSR2,
+ ARM_THUMB_INSTRUCTION_MOV1,
+ ARM_THUMB_INSTRUCTION_MOV2,
+ ARM_THUMB_INSTRUCTION_MOV3,
+ ARM_THUMB_INSTRUCTION_MUL,
+ ARM_THUMB_INSTRUCTION_MVN,
+ ARM_THUMB_INSTRUCTION_NEG,
+ ARM_THUMB_INSTRUCTION_ORR,
+ ARM_THUMB_INSTRUCTION_POP,
+ ARM_THUMB_INSTRUCTION_PUSH,
+ ARM_THUMB_INSTRUCTION_REV,
+ ARM_THUMB_INSTRUCTION_REV16,
+ ARM_THUMB_INSTRUCTION_REVSH,
+ ARM_THUMB_INSTRUCTION_ROR,
+ ARM_THUMB_INSTRUCTION_SBC,
+ ARM_THUMB_INSTRUCTION_SETEND,
+ ARM_THUMB_INSTRUCTION_STMIA,
+ ARM_THUMB_INSTRUCTION_STR1,
+ ARM_THUMB_INSTRUCTION_STR2,
+ ARM_THUMB_INSTRUCTION_STR3,
+ ARM_THUMB_INSTRUCTION_STRB1,
+ ARM_THUMB_INSTRUCTION_STRB2,
+ ARM_THUMB_INSTRUCTION_STRH1,
+ ARM_THUMB_INSTRUCTION_STRH2,
+ ARM_THUMB_INSTRUCTION_SUB1, /* - */
+ ARM_THUMB_INSTRUCTION_SUB2, /* | */
+ ARM_THUMB_INSTRUCTION_SUB3, /* - */
+ ARM_THUMB_INSTRUCTION_SUB4,
+ ARM_THUMB_INSTRUCTION_SWI,
+ ARM_THUMB_INSTRUCTION_SXTB,
+ ARM_THUMB_INSTRUCTION_SXTH,
+ ARM_THUMB_INSTRUCTION_TST,
+ ARM_THUMB_INSTRUCTION_UXTB,
+ ARM_THUMB_INSTRUCTION_UXTH,
+ ARM_THUMB_INSTRUCTION_UNKNOWN,
+ ARM_THUMB_INSTRUCTION_NOT_INSTRUMENTED,
+ ARM_THUMB_INSTRUCTION_TOTAL_COUNT,
+ ARM_THUMB_INSTRUCTIONS
+};
+
typedef void ARMWriteCPFunc(void *opaque, int cp_info,
int srcreg, int operand, uint32_t value);
typedef uint32_t ARMReadCPFunc(void *opaque, int cp_info,
@@ -202,6 +536,12 @@ typedef struct CPUARMState {
/* These fields after the common ones so they are preserved on reset. */
struct arm_boot_info *boot_info;
+
+ /* Instruction counting "regs". */
+ uint32_t arm_instr_count[ARM_INSTRUCTIONS];
+ uint32_t arm_vfp_instr_count[ARM_VFP_INSTRUCTIONS];
+ uint32_t arm_thumb_instr_count[ARM_THUMB_INSTRUCTIONS];
+
} CPUARMState;
CPUARMState *cpu_arm_init(const char *cpu_model);
@@ -446,4 +786,8 @@ static inline void cpu_get_tb_cpu_state(
*flags |= (1 << 7);
}
+extern const char const *arm_instr_names[];
+extern const char const *arm_vfp_instr_names[];
+extern const char const *arm_thumb_instr_names[];
+
#endif
diff -urp qemu-0.10.4/target-arm/translate.c qemu-0.10.4-instrcount/target-arm/translate.c
--- qemu-0.10.4/target-arm/translate.c 2009-05-12 17:56:33.000000000 +0300
+++ qemu-0.10.4-instrcount/target-arm/translate.c 2009-06-12 13:48:01.862626316 +0300
@@ -31,6 +31,8 @@
#include "tcg-op.h"
#include "qemu-log.h"
+#include "instrumentation.h"
+
#include "helpers.h"
#define GEN_HELPER 1
#include "helpers.h"
@@ -235,6 +237,365 @@ static void store_reg(DisasContext *s, i
/* Set NZCV flags from the high 4 bits of var. */
#define gen_set_nzcv(var) gen_set_cpsr(var, CPSR_NZCV)
+/* string names for arm_instruction enum values */
+const char const *arm_instr_names[] = {
+ "b",
+ "bl",
+ "blx",
+ "bx",
+ "bxj",
+ "adc",
+ "add",
+ "and",
+ "bic",
+ "cmn",
+ "cmp",
+ "eor",
+ "mov",
+ "mvn",
+ "orr",
+ "rsb",
+ "rsc",
+ "sbc",
+ "sub",
+ "teq",
+ "tst",
+ "mul",
+ "muls",
+ "mla",
+ "mlas",
+ "smla<x><y>",
+ "smlal",
+ "smlals",
+ "smlal<x><y>",
+ "smlaw<y>",
+ "smuad",
+ "smusd",
+ "smlad",
+ "smlsd",
+ "smlald",
+ "smlsld",
+ "smmla",
+ "smmls",
+ "smmul",
+ "smul<x><y>",
+ "smull",
+ "smulls",
+ "smulw<y>",
+ "umaal",
+ "umlal",
+ "umlals",
+ "umull",
+ "umulls",
+ "qadd",
+ "qdadd",
+ "qadd16",
+ "qaddsubx",
+ "qsubaddx",
+ "qsub16",
+ "qadd8",
+ "qsub8",
+ "qsub",
+ "qdsub",
+ "sadd16",
+ "saddsubx",
+ "ssubaddx",
+ "ssub16",
+ "sadd8",
+ "ssub8",
+ "shadd16",
+ "shaddsubx",
+ "shsubaddx",
+ "shsub16",
+ "shadd8",
+ "shsub8",
+ "uadd16",
+ "uaddsubx",
+ "usubaddx",
+ "usub16",
+ "uadd8",
+ "usub8",
+ "uhadd16",
+ "uhaddsubx",
+ "uhsubaddx",
+ "uhsub16",
+ "uhadd8",
+ "uhsub8",
+ "uqadd16",
+ "uqaddsubx",
+ "uqsubaddx",
+ "uqsub16",
+ "uqadd8",
+ "uqsub8",
+ "sxtab16",
+ "sxtab",
+ "sxtah",
+ "sxtb16",
+ "sxtb",
+ "sxth",
+ "uxtab16",
+ "uxtab",
+ "uxtah",
+ "uxtb16",
+ "uxtb",
+ "uxth",
+ "clz",
+ "usad8",
+ "usada8",
+ "pkh",
+ "pkhbt",
+ "pkhtb",
+ "rev",
+ "rev16",
+ "revsh",
+ "sel",
+ "ssat",
+ "ssat16",
+ "usat",
+ "usat16",
+ "mrs",
+ "msr",
+ "cps",
+ "setend",
+ "ldr",
+ "ldrb",
+ "ldrbt",
+ "ldrd",
+ "ldrex",
+ "ldrh",
+ "ldrsb",
+ "ldrsh",
+ "ldrt",
+ "str",
+ "strb",
+ "strbt",
+ "strd",
+ "strex",
+ "strh",
+ "strt",
+ "ldm1", //see arm manual ARM DDI 0100I page A3-27
+ "ldm2",
+ "ldm3",
+ "stm1",
+ "stm2",
+ "swp",
+ "swpb",
+ "bkpt",
+ "swi",
+ "cdp",
+ "ldc",
+ "mcr",
+ "mcrr",
+ "mrc",
+ "mrrc",
+ "stc",
+ "pld",
+ "rfe",
+ "srs",
+ "mcrr2",
+ "mrrc2",
+ "stc2",
+ "ldc2",
+ "cdp2",
+ "mcr2",
+ "mrc2",
+ "coprocessor",
+ "unknown",
+ "not_instrumented",
+ "total_instructions"
+};
+
+const char const *arm_vfp_instr_names[] = { /* string names for arm_vfp_instruction enum values */
+ "fabsd",
+ "fabss",
+ "faddd",
+ "fadds",
+ "fcmpd",
+ "fcmps",
+ "fcmped",
+ "fcmpes",
+ "fcmpezd",
+ "fcmpezs",
+ "fcmpzd",
+ "fcmpzs",
+ "fcpyd",
+ "fcpys",
+ "fcvtds",
+ "fcvtsd",
+ "fdivd",
+ "fdivs",
+ "fldd",
+ "flds",
+ "fldmd",
+ "fldms",
+ "fldmx",
+ "fmacd",
+ "fmacs",
+ "fmdhr",
+ "fmdlr",
+ "fmdrr",
+ "fmrdh",
+ "fmrdl",
+ "fmrrd",
+ "fmrrs",
+ "fmrs",
+ "fmrx",
+ "fmscd",
+ "fmscs",
+ "fmsr",
+ "fmsrr",
+ "fmstat",
+ "fmuld",
+ "fmuls",
+ "fmxr",
+ "fnegd",
+ "fnegs",
+ "fnmacd",
+ "fnmacs",
+ "fnmscd",
+ "fnmscs",
+ "fnmuld",
+ "fnmuls",
+ "fsitod",
+ "fsitos",
+ "fsqrtd",
+ "fsqrts",
+ "fstd",
+ "fsts",
+ "fstmd",
+ "fstms",
+ "fstmx",
+ "fsubd",
+ "fsubs",
+ "ftosid",
+ "ftosis",
+ "ftosizd",
+ "ftosizs",
+ "ftouid",
+ "ftouis",
+ "ftouizd",
+ "ftouizs",
+ "fuitod",
+ "fuitos",
+ "unknown",
+ "not_instrumented",
+ "total_count"
+};
+
+/* string names for arm_thumb_instruction enum values */
+const char const *arm_thumb_instr_names[] = {
+ "adc",
+ "add1",
+ "add2",
+ "add3",
+ "add4",
+ "add5",
+ "add6",
+ "add7",
+ "and",
+ "asr1",
+ "asr2",
+ "b1",
+ "b2",
+ "bic",
+ "bkpt",
+ "bl",
+ "blx1",
+ "blx2",
+ "bl-blx_high",
+ "bx",
+ "cmn",
+ "cmp1",
+ "cmp2",
+ "cmp3",
+ "cps",
+ "cpy",
+ "eor",
+ "ldmia",
+ "ldr1",
+ "ldr2",
+ "ldr3",
+ "ldr4",
+ "ldrb1",
+ "ldrb2",
+ "ldrh1",
+ "ldrh2",
+ "ldrsb",
+ "ldrsh",
+ "lsl1",
+ "lsl2",
+ "lsr1",
+ "lsr2",
+ "mov1",
+ "mov2",
+ "mov3",
+ "mul",
+ "mvn",
+ "neg",
+ "orr",
+ "pop",
+ "push",
+ "rev",
+ "rev16",
+ "revsh",
+ "ror",
+ "sbc",
+ "setend",
+ "stmia",
+ "str1",
+ "str2",
+ "str3",
+ "strb1",
+ "strb2",
+ "strh1",
+ "strh2",
+ "sub1",
+ "sub2",
+ "sub3",
+ "sub4",
+ "swi",
+ "sxtb",
+ "sxth",
+ "tst",
+ "uxtb",
+ "uxth",
+ "unknown",
+ "not_instrumented",
+ "total_count",
+};
+
+#define ARM_INSTRUCTION_COUNTER_OFFSET offsetof(CPUState, arm_instr_count)
+#define ARM_VFP_INSTRUCTION_COUNTER_OFFSET offsetof(CPUState, arm_vfp_instr_count)
+#define ARM_THUMB_INSTRUCTION_COUNTER_OFFSET offsetof(CPUState, arm_thumb_instr_count)
+
+typedef struct instr_counter_offsets {
+ uint32_t cpustate_offset;
+ TCGArg *tcg_offset[2];
+} instr_counter_offsets;
+
+static instr_counter_offsets instr_offsets;
+
+static inline void instr_count_inc_init(uint32_t offset, int instr)
+{
+ if (!instrumentation_count_instructions) return;
+ instr_offsets.cpustate_offset = offset;
+ TCGv tmp = new_tmp();
+ tcg_gen_ld_i32(tmp, cpu_env, instr_offsets.cpustate_offset + sizeof(uint32_t) * instr);
+ instr_offsets.tcg_offset[0] = gen_opparam_ptr - 1;
+ tcg_gen_addi_i32(tmp, tmp, 1);
+ tcg_gen_st_i32(tmp, cpu_env, instr_offsets.cpustate_offset + sizeof(uint32_t) * instr);
+ instr_offsets.tcg_offset[1] = gen_opparam_ptr - 1;
+ dead_tmp(tmp);
+}
+
+/* Increment instruction counter */
+static inline void instr_count_inc(int instr)
+{
+ if (!instrumentation_count_instructions) return;
+ *(instr_offsets.tcg_offset[0]) = instr_offsets.cpustate_offset + sizeof(uint32_t) * instr;
+ *(instr_offsets.tcg_offset[1]) = instr_offsets.cpustate_offset + sizeof(uint32_t) * instr;
+}
+
static void gen_exception(int excp)
{
TCGv tmp = new_tmp();
@@ -580,6 +941,7 @@ static inline void gen_arm_shift_reg(TCG
static void gen_arm_parallel_addsub(int op1, int op2, TCGv a, TCGv b)
{
TCGv_ptr tmp;
+ unsigned int instr_index = 0;
switch (op1) {
#define gen_pas_helper(name) glue(gen_helper_,name)(a, a, b, tmp)
@@ -587,28 +949,37 @@ static void gen_arm_parallel_addsub(int
tmp = tcg_temp_new_ptr();
tcg_gen_addi_ptr(tmp, cpu_env, offsetof(CPUState, GE));
PAS_OP(s)
+ instr_index = ARM_INSTRUCTION_SADD16;
break;
case 5:
tmp = tcg_temp_new_ptr();
tcg_gen_addi_ptr(tmp, cpu_env, offsetof(CPUState, GE));
PAS_OP(u)
+ instr_index = ARM_INSTRUCTION_UADD16;
break;
#undef gen_pas_helper
#define gen_pas_helper(name) glue(gen_helper_,name)(a, a, b)
case 2:
PAS_OP(q);
+ instr_index = ARM_INSTRUCTION_QADD16;
break;
case 3:
PAS_OP(sh);
+ instr_index = ARM_INSTRUCTION_SHADD16;
break;
case 6:
PAS_OP(uq);
+ instr_index = ARM_INSTRUCTION_UQADD16;
break;
case 7:
PAS_OP(uh);
+ instr_index = ARM_INSTRUCTION_UHADD16;
break;
#undef gen_pas_helper
}
+ if (op2 == 7) instr_index += 5;
+ else instr_index += op2;
+ instr_count_inc(instr_index);
}
#undef PAS_OP
@@ -2702,6 +3073,9 @@ static int disas_vfp_insn(CPUState * env
TCGv tmp;
TCGv tmp2;
+ instr_count_inc_init(ARM_VFP_INSTRUCTION_COUNTER_OFFSET,
+ ARM_VFP_INSTRUCTION_NOT_INSTRUMENTED);
+
if (!arm_feature(env, ARM_FEATURE_VFP))
return 1;
@@ -2724,6 +3098,8 @@ static int disas_vfp_insn(CPUState * env
int size;
int pass;
+ instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN);
+
VFP_DREG_N(rn, insn);
if (insn & 0xf)
return 1;
@@ -2770,6 +3146,11 @@ static int disas_vfp_insn(CPUState * env
}
break;
case 2:
+ if (pass) {
+ instr_count_inc(ARM_VFP_INSTRUCTION_FMRDH);
+ } else {
+ instr_count_inc(ARM_VFP_INSTRUCTION_FMRDL);
+ }
break;
}
store_reg(s, rd, tmp);
@@ -2801,6 +3182,11 @@ static int disas_vfp_insn(CPUState * env
dead_tmp(tmp2);
break;
case 2:
+ if (pass) {
+ instr_count_inc(ARM_VFP_INSTRUCTION_FMDHR);
+ } else {
+ instr_count_inc(ARM_VFP_INSTRUCTION_FMDLR);
+ }
break;
}
neon_store_reg(rn, pass, tmp);
@@ -2814,6 +3200,7 @@ static int disas_vfp_insn(CPUState * env
/* vfp->arm */
if (insn & (1 << 21)) {
/* system register */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FMRX);
rn >>= 1;
switch (rn) {
@@ -2841,6 +3228,7 @@ static int disas_vfp_insn(CPUState * env
break;
case ARM_VFP_FPSCR:
if (rd == 15) {
+ instr_count_inc(ARM_VFP_INSTRUCTION_FMSTAT);
tmp = load_cpu_field(vfp.xregs[ARM_VFP_FPSCR]);
tcg_gen_andi_i32(tmp, tmp, 0xf0000000);
} else {
@@ -2859,6 +3247,7 @@ static int disas_vfp_insn(CPUState * env
return 1;
}
} else {
+ instr_count_inc(ARM_VFP_INSTRUCTION_FMRS);
gen_mov_F0_vreg(0, rn);
tmp = gen_vfp_mrs();
}
@@ -2873,6 +3262,7 @@ static int disas_vfp_insn(CPUState * env
/* arm->vfp */
tmp = load_reg(s, rd);
if (insn & (1 << 21)) {
+ instr_count_inc(ARM_VFP_INSTRUCTION_FMXR);
rn >>= 1;
/* system register */
switch (rn) {
@@ -2900,6 +3290,7 @@ static int disas_vfp_insn(CPUState * env
return 1;
}
} else {
+ instr_count_inc(ARM_VFP_INSTRUCTION_FMSR);
gen_vfp_msr(tmp);
gen_mov_vreg_F0(0, rn);
}
@@ -3023,44 +3414,54 @@ static int disas_vfp_insn(CPUState * env
/* Perform the calculation. */
switch (op) {
case 0: /* mac: fd + (fn * fm) */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FMACD + (1 - dp));
gen_vfp_mul(dp);
gen_mov_F1_vreg(dp, rd);
gen_vfp_add(dp);
break;
case 1: /* nmac: fd - (fn * fm) */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FNMACD + (1 - dp));
gen_vfp_mul(dp);
gen_vfp_neg(dp);
gen_mov_F1_vreg(dp, rd);
gen_vfp_add(dp);
break;
case 2: /* msc: -fd + (fn * fm) */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FMSCD + (1 - dp));
gen_vfp_mul(dp);
gen_mov_F1_vreg(dp, rd);
gen_vfp_sub(dp);
break;
case 3: /* nmsc: -fd - (fn * fm) */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FNMSCD + (1 - dp));
gen_vfp_mul(dp);
gen_vfp_neg(dp);
gen_mov_F1_vreg(dp, rd);
gen_vfp_sub(dp);
break;
case 4: /* mul: fn * fm */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FMULD + (1 - dp));
gen_vfp_mul(dp);
break;
case 5: /* nmul: -(fn * fm) */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FNMULD + (1 - dp));
gen_vfp_mul(dp);
gen_vfp_neg(dp);
break;
case 6: /* add: fn + fm */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FADDD + (1 - dp));
gen_vfp_add(dp);
break;
case 7: /* sub: fn - fm */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FSUBD + (1 - dp));
gen_vfp_sub(dp);
break;
case 8: /* div: fn / fm */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FDIVD + (1 - dp));
gen_vfp_div(dp);
break;
case 14: /* fconst */
+ instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN);
if (!arm_feature(env, ARM_FEATURE_VFP3))
return 1;
@@ -3085,90 +3486,116 @@ static int disas_vfp_insn(CPUState * env
case 15: /* extension space */
switch (rn) {
case 0: /* cpy */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FCPYD + (1 - dp));
/* no-op */
break;
case 1: /* abs */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FABSD + (1 - dp));
gen_vfp_abs(dp);
break;
case 2: /* neg */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FNEGD + (1 - dp));
gen_vfp_neg(dp);
break;
case 3: /* sqrt */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FSQRTD + (1 - dp));
gen_vfp_sqrt(dp);
break;
case 8: /* cmp */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FCMPD + (1 - dp));
gen_vfp_cmp(dp);
break;
case 9: /* cmpe */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FCMPED + (1 - dp));
gen_vfp_cmpe(dp);
break;
case 10: /* cmpz */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FCMPZD + (1 - dp));
gen_vfp_cmp(dp);
break;
case 11: /* cmpez */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FCMPEZD + (1 - dp));
gen_vfp_F1_ld0(dp);
gen_vfp_cmpe(dp);
break;
case 15: /* single<->double conversion */
- if (dp)
+ if (dp) {
+ instr_count_inc(ARM_VFP_INSTRUCTION_FCVTSD);
gen_helper_vfp_fcvtsd(cpu_F0s, cpu_F0d, cpu_env);
- else
+ }
+ else {
+ instr_count_inc(ARM_VFP_INSTRUCTION_FCVTDS);
gen_helper_vfp_fcvtds(cpu_F0d, cpu_F0s, cpu_env);
+ }
break;
case 16: /* fuito */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FUITOD + (1 - dp));
gen_vfp_uito(dp);
break;
case 17: /* fsito */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FSITOD + (1 - dp));
gen_vfp_sito(dp);
break;
case 20: /* fshto */
+ instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN);
if (!arm_feature(env, ARM_FEATURE_VFP3))
return 1;
gen_vfp_shto(dp, 16 - rm);
break;
case 21: /* fslto */
+ instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN);
if (!arm_feature(env, ARM_FEATURE_VFP3))
return 1;
gen_vfp_slto(dp, 32 - rm);
break;
case 22: /* fuhto */
+ instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN);
if (!arm_feature(env, ARM_FEATURE_VFP3))
return 1;
gen_vfp_uhto(dp, 16 - rm);
break;
case 23: /* fulto */
+ instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN);
if (!arm_feature(env, ARM_FEATURE_VFP3))
return 1;
gen_vfp_ulto(dp, 32 - rm);
break;
case 24: /* ftoui */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FTOUID + (1 - dp));
gen_vfp_toui(dp);
break;
case 25: /* ftouiz */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FTOUIZD + (1 - dp));
gen_vfp_touiz(dp);
break;
case 26: /* ftosi */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FTOSID + (1 - dp));
gen_vfp_tosi(dp);
break;
case 27: /* ftosiz */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FTOSIZD + (1 - dp));
gen_vfp_tosiz(dp);
break;
case 28: /* ftosh */
+ instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN);
if (!arm_feature(env, ARM_FEATURE_VFP3))
return 1;
gen_vfp_tosh(dp, 16 - rm);
break;
case 29: /* ftosl */
+ instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN);
if (!arm_feature(env, ARM_FEATURE_VFP3))
return 1;
gen_vfp_tosl(dp, 32 - rm);
break;
case 30: /* ftouh */
+ instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN);
if (!arm_feature(env, ARM_FEATURE_VFP3))
return 1;
gen_vfp_touh(dp, 16 - rm);
break;
case 31: /* ftoul */
+ instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN);
if (!arm_feature(env, ARM_FEATURE_VFP3))
return 1;
gen_vfp_toul(dp, 32 - rm);
@@ -3247,6 +3674,7 @@ static int disas_vfp_insn(CPUState * env
if (insn & ARM_CP_RW_BIT) {
/* vfp->arm */
if (dp) {
+ instr_count_inc(ARM_VFP_INSTRUCTION_FMRRD);
gen_mov_F0_vreg(0, rm * 2);
tmp = gen_vfp_mrs();
store_reg(s, rd, tmp);
@@ -3254,6 +3682,7 @@ static int disas_vfp_insn(CPUState * env
tmp = gen_vfp_mrs();
store_reg(s, rn, tmp);
} else {
+ instr_count_inc(ARM_VFP_INSTRUCTION_FMRRS);
gen_mov_F0_vreg(0, rm);
tmp = gen_vfp_mrs();
store_reg(s, rn, tmp);
@@ -3264,6 +3693,7 @@ static int disas_vfp_insn(CPUState * env
} else {
/* arm->vfp */
if (dp) {
+ instr_count_inc(ARM_VFP_INSTRUCTION_FMDRR);
tmp = load_reg(s, rd);
gen_vfp_msr(tmp);
gen_mov_vreg_F0(0, rm * 2);
@@ -3271,6 +3701,7 @@ static int disas_vfp_insn(CPUState * env
gen_vfp_msr(tmp);
gen_mov_vreg_F0(0, rm * 2 + 1);
} else {
+ instr_count_inc(ARM_VFP_INSTRUCTION_FMSRR);
tmp = load_reg(s, rn);
gen_vfp_msr(tmp);
gen_mov_vreg_F0(0, rm);
@@ -3298,9 +3729,11 @@ static int disas_vfp_insn(CPUState * env
offset = -offset;
gen_op_addl_T1_im(offset);
if (insn & (1 << 20)) {
+ instr_count_inc(ARM_VFP_INSTRUCTION_FLDD + (1 - dp));
gen_vfp_ld(s, dp);
gen_mov_vreg_F0(dp, rd);
} else {
+ instr_count_inc(ARM_VFP_INSTRUCTION_FSTD + (1 - dp));
gen_mov_F0_vreg(dp, rd);
gen_vfp_st(s, dp);
}
@@ -3321,10 +3754,12 @@ static int disas_vfp_insn(CPUState * env
for (i = 0; i < n; i++) {
if (insn & ARM_CP_RW_BIT) {
/* load */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FLDMD + (1 - dp));
gen_vfp_ld(s, dp);
gen_mov_vreg_F0(dp, rd + i);
} else {
/* store */
+ instr_count_inc(ARM_VFP_INSTRUCTION_FSTMD + (1 - dp));
gen_mov_F0_vreg(dp, rd + i);
gen_vfp_st(s, dp);
}
@@ -5697,6 +6132,7 @@ static void gen_logicq_cc(TCGv_i64 val)
static void disas_arm_insn(CPUState * env, DisasContext *s)
{
unsigned int cond, insn, val, op1, i, shift, rm, rs, rn, rd, sh;
+ unsigned int instr_index = 0;
TCGv tmp;
TCGv tmp2;
TCGv tmp3;
@@ -5706,14 +6142,18 @@ static void disas_arm_insn(CPUState * en
insn = ldl_code(s->pc);
s->pc += 4;
+ instr_count_inc_init(ARM_INSTRUCTION_COUNTER_OFFSET,
+ ARM_INSTRUCTION_NOT_INSTRUMENTED);
+
/* M variants do not implement ARM mode. */
if (IS_M(env))
goto illegal_op;
cond = insn >> 28;
- if (cond == 0xf){
+ if (cond == 0xf) {
/* Unconditional instructions. */
if (((insn >> 25) & 7) == 1) {
/* NEON Data processing. */
+ instr_count_inc(ARM_INSTRUCTION_UNKNOWN);
if (!arm_feature(env, ARM_FEATURE_NEON))
goto illegal_op;
@@ -5723,6 +6163,7 @@ static void disas_arm_insn(CPUState * en
}
if ((insn & 0x0f100000) == 0x04000000) {
/* NEON load/store. */
+ instr_count_inc(ARM_INSTRUCTION_UNKNOWN);
if (!arm_feature(env, ARM_FEATURE_NEON))
goto illegal_op;
@@ -5734,6 +6175,7 @@ static void disas_arm_insn(CPUState * en
return; /* PLD */
else if ((insn & 0x0ffffdff) == 0x01010000) {
ARCH(6);
+ instr_count_inc(ARM_INSTRUCTION_SETEND);
/* setend */
if (insn & (1 << 9)) {
/* BE8 mode not implemented. */
@@ -5744,11 +6186,13 @@ static void disas_arm_insn(CPUState * en
switch ((insn >> 4) & 0xf) {
case 1: /* clrex */
ARCH(6K);
+ instr_count_inc(ARM_INSTRUCTION_UNKNOWN);
gen_helper_clrex(cpu_env);
return;
case 4: /* dsb */
case 5: /* dmb */
case 6: /* isb */
+ instr_count_inc(ARM_INSTRUCTION_UNKNOWN);
ARCH(7);
/* We don't emulate caches so these are a no-op. */
return;
@@ -5758,6 +6202,7 @@ static void disas_arm_insn(CPUState * en
} else if ((insn & 0x0e5fffe0) == 0x084d0500) {
/* srs */
uint32_t offset;
+ instr_count_inc(ARM_INSTRUCTION_SRS);
if (IS_USER(s))
goto illegal_op;
ARCH(6);
@@ -5808,6 +6253,7 @@ static void disas_arm_insn(CPUState * en
uint32_t offset;
if (IS_USER(s))
goto illegal_op;
+ instr_count_inc(ARM_INSTRUCTION_RFE);
ARCH(6);
rn = (insn >> 16) & 0xf;
addr = load_reg(s, rn);
@@ -5844,7 +6290,7 @@ static void disas_arm_insn(CPUState * en
} else if ((insn & 0x0e000000) == 0x0a000000) {
/* branch link and change to thumb (blx <offset>) */
int32_t offset;
-
+ instr_count_inc(ARM_INSTRUCTION_BLX);
val = (uint32_t)s->pc;
tmp = new_tmp();
tcg_gen_movi_i32(tmp, val);
@@ -5858,6 +6304,7 @@ static void disas_arm_insn(CPUState * en
gen_bx_im(s, val);
return;
} else if ((insn & 0x0e000f00) == 0x0c000100) {
+ instr_count_inc(ARM_INSTRUCTION_UNKNOWN);
if (arm_feature(env, ARM_FEATURE_IWMMXT)) {
/* iWMMXt register transfer. */
if (env->cp15.c15_cpar & (1 << 1))
@@ -5865,13 +6312,16 @@ static void disas_arm_insn(CPUState * en
return;
}
} else if ((insn & 0x0fe00000) == 0x0c400000) {
+ instr_count_inc(ARM_INSTRUCTION_UNKNOWN);
/* Coprocessor double register transfer. */
} else if ((insn & 0x0f000010) == 0x0e000010) {
+ instr_count_inc(ARM_INSTRUCTION_UNKNOWN);
/* Additional coprocessor register transfer. */
} else if ((insn & 0x0ff10020) == 0x01000000) {
uint32_t mask;
uint32_t val;
/* cps (privileged) */
+ instr_count_inc(ARM_INSTRUCTION_CPS);
if (IS_USER(s))
return;
mask = val = 0;
@@ -5911,10 +6361,12 @@ static void disas_arm_insn(CPUState * en
val = ((insn >> 4) & 0xf000) | (insn & 0xfff);
if ((insn & (1 << 22)) == 0) {
/* MOVW */
+ instr_count_inc(ARM_INSTRUCTION_UNKNOWN);
tmp = new_tmp();
tcg_gen_movi_i32(tmp, val);
} else {
/* MOVT */
+ instr_count_inc(ARM_INSTRUCTION_UNKNOWN);
tmp = load_reg(s, rd);
tcg_gen_ext16u_i32(tmp, tmp);
tcg_gen_ori_i32(tmp, tmp, val << 16);
@@ -5924,9 +6376,11 @@ static void disas_arm_insn(CPUState * en
if (((insn >> 12) & 0xf) != 0xf)
goto illegal_op;
if (((insn >> 16) & 0xf) == 0) {
+ instr_count_inc(ARM_INSTRUCTION_UNKNOWN);
gen_nop_hint(s, insn & 0xff);
} else {
/* CPSR = immediate */
+ instr_count_inc(ARM_INSTRUCTION_MSR);
val = insn & 0xff;
shift = ((insn >> 8) & 0xf) * 2;
if (shift)
@@ -5947,12 +6401,14 @@ static void disas_arm_insn(CPUState * en
case 0x0: /* move program status register */
if (op1 & 1) {
/* PSR = reg */
+ instr_count_inc(ARM_INSTRUCTION_MSR);
gen_movl_T0_reg(s, rm);
i = ((op1 & 2) != 0);
if (gen_set_psr_T0(s, msr_mask(env, s, (insn >> 16) & 0xf, i), i))
goto illegal_op;
} else {
/* reg = PSR */
+ instr_count_inc(ARM_INSTRUCTION_MRS);
rd = (insn >> 12) & 0xf;
if (op1 & 2) {
if (IS_USER(s))
@@ -5968,10 +6424,12 @@ static void disas_arm_insn(CPUState * en
case 0x1:
if (op1 == 1) {
/* branch/exchange thumb (bx). */
+ instr_count_inc(ARM_INSTRUCTION_BX);
tmp = load_reg(s, rm);
gen_bx(s, tmp);
} else if (op1 == 3) {
/* clz */
+ instr_count_inc(ARM_INSTRUCTION_CLZ);
rd = (insn >> 12) & 0xf;
tmp = load_reg(s, rm);
gen_helper_clz(tmp, tmp);
@@ -5982,6 +6440,7 @@ static void disas_arm_insn(CPUState * en
break;
case 0x2:
if (op1 == 1) {
+ instr_count_inc(ARM_INSTRUCTION_BXJ);
ARCH(5J); /* bxj */
/* Trivial implementation equivalent to bx. */
tmp = load_reg(s, rm);
@@ -5994,6 +6453,7 @@ static void disas_arm_insn(CPUState * en
if (op1 != 1)
goto illegal_op;
+ instr_count_inc(ARM_INSTRUCTION_BLX);
/* branch link/exchange thumb (blx) */
tmp = load_reg(s, rm);
tmp2 = new_tmp();
@@ -6006,16 +6466,24 @@ static void disas_arm_insn(CPUState * en
rn = (insn >> 16) & 0xf;
tmp = load_reg(s, rm);
tmp2 = load_reg(s, rn);
- if (op1 & 2)
+ if (op1 & 2) {
gen_helper_double_saturate(tmp2, tmp2);
- if (op1 & 1)
+ if (op1 & 1) instr_count_inc(ARM_INSTRUCTION_QDSUB);
+ else instr_count_inc(ARM_INSTRUCTION_QDADD);
+ }
+ if (op1 & 1) {
gen_helper_sub_saturate(tmp, tmp, tmp2);
- else
+ instr_count_inc(ARM_INSTRUCTION_QSUB);
+ }
+ else {
gen_helper_add_saturate(tmp, tmp, tmp2);
+ instr_count_inc(ARM_INSTRUCTION_QADD);
+ }
dead_tmp(tmp2);
store_reg(s, rd, tmp);
break;
case 7: /* bkpt */
+ instr_count_inc(ARM_INSTRUCTION_BKPT);
gen_set_condexec(s);
gen_set_pc_im(s->pc - 4);
gen_exception(EXCP_BKPT);
@@ -6041,18 +6509,22 @@ static void disas_arm_insn(CPUState * en
tmp = new_tmp();
tcg_gen_trunc_i64_i32(tmp, tmp64);
if ((sh & 2) == 0) {
+ instr_count_inc(ARM_INSTRUCTION_SMLAWY);
tmp2 = load_reg(s, rn);
gen_helper_add_setq(tmp, tmp, tmp2);
dead_tmp(tmp2);
}
+ else instr_count_inc(ARM_INSTRUCTION_SMULWY);
store_reg(s, rd, tmp);
} else {
/* 16 * 16 */
+ if (op1 == 3) instr_count_inc(ARM_INSTRUCTION_SMULXY);
tmp = load_reg(s, rm);
tmp2 = load_reg(s, rs);
gen_mulxy(tmp, tmp2, sh & 2, sh & 4);
dead_tmp(tmp2);
if (op1 == 2) {
+ instr_count_inc(ARM_INSTRUCTION_SMLALXY);
tmp64 = tcg_temp_new_i64();
tcg_gen_ext_i32_i64(tmp64, tmp);
dead_tmp(tmp);
@@ -6060,6 +6532,7 @@ static void disas_arm_insn(CPUState * en
gen_storeq_reg(s, rn, rd, tmp64);
} else {
if (op1 == 0) {
+ instr_count_inc(ARM_INSTRUCTION_SMLAXY);
tmp2 = load_reg(s, rn);
gen_helper_add_setq(tmp, tmp, tmp2);
dead_tmp(tmp2);
@@ -6111,18 +6584,21 @@ static void disas_arm_insn(CPUState * en
rd = (insn >> 12) & 0xf;
switch(op1) {
case 0x00:
+ instr_count_inc(ARM_INSTRUCTION_AND);
gen_op_andl_T0_T1();
gen_movl_reg_T0(s, rd);
if (logic_cc)
gen_op_logic_T0_cc();
break;
case 0x01:
+ instr_count_inc(ARM_INSTRUCTION_EOR);
gen_op_xorl_T0_T1();
gen_movl_reg_T0(s, rd);
if (logic_cc)
gen_op_logic_T0_cc();
break;
case 0x02:
+ instr_count_inc(ARM_INSTRUCTION_SUB);
if (set_cc && rd == 15) {
/* SUBS r15, ... is used for exception return. */
if (IS_USER(s))
@@ -6138,6 +6614,7 @@ static void disas_arm_insn(CPUState * en
}
break;
case 0x03:
+ instr_count_inc(ARM_INSTRUCTION_RSB);
if (set_cc)
gen_op_rsbl_T0_T1_cc();
else
@@ -6145,6 +6622,7 @@ static void disas_arm_insn(CPUState * en
gen_movl_reg_T0(s, rd);
break;
case 0x04:
+ instr_count_inc(ARM_INSTRUCTION_ADD);
if (set_cc)
gen_op_addl_T0_T1_cc();
else
@@ -6152,6 +6630,7 @@ static void disas_arm_insn(CPUState * en
gen_movl_reg_T0(s, rd);
break;
case 0x05:
+ instr_count_inc(ARM_INSTRUCTION_ADC);
if (set_cc)
gen_op_adcl_T0_T1_cc();
else
@@ -6159,6 +6638,7 @@ static void disas_arm_insn(CPUState * en
gen_movl_reg_T0(s, rd);
break;
case 0x06:
+ instr_count_inc(ARM_INSTRUCTION_SBC);
if (set_cc)
gen_op_sbcl_T0_T1_cc();
else
@@ -6166,6 +6646,7 @@ static void disas_arm_insn(CPUState * en
gen_movl_reg_T0(s, rd);
break;
case 0x07:
+ instr_count_inc(ARM_INSTRUCTION_RSC);
if (set_cc)
gen_op_rscl_T0_T1_cc();
else
@@ -6173,34 +6654,40 @@ static void disas_arm_insn(CPUState * en
gen_movl_reg_T0(s, rd);
break;
case 0x08:
+ instr_count_inc(ARM_INSTRUCTION_TST);
if (set_cc) {
gen_op_andl_T0_T1();
gen_op_logic_T0_cc();
}
break;
case 0x09:
+ instr_count_inc(ARM_INSTRUCTION_TEQ);
if (set_cc) {
gen_op_xorl_T0_T1();
gen_op_logic_T0_cc();
}
break;
case 0x0a:
+ instr_count_inc(ARM_INSTRUCTION_CMP);
if (set_cc) {
gen_op_subl_T0_T1_cc();
}
break;
case 0x0b:
+ instr_count_inc(ARM_INSTRUCTION_CMN);
if (set_cc) {
gen_op_addl_T0_T1_cc();
}
break;
case 0x0c:
+ instr_count_inc(ARM_INSTRUCTION_ORR);
gen_op_orl_T0_T1();
gen_movl_reg_T0(s, rd);
if (logic_cc)
gen_op_logic_T0_cc();
break;
case 0x0d:
+ instr_count_inc(ARM_INSTRUCTION_MOV);
if (logic_cc && rd == 15) {
/* MOVS r15, ... is used for exception return. */
if (IS_USER(s))
@@ -6214,6 +6701,7 @@ static void disas_arm_insn(CPUState * en
}
break;
case 0x0e:
+ instr_count_inc(ARM_INSTRUCTION_BIC);
gen_op_bicl_T0_T1();
gen_movl_reg_T0(s, rd);
if (logic_cc)
@@ -6221,6 +6709,7 @@ static void disas_arm_insn(CPUState * en
break;
default:
case 0x0f:
+ instr_count_inc(ARM_INSTRUCTION_MVN);
gen_op_notl_T1();
gen_movl_reg_T1(s, rd);
if (logic_cc)
@@ -6245,43 +6734,63 @@ static void disas_arm_insn(CPUState * en
switch (op1) {
case 0: case 1: case 2: case 3: case 6:
/* 32 bit mul */
+ instr_index = ARM_INSTRUCTION_MUL;
tmp = load_reg(s, rs);
tmp2 = load_reg(s, rm);
tcg_gen_mul_i32(tmp, tmp, tmp2);
dead_tmp(tmp2);
if (insn & (1 << 22)) {
/* Subtract (mls) */
+ instr_count_inc(ARM_INSTRUCTION_UNKNOWN);
ARCH(6T2);
tmp2 = load_reg(s, rn);
tcg_gen_sub_i32(tmp, tmp2, tmp);
dead_tmp(tmp2);
} else if (insn & (1 << 21)) {
/* Add */
+ instr_index = ARM_INSTRUCTION_MLA;
tmp2 = load_reg(s, rn);
tcg_gen_add_i32(tmp, tmp, tmp2);
dead_tmp(tmp2);
}
- if (insn & (1 << 20))
+ if (insn & (1 << 20)) {
gen_logic_CC(tmp);
+ instr_index++; /* MULS and MLAS */
+ }
+ instr_count_inc(instr_index);
store_reg(s, rd, tmp);
break;
default:
/* 64 bit mul */
tmp = load_reg(s, rs);
tmp2 = load_reg(s, rm);
- if (insn & (1 << 22))
+ if (insn & (1 << 22)) {
tmp64 = gen_muls_i64_i32(tmp, tmp2);
- else
+ instr_index = ARM_INSTRUCTION_SMULL;
+ }
+ else {
tmp64 = gen_mulu_i64_i32(tmp, tmp2);
- if (insn & (1 << 21)) /* mult accumulate */
+ instr_index = ARM_INSTRUCTION_UMULL;
+ }
+ if (insn & (1 << 21)) {
+ /* mult accumulate */
gen_addq(s, tmp64, rn, rd);
+ if (insn & (1 << 22)) {
+ instr_index = ARM_INSTRUCTION_SMLAL;
+ } else {
+ instr_index = ARM_INSTRUCTION_UMLAL;
+ }
+ }
if (!(insn & (1 << 23))) { /* double accumulate */
ARCH(6);
gen_addq_lo(s, tmp64, rn);
gen_addq_lo(s, tmp64, rd);
}
- if (insn & (1 << 20))
+ if (insn & (1 << 20)) {
gen_logicq_cc(tmp64);
+ instr_index++; /* SMULLS, UMULLS, SMLALS, UMLALS */
+ }
+ instr_count_inc(instr_index);
gen_storeq_reg(s, rn, rd, tmp64);
break;
}
@@ -6300,6 +6809,7 @@ static void disas_arm_insn(CPUState * en
if (insn & (1 << 20)) {
gen_helper_mark_exclusive(cpu_env, cpu_T[1]);
switch (op1) {
+ instr_count_inc(ARM_INSTRUCTION_LDREX);
case 0: /* ldrex */
tmp = gen_ld32(addr, IS_USER(s));
break;
@@ -6327,6 +6837,7 @@ static void disas_arm_insn(CPUState * en
tcg_gen_brcondi_i32(TCG_COND_NE, cpu_T[0],
0, label);
tmp = load_reg(s,rm);
+ instr_count_inc(ARM_INSTRUCTION_STREX);
switch (op1) {
case 0: /* strex */
gen_st32(tmp, addr, IS_USER(s));
@@ -6359,9 +6870,11 @@ static void disas_arm_insn(CPUState * en
addr = load_reg(s, rn);
tmp = load_reg(s, rm);
if (insn & (1 << 22)) {
+ instr_count_inc(ARM_INSTRUCTION_SWPB);
tmp2 = gen_ld8u(addr, IS_USER(s));
gen_st8(tmp, addr, IS_USER(s));
} else {
+ instr_count_inc(ARM_INSTRUCTION_SWP);
tmp2 = gen_ld32(addr, IS_USER(s));
gen_st32(tmp, addr, IS_USER(s));
}
@@ -6383,13 +6896,16 @@ static void disas_arm_insn(CPUState * en
/* load */
switch(sh) {
case 1:
+ instr_count_inc(ARM_INSTRUCTION_LDRH);
tmp = gen_ld16u(addr, IS_USER(s));
break;
case 2:
+ instr_count_inc(ARM_INSTRUCTION_LDRSB);
tmp = gen_ld8s(addr, IS_USER(s));
break;
default:
case 3:
+ instr_count_inc(ARM_INSTRUCTION_LDRSH);
tmp = gen_ld16s(addr, IS_USER(s));
break;
}
@@ -6398,6 +6914,7 @@ static void disas_arm_insn(CPUState * en
/* doubleword */
if (sh & 1) {
/* store */
+ instr_count_inc(ARM_INSTRUCTION_STRD);
tmp = load_reg(s, rd);
gen_st32(tmp, addr, IS_USER(s));
tcg_gen_addi_i32(addr, addr, 4);
@@ -6406,6 +6923,7 @@ static void disas_arm_insn(CPUState * en
load = 0;
} else {
/* load */
+ instr_count_inc(ARM_INSTRUCTION_LDRD);
tmp = gen_ld32(addr, IS_USER(s));
store_reg(s, rd, tmp);
tcg_gen_addi_i32(addr, addr, 4);
@@ -6417,6 +6935,7 @@ static void disas_arm_insn(CPUState * en
} else {
/* store */
tmp = load_reg(s, rd);
+ instr_count_inc(ARM_INSTRUCTION_STRH);
gen_st16(tmp, addr, IS_USER(s));
load = 0;
}
@@ -6454,6 +6973,7 @@ static void disas_arm_insn(CPUState * en
rs = (insn >> 8) & 0xf;
switch ((insn >> 23) & 3) {
case 0: /* Parallel add/subtract. */
+ instr_count_inc(ARM_INSTRUCTION_UNKNOWN);
op1 = (insn >> 20) & 7;
tmp = load_reg(s, rn);
tmp2 = load_reg(s, rm);
@@ -6472,6 +6992,7 @@ static void disas_arm_insn(CPUState * en
shift = (insn >> 7) & 0x1f;
if (insn & (1 << 6)) {
/* pkhtb */
+ instr_count_inc(ARM_INSTRUCTION_PKHTB);
if (shift == 0)
shift = 31;
tcg_gen_sari_i32(tmp2, tmp2, shift);
@@ -6479,6 +7000,7 @@ static void disas_arm_insn(CPUState * en
tcg_gen_ext16u_i32(tmp2, tmp2);
} else {
/* pkhbt */
+ instr_count_inc(ARM_INSTRUCTION_PKHBT);
if (shift)
tcg_gen_shli_i32(tmp2, tmp2, shift);
tcg_gen_ext16u_i32(tmp, tmp);
@@ -6500,10 +7022,14 @@ static void disas_arm_insn(CPUState * en
}
sh = (insn >> 16) & 0x1f;
if (sh != 0) {
- if (insn & (1 << 22))
+ if (insn & (1 << 22)) {
+ instr_count_inc(ARM_INSTRUCTION_USAT);
gen_helper_usat(tmp, tmp, tcg_const_i32(sh));
- else
+ }
+ else {
+ instr_count_inc(ARM_INSTRUCTION_SSAT);
gen_helper_ssat(tmp, tmp, tcg_const_i32(sh));
+ }
}
store_reg(s, rd, tmp);
} else if ((insn & 0x00300fe0) == 0x00200f20) {
@@ -6511,14 +7037,19 @@ static void disas_arm_insn(CPUState * en
tmp = load_reg(s, rm);
sh = (insn >> 16) & 0x1f;
if (sh != 0) {
- if (insn & (1 << 22))
+ if (insn & (1 << 22)) {
+ instr_count_inc(ARM_INSTRUCTION_USAT16);
gen_helper_usat16(tmp, tmp, tcg_const_i32(sh));
- else
+ }
+ else {
+ instr_count_inc(ARM_INSTRUCTION_SSAT16);
gen_helper_ssat16(tmp, tmp, tcg_const_i32(sh));
+ }
}
store_reg(s, rd, tmp);
} else if ((insn & 0x00700fe0) == 0x00000fa0) {
/* Select bytes. */
+ instr_count_inc(ARM_INSTRUCTION_SEL);
tmp = load_reg(s, rn);
tmp2 = load_reg(s, rm);
tmp3 = new_tmp();
@@ -6536,12 +7067,30 @@ static void disas_arm_insn(CPUState * en
tcg_gen_rori_i32(tmp, tmp, shift * 8);
op1 = (insn >> 20) & 7;
switch (op1) {
- case 0: gen_sxtb16(tmp); break;
- case 2: gen_sxtb(tmp); break;
- case 3: gen_sxth(tmp); break;
- case 4: gen_uxtb16(tmp); break;
- case 6: gen_uxtb(tmp); break;
- case 7: gen_uxth(tmp); break;
+ case 0:
+ instr_index = ARM_INSTRUCTION_SXTB16;
+ gen_sxtb16(tmp);
+ break;
+ case 2:
+ instr_index = ARM_INSTRUCTION_SXTB;
+ gen_sxtb(tmp);
+ break;
+ case 3:
+ instr_index = ARM_INSTRUCTION_SXTH;
+ gen_sxth(tmp);
+ break;
+ case 4:
+ instr_index = ARM_INSTRUCTION_UXTB16;
+ gen_uxtb16(tmp);
+ break;
+ case 6:
+ instr_index = ARM_INSTRUCTION_UXTB;
+ gen_uxtb(tmp);
+ break;
+ case 7:
+ instr_index = ARM_INSTRUCTION_UXTH;
+ gen_uxth(tmp);
+ break;
default: goto illegal_op;
}
if (rn != 15) {
@@ -6552,23 +7101,30 @@ static void disas_arm_insn(CPUState * en
tcg_gen_add_i32(tmp, tmp, tmp2);
dead_tmp(tmp2);
}
+ instr_index -= 3; /* add variants */
}
+ instr_count_inc(instr_index);
store_reg(s, rd, tmp);
} else if ((insn & 0x003f0f60) == 0x003f0f20) {
/* rev */
tmp = load_reg(s, rm);
if (insn & (1 << 22)) {
if (insn & (1 << 7)) {
+ instr_count_inc(ARM_INSTRUCTION_REVSH);
gen_revsh(tmp);
} else {
ARCH(6T2);
gen_helper_rbit(tmp, tmp);
}
} else {
- if (insn & (1 << 7))
+ if (insn & (1 << 7)) {
+ instr_count_inc(ARM_INSTRUCTION_REV16);
gen_rev16(tmp);
- else
+ }
+ else {
+ instr_count_inc(ARM_INSTRUCTION_REV);
tcg_gen_bswap_i32(tmp, tmp);
+ }
}
store_reg(s, rd, tmp);
} else {
@@ -6590,11 +7146,16 @@ static void disas_arm_insn(CPUState * en
tmp2 = load_reg(s, rd);
if (insn & (1 << 6)) {
tcg_gen_sub_i32(tmp, tmp, tmp2);
+ instr_count_inc(ARM_INSTRUCTION_SMMLS);
} else {
tcg_gen_add_i32(tmp, tmp, tmp2);
+ instr_count_inc(ARM_INSTRUCTION_SMMLA);
}
dead_tmp(tmp2);
}
+ else {
+ instr_count_inc(ARM_INSTRUCTION_SMMUL);
+ }
store_reg(s, rn, tmp);
} else {
if (insn & (1 << 5))
@@ -6603,8 +7164,10 @@ static void disas_arm_insn(CPUState * en
/* This addition cannot overflow. */
if (insn & (1 << 6)) {
tcg_gen_sub_i32(tmp, tmp, tmp2);
+ instr_index = 1;
} else {
tcg_gen_add_i32(tmp, tmp, tmp2);
+ instr_index = 0;
}
dead_tmp(tmp2);
if (insn & (1 << 22)) {
@@ -6614,6 +7177,8 @@ static void disas_arm_insn(CPUState * en
dead_tmp(tmp);
gen_addq(s, tmp64, rd, rn);
gen_storeq_reg(s, rd, rn, tmp64);
+ instr_index += ARM_INSTRUCTION_SMLALD;
+ instr_count_inc(instr_index);
} else {
/* smuad, smusd, smlad, smlsd */
if (rd != 15)
@@ -6621,8 +7186,11 @@ static void disas_arm_insn(CPUState * en
tmp2 = load_reg(s, rd);
gen_helper_add_setq(tmp, tmp, tmp2);
dead_tmp(tmp2);
+ instr_index += 2; /* SMLAD, SMLSD */
}
store_reg(s, rn, tmp);
+ instr_index += ARM_INSTRUCTION_SMUAD;
+ instr_count_inc(instr_index);
}
}
break;
@@ -6639,12 +7207,15 @@ static void disas_arm_insn(CPUState * en
tmp2 = load_reg(s, rd);
tcg_gen_add_i32(tmp, tmp, tmp2);
dead_tmp(tmp2);
+ instr_count_inc(ARM_INSTRUCTION_USADA8);
}
+ else instr_count_inc(ARM_INSTRUCTION_USAD8);
store_reg(s, rn, tmp);
break;
case 0x20: case 0x24: case 0x28: case 0x2c:
/* Bitfield insert/clear. */
ARCH(6T2);
+ instr_count_inc(ARM_INSTRUCTION_UNKNOWN);
shift = (insn >> 7) & 0x1f;
i = (insn >> 16) & 0x1f;
i = i + 1 - shift;
@@ -6664,6 +7235,7 @@ static void disas_arm_insn(CPUState * en
case 0x12: case 0x16: case 0x1a: case 0x1e: /* sbfx */
case 0x32: case 0x36: case 0x3a: case 0x3e: /* ubfx */
ARCH(6T2);
+ instr_count_inc(ARM_INSTRUCTION_UNKNOWN);
tmp = load_reg(s, rm);
shift = (insn >> 7) & 0x1f;
i = ((insn >> 16) & 0x1f) + 1;
@@ -6705,17 +7277,23 @@ static void disas_arm_insn(CPUState * en
if (insn & (1 << 20)) {
/* load */
if (insn & (1 << 22)) {
+ instr_count_inc(ARM_INSTRUCTION_LDRB);
tmp = gen_ld8u(tmp2, i);
} else {
+ instr_count_inc(ARM_INSTRUCTION_LDR);
tmp = gen_ld32(tmp2, i);
}
} else {
/* store */
tmp = load_reg(s, rd);
- if (insn & (1 << 22))
+ if (insn & (1 << 22)) {
+ instr_count_inc(ARM_INSTRUCTION_STRB);
gen_st8(tmp, tmp2, i);
- else
+ }
+ else {
+ instr_count_inc(ARM_INSTRUCTION_STR);
gen_st32(tmp, tmp2, i);
+ }
}
if (!(insn & (1 << 24))) {
gen_add_data_offset(s, insn, tmp2);
@@ -6740,6 +7318,18 @@ static void disas_arm_insn(CPUState * en
TCGv loaded_var;
/* load/store multiple words */
/* XXX: store correct base if write back */
+ switch (insn & 0x00500000 >> 20) {
+ case 0x0: instr_count_inc(ARM_INSTRUCTION_STM1); break;
+ case 0x1: instr_count_inc(ARM_INSTRUCTION_LDM1); break;
+ case 0x4: instr_count_inc(ARM_INSTRUCTION_STM2); break;
+ case 0x5:
+ if (insn & (1 << 15)) {
+ instr_count_inc(ARM_INSTRUCTION_LDM3);
+ } else {
+ instr_count_inc(ARM_INSTRUCTION_LDM2);
+ }
+ break;
+ }
user = 0;
if (insn & (1 << 22)) {
if (IS_USER(s))
@@ -6854,14 +7444,15 @@ static void disas_arm_insn(CPUState * en
case 0xb:
{
int32_t offset;
-
/* branch (and link) */
val = (int32_t)s->pc;
if (insn & (1 << 24)) {
+ instr_count_inc(ARM_INSTRUCTION_B);
tmp = new_tmp();
tcg_gen_movi_i32(tmp, val);
store_reg(s, 14, tmp);
}
+ else instr_count_inc(ARM_INSTRUCTION_B);
offset = (((int32_t)insn << 8) >> 8);
val += (offset << 2) + 4;
gen_jmp(s, val);
@@ -6871,11 +7462,13 @@ static void disas_arm_insn(CPUState * en
case 0xd:
case 0xe:
/* Coprocessor. */
+ instr_count_inc(ARM_INSTRUCTION_COPROCESSOR);
if (disas_coproc_insn(env, s, insn))
goto illegal_op;
break;
case 0xf:
/* swi */
+ instr_count_inc(ARM_INSTRUCTION_SWI);
gen_set_pc_im(s->pc);
s->is_jmp = DISAS_SWI;
break;
@@ -6988,6 +7581,9 @@ static int disas_thumb2_insn(CPUState *e
int conds;
int logic_cc;
+ instr_count_inc_init(ARM_THUMB_INSTRUCTION_COUNTER_OFFSET,
+ ARM_THUMB_INSTRUCTION_NOT_INSTRUMENTED);
+
if (!(arm_feature(env, ARM_FEATURE_THUMB2)
|| arm_feature (env, ARM_FEATURE_M))) {
/* Thumb-1 cores may need to treat bl and blx as a pair of
@@ -7601,10 +8197,12 @@ static int disas_thumb2_insn(CPUState *e
if (insn & (1 << 12)) {
/* b/bl */
gen_jmp(s, offset);
+ instr_count_inc(ARM_THUMB_INSTRUCTION_BL);
} else {
/* blx */
offset &= ~(uint32_t)2;
gen_bx_im(s, offset);
+ instr_count_inc(ARM_THUMB_INSTRUCTION_BLX1);
}
} else if (((insn >> 23) & 7) == 7) {
/* Misc control */
@@ -7995,13 +8593,19 @@ illegal_op:
static void disas_thumb_insn(CPUState *env, DisasContext *s)
{
- uint32_t val, insn, op, rm, rn, rd, shift, cond;
+ uint32_t val, insn, op, rm, rn, rd, shift, cond, instr_index;
int32_t offset;
int i;
TCGv tmp;
TCGv tmp2;
TCGv addr;
+ instr_index = 0;
+
+ instr_count_inc_init(ARM_THUMB_INSTRUCTION_COUNTER_OFFSET,
+ ARM_THUMB_INSTRUCTION_NOT_INSTRUMENTED);
+
+
if (s->condexec_mask) {
cond = s->condexec_cond;
s->condlabel = gen_new_label();
@@ -8022,18 +8626,26 @@ static void disas_thumb_insn(CPUState *e
gen_movl_T0_reg(s, rn);
if (insn & (1 << 10)) {
/* immediate */
+ instr_index = 0;
gen_op_movl_T1_im((insn >> 6) & 7);
} else {
/* reg */
+ instr_index = 2; /* ADD3 / SUB3 */
rm = (insn >> 6) & 7;
gen_movl_T1_reg(s, rm);
}
if (insn & (1 << 9)) {
+ instr_count_inc(ARM_THUMB_INSTRUCTION_SUB1 + instr_index);
if (s->condexec_mask)
gen_op_subl_T0_T1();
else
gen_op_subl_T0_T1_cc();
} else {
+ if ((insn >> 6) & 7) {
+ instr_count_inc(ARM_THUMB_INSTRUCTION_ADD1 + instr_index);
+ } else {
+ instr_count_inc(ARM_THUMB_INSTRUCTION_MOV2);
+ }
if (s->condexec_mask)
gen_op_addl_T0_T1();
else
@@ -8042,6 +8654,17 @@ static void disas_thumb_insn(CPUState *e
gen_movl_reg_T0(s, rd);
} else {
/* shift immediate */
+ switch (op) {
+ case 0x0:
+ instr_count_inc(ARM_THUMB_INSTRUCTION_LSL1);
+ break;
+ case 0x1:
+ instr_count_inc(ARM_THUMB_INSTRUCTION_LSR1);
+ break;
+ case 0x2:
+ instr_count_inc(ARM_THUMB_INSTRUCTION_ASR1);
+ break;
+ }
rm = (insn >> 3) & 7;
shift = (insn >> 6) & 0x1f;
tmp = load_reg(s, rm);
@@ -8063,19 +8686,23 @@ static void disas_thumb_insn(CPUState *e
}
switch (op) {
case 0: /* mov */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_MOV1);
if (!s->condexec_mask)
gen_op_logic_T0_cc();
break;
case 1: /* cmp */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_CMP1);
gen_op_subl_T0_T1_cc();
break;
case 2: /* add */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_ADD2);
if (s->condexec_mask)
gen_op_addl_T0_T1();
else
gen_op_addl_T0_T1_cc();
break;
case 3: /* sub */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_SUB2);
if (s->condexec_mask)
gen_op_subl_T0_T1();
else
@@ -8087,6 +8714,7 @@ static void disas_thumb_insn(CPUState *e
break;
case 4:
if (insn & (1 << 11)) {
+ instr_count_inc(ARM_THUMB_INSTRUCTION_LDR3);
rd = (insn >> 8) & 7;
/* load pc-relative. Bit 1 of PC is ignored. */
val = s->pc + 2 + ((insn & 0xff) * 4);
@@ -8105,23 +8733,28 @@ static void disas_thumb_insn(CPUState *e
op = (insn >> 8) & 3;
switch (op) {
case 0: /* add */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_ADD4);
gen_movl_T0_reg(s, rd);
gen_movl_T1_reg(s, rm);
gen_op_addl_T0_T1();
gen_movl_reg_T0(s, rd);
break;
case 1: /* cmp */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_CMP3);
gen_movl_T0_reg(s, rd);
gen_movl_T1_reg(s, rm);
gen_op_subl_T0_T1_cc();
break;
case 2: /* mov/cpy */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_MOV3);
gen_movl_T0_reg(s, rm);
gen_movl_reg_T0(s, rd);
break;
case 3:/* branch [and link] exchange thumb register */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_BX);
tmp = load_reg(s, rm);
if (insn & (1 << 7)) {
+ instr_count_inc(ARM_THUMB_INSTRUCTION_BLX2);
val = (uint32_t)s->pc | 1;
tmp2 = new_tmp();
tcg_gen_movi_i32(tmp2, val);
@@ -8155,16 +8788,19 @@ static void disas_thumb_insn(CPUState *e
gen_movl_T1_reg(s, rm);
switch (op) {
case 0x0: /* and */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_AND);
gen_op_andl_T0_T1();
if (!s->condexec_mask)
gen_op_logic_T0_cc();
break;
case 0x1: /* eor */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_EOR);
gen_op_xorl_T0_T1();
if (!s->condexec_mask)
gen_op_logic_T0_cc();
break;
case 0x2: /* lsl */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_LSL2);
if (s->condexec_mask) {
gen_helper_shl(cpu_T[1], cpu_T[1], cpu_T[0]);
} else {
@@ -8173,6 +8809,7 @@ static void disas_thumb_insn(CPUState *e
}
break;
case 0x3: /* lsr */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_LSR2);
if (s->condexec_mask) {
gen_helper_shr(cpu_T[1], cpu_T[1], cpu_T[0]);
} else {
@@ -8181,6 +8818,7 @@ static void disas_thumb_insn(CPUState *e
}
break;
case 0x4: /* asr */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_ASR2);
if (s->condexec_mask) {
gen_helper_sar(cpu_T[1], cpu_T[1], cpu_T[0]);
} else {
@@ -8189,18 +8827,21 @@ static void disas_thumb_insn(CPUState *e
}
break;
case 0x5: /* adc */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_ADC);
if (s->condexec_mask)
gen_adc_T0_T1();
else
gen_op_adcl_T0_T1_cc();
break;
case 0x6: /* sbc */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_SBC);
if (s->condexec_mask)
gen_sbc_T0_T1();
else
gen_op_sbcl_T0_T1_cc();
break;
case 0x7: /* ror */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_ROR);
if (s->condexec_mask) {
gen_helper_ror(cpu_T[1], cpu_T[1], cpu_T[0]);
} else {
@@ -8209,40 +8850,48 @@ static void disas_thumb_insn(CPUState *e
}
break;
case 0x8: /* tst */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_TST);
gen_op_andl_T0_T1();
gen_op_logic_T0_cc();
rd = 16;
break;
case 0x9: /* neg */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_NEG);
if (s->condexec_mask)
tcg_gen_neg_i32(cpu_T[0], cpu_T[1]);
else
gen_op_subl_T0_T1_cc();
break;
case 0xa: /* cmp */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_CMP2);
gen_op_subl_T0_T1_cc();
rd = 16;
break;
case 0xb: /* cmn */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_CMN);
gen_op_addl_T0_T1_cc();
rd = 16;
break;
case 0xc: /* orr */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_ORR);
gen_op_orl_T0_T1();
if (!s->condexec_mask)
gen_op_logic_T0_cc();
break;
case 0xd: /* mul */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_MUL);
gen_op_mull_T0_T1();
if (!s->condexec_mask)
gen_op_logic_T0_cc();
break;
case 0xe: /* bic */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_BIC);
gen_op_bicl_T0_T1();
if (!s->condexec_mask)
gen_op_logic_T0_cc();
break;
case 0xf: /* mvn */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_MVN);
gen_op_notl_T1();
if (!s->condexec_mask)
gen_op_logic_T1_cc();
@@ -8274,27 +8923,35 @@ static void disas_thumb_insn(CPUState *e
switch (op) {
case 0: /* str */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_STR2);
gen_st32(tmp, addr, IS_USER(s));
break;
case 1: /* strh */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_STRH2);
gen_st16(tmp, addr, IS_USER(s));
break;
case 2: /* strb */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_STRB2);
gen_st8(tmp, addr, IS_USER(s));
break;
case 3: /* ldrsb */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_LDRSB);
tmp = gen_ld8s(addr, IS_USER(s));
break;
case 4: /* ldr */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_LDR2);
tmp = gen_ld32(addr, IS_USER(s));
break;
case 5: /* ldrh */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_LDRH2);
tmp = gen_ld16u(addr, IS_USER(s));
break;
case 6: /* ldrb */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_LDRB2);
tmp = gen_ld8u(addr, IS_USER(s));
break;
case 7: /* ldrsh */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_LDRSH);
tmp = gen_ld16s(addr, IS_USER(s));
break;
}
@@ -8313,10 +8970,12 @@ static void disas_thumb_insn(CPUState *e
if (insn & (1 << 11)) {
/* load */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_LDR1);
tmp = gen_ld32(addr, IS_USER(s));
store_reg(s, rd, tmp);
} else {
/* store */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_STR1);
tmp = load_reg(s, rd);
gen_st32(tmp, addr, IS_USER(s));
}
@@ -8333,10 +8992,12 @@ static void disas_thumb_insn(CPUState *e
if (insn & (1 << 11)) {
/* load */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_LDRB1);
tmp = gen_ld8u(addr, IS_USER(s));
store_reg(s, rd, tmp);
} else {
/* store */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_STRB1);
tmp = load_reg(s, rd);
gen_st8(tmp, addr, IS_USER(s));
}
@@ -8353,10 +9014,12 @@ static void disas_thumb_insn(CPUState *e
if (insn & (1 << 11)) {
/* load */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_LDRH1);
tmp = gen_ld16u(addr, IS_USER(s));
store_reg(s, rd, tmp);
} else {
/* store */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_STRH1);
tmp = load_reg(s, rd);
gen_st16(tmp, addr, IS_USER(s));
}
@@ -8372,10 +9035,12 @@ static void disas_thumb_insn(CPUState *e
if (insn & (1 << 11)) {
/* load */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_LDR4);
tmp = gen_ld32(addr, IS_USER(s));
store_reg(s, rd, tmp);
} else {
/* store */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_STR3);
tmp = load_reg(s, rd);
gen_st32(tmp, addr, IS_USER(s));
}
@@ -8387,9 +9052,11 @@ static void disas_thumb_insn(CPUState *e
rd = (insn >> 8) & 7;
if (insn & (1 << 11)) {
/* SP */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_ADD6);
tmp = load_reg(s, 13);
} else {
/* PC. bit 1 is ignored. */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_ADD5);
tmp = new_tmp();
tcg_gen_movi_i32(tmp, (s->pc + 2) & ~(uint32_t)2);
}
@@ -8406,8 +9073,11 @@ static void disas_thumb_insn(CPUState *e
/* adjust stack pointer */
tmp = load_reg(s, 13);
val = (insn & 0x7f) * 4;
- if (insn & (1 << 7))
+ if (insn & (1 << 7)) {
+ instr_count_inc(ARM_THUMB_INSTRUCTION_ADD7);
val = -(int32_t)val;
+ }
+ else instr_count_inc(ARM_THUMB_INSTRUCTION_SUB4);
tcg_gen_addi_i32(tmp, tmp, val);
store_reg(s, 13, tmp);
break;
@@ -8418,10 +9088,22 @@ static void disas_thumb_insn(CPUState *e
rm = (insn >> 3) & 7;
tmp = load_reg(s, rm);
switch ((insn >> 6) & 3) {
- case 0: gen_sxth(tmp); break;
- case 1: gen_sxtb(tmp); break;
- case 2: gen_uxth(tmp); break;
- case 3: gen_uxtb(tmp); break;
+ case 0:
+ instr_count_inc(ARM_THUMB_INSTRUCTION_SXTH);
+ gen_sxth(tmp);
+ break;
+ case 1:
+ instr_count_inc(ARM_THUMB_INSTRUCTION_SXTB);
+ gen_sxtb(tmp);
+ break;
+ case 2:
+ instr_count_inc(ARM_THUMB_INSTRUCTION_UXTH);
+ gen_uxth(tmp);
+ break;
+ case 3:
+ instr_count_inc(ARM_THUMB_INSTRUCTION_UXTB);
+ gen_uxtb(tmp);
+ break;
}
store_reg(s, rd, tmp);
break;
@@ -8443,10 +9125,12 @@ static void disas_thumb_insn(CPUState *e
if (insn & (1 << i)) {
if (insn & (1 << 11)) {
/* pop */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_POP);
tmp = gen_ld32(addr, IS_USER(s));
store_reg(s, i, tmp);
} else {
/* push */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_PUSH);
tmp = load_reg(s, i);
gen_st32(tmp, addr, IS_USER(s));
}
@@ -8458,11 +9142,13 @@ static void disas_thumb_insn(CPUState *e
if (insn & (1 << 8)) {
if (insn & (1 << 11)) {
/* pop pc */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_POP);
tmp = gen_ld32(addr, IS_USER(s));
/* don't set the pc until the rest of the instruction
has completed */
} else {
/* push lr */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_PUSH);
tmp = load_reg(s, 14);
gen_st32(tmp, addr, IS_USER(s));
}
@@ -8506,6 +9192,7 @@ static void disas_thumb_insn(CPUState *e
break;
case 0xe: /* bkpt */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_BKPT);
gen_set_condexec(s);
gen_set_pc_im(s->pc - 2);
gen_exception(EXCP_BKPT);
@@ -8518,15 +9205,25 @@ static void disas_thumb_insn(CPUState *e
rd = insn & 0x7;
tmp = load_reg(s, rn);
switch ((insn >> 6) & 3) {
- case 0: tcg_gen_bswap_i32(tmp, tmp); break;
- case 1: gen_rev16(tmp); break;
- case 3: gen_revsh(tmp); break;
+ case 0:
+ instr_count_inc(ARM_THUMB_INSTRUCTION_REV);
+ tcg_gen_bswap_i32(tmp, tmp);
+ break;
+ case 1:
+ instr_count_inc(ARM_THUMB_INSTRUCTION_REV16);
+ gen_rev16(tmp);
+ break;
+ case 3:
+ instr_count_inc(ARM_THUMB_INSTRUCTION_REVSH);
+ gen_revsh(tmp);
+ break;
default: goto illegal_op;
}
store_reg(s, rd, tmp);
break;
case 6: /* cps */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_CPS);
ARCH(6);
if (IS_USER(s))
break;
@@ -8568,10 +9265,12 @@ static void disas_thumb_insn(CPUState *e
if (insn & (1 << i)) {
if (insn & (1 << 11)) {
/* load */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_LDMIA);
tmp = gen_ld32(addr, IS_USER(s));
store_reg(s, i, tmp);
} else {
/* store */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_STMIA);
tmp = load_reg(s, i);
gen_st32(tmp, addr, IS_USER(s));
}
@@ -8595,6 +9294,7 @@ static void disas_thumb_insn(CPUState *e
if (cond == 0xf) {
/* swi */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_SWI);
gen_set_condexec(s);
gen_set_pc_im(s->pc);
s->is_jmp = DISAS_SWI;
@@ -8607,6 +9307,7 @@ static void disas_thumb_insn(CPUState *e
gen_movl_T1_reg(s, 15);
/* jump to the offset */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_B1);
val = (uint32_t)s->pc + 2;
offset = ((int32_t)insn << 24) >> 24;
val += offset << 1;
@@ -8615,11 +9316,14 @@ static void disas_thumb_insn(CPUState *e
case 14:
if (insn & (1 << 11)) {
+ printf("BLX1\n");
+ instr_count_inc(ARM_THUMB_INSTRUCTION_BLX1);
if (disas_thumb2_insn(env, s, insn))
goto undef32;
break;
}
/* unconditional branch */
+ instr_count_inc(ARM_THUMB_INSTRUCTION_B2);
val = (uint32_t)s->pc;
offset = ((int32_t)insn << 21) >> 21;
val += (offset << 1) + 2;
@@ -8627,6 +9331,11 @@ static void disas_thumb_insn(CPUState *e
break;
case 15:
+ if (insn & (1 << 11)) {
+ instr_count_inc(ARM_THUMB_INSTRUCTION_BL);
+ } else {
+ instr_count_inc(ARM_THUMB_INSTRUCTION_BL_BLX_HIGH_PART);
+ }
if (disas_thumb2_insn(env, s, insn))
goto undef32;
break;
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [Qemu-devel] [PATCH] Instruction counting instrumentation for ARM, 2nd version 2009-06-12 10:56 [Qemu-devel] [PATCH] Instruction counting instrumentation for ARM, 2nd version Sami Kiminki @ 2009-06-12 15:41 ` Jamie Lokier 2009-06-15 8:12 ` Sami Kiminki 2009-06-15 13:26 ` Laurent Desnogues [not found] ` <761ea48b0906150531j6cf88fa2v5652322efcc7469c@mail.gmail.com> 2 siblings, 1 reply; 6+ messages in thread From: Jamie Lokier @ 2009-06-12 15:41 UTC (permalink / raw) To: Sami Kiminki; +Cc: qemu-devel Sami Kiminki wrote: > What we would really like to see is a more general instrumentation > framework, not just instruction counting and not just for ARM targets. > The reason for this is that many measurements are so much easier to do > in emulated/simulated environment than in real HW (e.g. instruction > counting) and doing them in QEMU is way faster than using an ISA > interpreter such as Valgrind. Some other instrumentation examples that > come to my mind are cache usage efficiency analysis, branch profiling, > and naturally instruction and memory access tracing. Valgrind isn't an interpreter. It's a JIT compiler like QEMU's TCG, so are you sure these things are way faster in QEMU? What might work better would be to share some code from Valgrind/Cachegrind. -- Jamie ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [Qemu-devel] [PATCH] Instruction counting instrumentation for ARM, 2nd version 2009-06-12 15:41 ` Jamie Lokier @ 2009-06-15 8:12 ` Sami Kiminki 0 siblings, 0 replies; 6+ messages in thread From: Sami Kiminki @ 2009-06-15 8:12 UTC (permalink / raw) To: Jamie Lokier; +Cc: qemu-devel On Fri, 2009-06-12 at 16:41 +0100, Jamie Lokier wrote: > Sami Kiminki wrote: > > What we would really like to see is a more general instrumentation > > framework, not just instruction counting and not just for ARM targets. > > The reason for this is that many measurements are so much easier to do > > in emulated/simulated environment than in real HW (e.g. instruction > > counting) and doing them in QEMU is way faster than using an ISA > > interpreter such as Valgrind. Some other instrumentation examples that > > come to my mind are cache usage efficiency analysis, branch profiling, > > and naturally instruction and memory access tracing. > > Valgrind isn't an interpreter. It's a JIT compiler like QEMU's TCG, > so are you sure these things are way faster in QEMU? No, not anymore. Thanks for correcting ;) However, what would still speak in favor of having some instrumentation support in QEMU, is measuring things at system-level. I assume this is pretty high in embedded system developers' wish-list. > What might work better would be to share some code from Valgrind/Cachegrind. Obviously. - Sami ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [Qemu-devel] [PATCH] Instruction counting instrumentation for ARM, 2nd version 2009-06-12 10:56 [Qemu-devel] [PATCH] Instruction counting instrumentation for ARM, 2nd version Sami Kiminki 2009-06-12 15:41 ` Jamie Lokier @ 2009-06-15 13:26 ` Laurent Desnogues 2009-06-29 8:42 ` [Qemu-devel] [PATCH] Instruction counting instrumentation for ARM v3 Sami Kiminki [not found] ` <761ea48b0906150531j6cf88fa2v5652322efcc7469c@mail.gmail.com> 2 siblings, 1 reply; 6+ messages in thread From: Laurent Desnogues @ 2009-06-15 13:26 UTC (permalink / raw) To: Sami Kiminki; +Cc: qemu-devel On Fri, Jun 12, 2009 at 12:56 PM, Sami Kiminki<sami.kiminki@tkk.fi> wrote: [...] > > There are also other ways to implement instruction counting (see > responses to our previous patch [1]). As to our approach, I believe this > is the cleanest way to implement this specific instrumentation. However, > from the general point of view, I'm not so sure. I'd like to ask for > more comments and options. Apart from the fact your patch doesn't contain instrumentation.[ch] it is bogus in several places and shows why I think the approach is probably not the best. E.g.: @@ -6300,6 +6809,7 @@ static void disas_arm_insn(CPUState * en if (insn & (1 << 20)) { gen_helper_mark_exclusive(cpu_env, cpu_T[1]); switch (op1) { + instr_count_inc(ARM_INSTRUCTION_LDREX); case 0: /* ldrex */ tmp = gen_ld32(addr, IS_USER(s)); break; This is misplaced. - if (op1 & 2) + if (op1 & 2) { gen_helper_double_saturate(tmp2, tmp2); - if (op1 & 1) + if (op1 & 1) instr_count_inc(ARM_INSTRUCTION_QDSUB); + else instr_count_inc(ARM_INSTRUCTION_QDADD); + } + if (op1 & 1) { gen_helper_sub_saturate(tmp, tmp, tmp2); - else + instr_count_inc(ARM_INSTRUCTION_QSUB); + } + else { gen_helper_add_saturate(tmp, tmp, tmp2); + instr_count_inc(ARM_INSTRUCTION_QADD); + } Here your two last instr_count_inc will overwrite the first two ones. So you don't distinguish between QDADD/QDSUB and QADD/QSUB. I also would like to see a more general instrumentation framework but your approach is too intrusive and so it's too easy to introduce hard to detect bugs. Cheers, Laurent ^ permalink raw reply [flat|nested] 6+ messages in thread
* [Qemu-devel] [PATCH] Instruction counting instrumentation for ARM v3 2009-06-15 13:26 ` Laurent Desnogues @ 2009-06-29 8:42 ` Sami Kiminki 0 siblings, 0 replies; 6+ messages in thread From: Sami Kiminki @ 2009-06-29 8:42 UTC (permalink / raw) To: qemu-devel; +Cc: Laurent Desnogues [-- Attachment #1: Type: text/plain, Size: 2404 bytes --] Hi, Attached is a version of Timo Töyry's patch which should fix the issues pointed out below. I'm not expecting this to get committed, but thought to share it anyway, should anyone have use for it. - Sami On Mon, 2009-06-15 at 15:26 +0200, Laurent Desnogues wrote: > On Fri, Jun 12, 2009 at 12:56 PM, Sami Kiminki<sami.kiminki@tkk.fi> wrote: > [...] > > > > There are also other ways to implement instruction counting (see > > responses to our previous patch [1]). As to our approach, I believe this > > is the cleanest way to implement this specific instrumentation. However, > > from the general point of view, I'm not so sure. I'd like to ask for > > more comments and options. > > Apart from the fact your patch doesn't contain instrumentation.[ch] > it is bogus in several places and shows why I think the approach > is probably not the best. > > E.g.: > > @@ -6300,6 +6809,7 @@ static void disas_arm_insn(CPUState * en > if (insn & (1 << 20)) { > gen_helper_mark_exclusive(cpu_env, cpu_T[1]); > switch (op1) { > + instr_count_inc(ARM_INSTRUCTION_LDREX); > case 0: /* ldrex */ > tmp = gen_ld32(addr, IS_USER(s)); > break; > > This is misplaced. > > - if (op1 & 2) > + if (op1 & 2) { > gen_helper_double_saturate(tmp2, tmp2); > - if (op1 & 1) > + if (op1 & 1) instr_count_inc(ARM_INSTRUCTION_QDSUB); > + else instr_count_inc(ARM_INSTRUCTION_QDADD); > + } > + if (op1 & 1) { > gen_helper_sub_saturate(tmp, tmp, tmp2); > - else > + instr_count_inc(ARM_INSTRUCTION_QSUB); > + } > + else { > gen_helper_add_saturate(tmp, tmp, tmp2); > + instr_count_inc(ARM_INSTRUCTION_QADD); > + } > > Here your two last instr_count_inc will overwrite the first two ones. > So you don't distinguish between QDADD/QDSUB and > QADD/QSUB. > > I also would like to see a more general instrumentation framework > but your approach is too intrusive and so it's too easy to introduce > hard to detect bugs. > > Cheers, > > Laurent [-- Attachment #2: qemu-0.10.4-instrcount-2.patch --] [-- Type: text/x-patch, Size: 100020 bytes --] diff -Nurp qemu-0.10.4/Makefile qemu-0.10.4-instrcount/Makefile --- qemu-0.10.4/Makefile 2009-05-12 17:56:04.000000000 +0300 +++ qemu-0.10.4-instrcount/Makefile 2009-06-29 11:16:23.190995931 +0300 @@ -179,6 +179,10 @@ libqemu_common.a: $(OBJS) # USER_OBJS is code used by qemu userspace emulation USER_OBJS=cutils.o cache-utils.o +# instruction count instrumentation +USER_OBJS+=instrumentation.o + + libqemu_user.a: $(USER_OBJS) ###################################################################### diff -Nurp qemu-0.10.4/Makefile.target qemu-0.10.4-instrcount/Makefile.target --- qemu-0.10.4/Makefile.target 2009-05-12 17:56:04.000000000 +0300 +++ qemu-0.10.4-instrcount/Makefile.target 2009-06-29 11:16:23.184328498 +0300 @@ -208,8 +208,10 @@ ifeq ($(findstring s390, $(TARGET_ARCH) LIBOBJS+=s390-dis.o endif -# libqemu +# instrumentation support +LIBOBJS+=instrumentation.o +# libqemu libqemu.a: $(LIBOBJS) translate.o: translate.c cpu.h diff -Nurp qemu-0.10.4/instrumentation.c qemu-0.10.4-instrcount/instrumentation.c --- qemu-0.10.4/instrumentation.c 1970-01-01 02:00:00.000000000 +0200 +++ qemu-0.10.4-instrcount/instrumentation.c 2009-06-29 11:16:23.190995931 +0300 @@ -0,0 +1,37 @@ +/* + * instrument.c + * + * Created on: May 14, 2009 + * Author: ttoyry + */ + +#include "instrumentation.h" +unsigned int instrumentation_count_instructions = 0; +unsigned int instrumentation_count_instructions_log = 0; + +/* +static instr_counter_offsets instr_offsets; + +static inline void instr_count_inc_init(uint32_t offset, int instr) +{ + if (!instrumentation_count_instructions) return; + instr_offsets.cpustate_offset = offset; + TCGv tmp = new_tmp(); + tcg_gen_ld_i32(tmp, cpu_env, instr_offsets.cpustate_offset + sizeof(uint32_t) * instr); + instr_offsets.tcg_offset[0] = gen_opparam_ptr - 1; + tcg_gen_addi_i32(tmp, tmp, 1); + tcg_gen_st_i32(tmp, cpu_env, instr_offsets.cpustate_offset + sizeof(uint32_t) * instr); + instr_offsets.tcg_offset[1] = gen_opparam_ptr - 1; + dead_tmp(tmp); +} + + Increment instruction counter +static inline void instr_count_inc(int instr) +{ + if (!instrumentation_count_instructions) return; + *(instr_offsets.tcg_offset[0]) = instr_offsets.cpustate_offset + sizeof(uint32_t) * instr; + *(instr_offsets.tcg_offset[1]) = instr_offsets.cpustate_offset + sizeof(uint32_t) * instr; +} +*/ + + diff -Nurp qemu-0.10.4/instrumentation.h qemu-0.10.4-instrcount/instrumentation.h --- qemu-0.10.4/instrumentation.h 1970-01-01 02:00:00.000000000 +0200 +++ qemu-0.10.4-instrcount/instrumentation.h 2009-06-29 11:16:23.190995931 +0300 @@ -0,0 +1,47 @@ +/* + * instrumentation.h + * + * Author: Timo Toyry + */ + +#ifndef INSTRUMENTATION_H +#define INSTRUMENTATION_H + +#include <stdarg.h> +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <inttypes.h> + +/* + * 0 to disable (default) + * nonzero to enable + */ +extern unsigned int instrumentation_count_instructions; + +/* + * 0 output counters to stderr (default) + * nonzero output counters to qemulog-file + */ +extern unsigned int instrumentation_count_instructions_log; + +/* +extern TCGv_ptr cpu_env; +extern TCGv_i32 new_tmp(void); +extern void dead_tmp(TCGv tmp); + +#define ARM_INSTRUCTION_COUNTER_OFFSET offsetof(CPUState, arm_instr_count) +#define ARM_VFP_INSTRUCTION_COUNTER_OFFSET offsetof(CPUState, arm_vfp_instr_count) +#define ARM_THUMB_INSTRUCTION_COUNTER_OFFSET offsetof(CPUState, arm_thumb_instr_count) + +static inline void instr_count_inc_init(uint32_t offset, int instr); +static inline void instr_count_inc(int instr); + +typedef struct instr_counter_offsets { + uint32_t cpustate_offset; + TCGArg *tcg_offset[2]; +} instr_counter_offsets; +*/ + + +#endif /* INSTRUMENTATION_H */ diff -Nurp qemu-0.10.4/linux-user/main.c qemu-0.10.4-instrcount/linux-user/main.c --- qemu-0.10.4/linux-user/main.c 2009-05-12 17:56:03.000000000 +0300 +++ qemu-0.10.4-instrcount/linux-user/main.c 2009-06-29 11:16:23.187663087 +0300 @@ -35,6 +35,8 @@ #include "envlist.h" +#include "instrumentation.h" + #define DEBUG_LOGFILE "/tmp/qemu.log" char *exec_path; @@ -2199,6 +2201,12 @@ static void usage(void) "-p pagesize set the host page size to 'pagesize'\n" "-strace log system calls\n" "\n" +#ifdef TARGET_ARM + "Other:\n" + "-instrcount Count instructions\n" + "-instrcountlog=qemu_log Output counters to qemu-log file\n" + "\n" +#endif "Environment variables:\n" "QEMU_STRACE Print system calls and arguments similar to the\n" " 'strace' program. Enable by setting to any value.\n" @@ -2341,8 +2349,11 @@ int main(int argc, char **argv, char **e (void) envlist_unsetenv(envlist, "LD_PRELOAD"); } else if (!strcmp(r, "strace")) { do_strace = 1; - } else - { + } else if (!strcmp(r, "instrcount")) { + instrumentation_count_instructions = 1; + } else if (!strcmp(r, "instrcountlog=qemu_log")) { + instrumentation_count_instructions_log = 1; + } else { usage(); } } diff -Nurp qemu-0.10.4/linux-user/syscall.c qemu-0.10.4-instrcount/linux-user/syscall.c --- qemu-0.10.4/linux-user/syscall.c 2009-05-12 17:56:03.000000000 +0300 +++ qemu-0.10.4-instrcount/linux-user/syscall.c 2009-06-29 11:16:23.187663087 +0300 @@ -79,6 +79,9 @@ #include "qemu.h" #include "qemu-common.h" +#include "qemu-log.h" +#include "instrumentation.h" + #if defined(USE_NPTL) #include <linux/futex.h> #define CLONE_NPTL_FLAGS2 (CLONE_SETTLS | \ @@ -300,6 +303,67 @@ extern int setfsuid(int); extern int setfsgid(int); extern int setgroups(int, gid_t *); + +inline static void print_counters(const char *buf) +{ + if (!instrumentation_count_instructions_log) { + fprintf(stderr, "%s", buf); + } else { + qemu_log("%s", buf); + } +} + +inline static void print_instruction_counters_helper( + const char **instr_names, int no_instructions, const uint32_t *counters) +{ + char buf[256]; + int i1; + uint32_t counted = 0; + for (i1 = 0; i1 < no_instructions; i1++) { + if (counters[i1] > 0) { + sprintf(buf, "%s: %d\n", instr_names[i1], + counters[i1]); + print_counters(buf); + if (i1 < (no_instructions - 2)) { + counted += counters[i1]; + } + } + } + sprintf(buf, "Counted instructions: %d\n", counted); + print_counters(buf); +} + +inline static void print_instruction_counters(CPUState *env) +{ + char buf[256]; +#ifdef TARGET_ARM + if (!instrumentation_count_instructions) return; + if (instrumentation_count_instructions_log && !logfile) { + fprintf(stderr, "Setting log file to \"qemu_instr_count.log\"\n"); + cpu_set_log_filename("qemu_instr_count.log"); + cpu_set_log(1); + } + + sprintf(buf, "Arm instructions:\n"); + print_counters(buf); + print_instruction_counters_helper(arm_instr_names, ARM_INSTRUCTIONS, + env->arm_instr_count); + + sprintf(buf, "VFP instructions:\n"); + print_counters(buf); + print_instruction_counters_helper(arm_vfp_instr_names, + ARM_VFP_INSTRUCTIONS, env->arm_vfp_instr_count); + + sprintf(buf, "Thumb instructions:\n"); + print_counters(buf); + print_instruction_counters_helper(arm_thumb_instr_names, + ARM_THUMB_INSTRUCTIONS, env->arm_thumb_instr_count); +#else + sprintf(buf, "Instruction counting not supported in this platform.\n"); + print_counters(buf); +#endif +} + #define ERRNO_TABLE_SIZE 1200 /* target_to_host_errno_table[] is initialized from @@ -3431,6 +3495,7 @@ abi_long do_syscall(void *cpu_env, int n #ifdef HAVE_GPROF _mcleanup(); #endif + print_instruction_counters(cpu_env); gdb_exit(cpu_env, arg1); /* XXX: should free thread stack and CPU env */ sys_exit(arg1); @@ -4923,6 +4988,7 @@ abi_long do_syscall(void *cpu_env, int n #ifdef HAVE_GPROF _mcleanup(); #endif + print_instruction_counters(cpu_env); gdb_exit(cpu_env, arg1); ret = get_errno(exit_group(arg1)); break; diff -Nurp qemu-0.10.4/target-arm/cpu.h qemu-0.10.4-instrcount/target-arm/cpu.h --- qemu-0.10.4/target-arm/cpu.h 2009-05-12 17:56:33.000000000 +0300 +++ qemu-0.10.4-instrcount/target-arm/cpu.h 2009-06-29 11:16:23.190995931 +0300 @@ -51,6 +51,346 @@ #define ARMV7M_EXCP_PENDSV 14 #define ARMV7M_EXCP_SYSTICK 15 +/* Do not change the order of the instructions in the blocks marked + * by - | -. */ +enum arm_instructions { + ARM_INSTRUCTION_B, + ARM_INSTRUCTION_BL, + ARM_INSTRUCTION_BLX, + ARM_INSTRUCTION_BX, + ARM_INSTRUCTION_BXJ, + ARM_INSTRUCTION_ADC, + ARM_INSTRUCTION_ADD, + ARM_INSTRUCTION_AND, + ARM_INSTRUCTION_BIC, + ARM_INSTRUCTION_CMN, + ARM_INSTRUCTION_CMP, + ARM_INSTRUCTION_EOR, + ARM_INSTRUCTION_MOV, + ARM_INSTRUCTION_MVN, + ARM_INSTRUCTION_ORR, + ARM_INSTRUCTION_RSB, + ARM_INSTRUCTION_RSC, + ARM_INSTRUCTION_SBC, + ARM_INSTRUCTION_SUB, + ARM_INSTRUCTION_TEQ, + ARM_INSTRUCTION_TST, + ARM_INSTRUCTION_MUL, /* - */ + ARM_INSTRUCTION_MULS, /* - */ + ARM_INSTRUCTION_MLA, /* - */ + ARM_INSTRUCTION_MLAS, /* - */ + ARM_INSTRUCTION_SMLAXY, + ARM_INSTRUCTION_SMLAL, /* - */ + ARM_INSTRUCTION_SMLALS, /* - */ + ARM_INSTRUCTION_SMLALXY, + ARM_INSTRUCTION_SMLAWY, + ARM_INSTRUCTION_SMUAD, /* - */ + ARM_INSTRUCTION_SMUSD, /* | */ + ARM_INSTRUCTION_SMLAD, /* | */ + ARM_INSTRUCTION_SMLSD, /* - */ + ARM_INSTRUCTION_SMLALD, /* - */ + ARM_INSTRUCTION_SMLSLD, /* - */ + ARM_INSTRUCTION_SMMLA, + ARM_INSTRUCTION_SMMLS, + ARM_INSTRUCTION_SMMUL, + ARM_INSTRUCTION_SMULXY, + ARM_INSTRUCTION_SMULL, /* - */ + ARM_INSTRUCTION_SMULLS, /* - */ + ARM_INSTRUCTION_SMULWY, + ARM_INSTRUCTION_UMAAL, + ARM_INSTRUCTION_UMLAL, /* - */ + ARM_INSTRUCTION_UMLALS, /* - */ + ARM_INSTRUCTION_UMULL, /* - */ + ARM_INSTRUCTION_UMULLS, /* - */ + ARM_INSTRUCTION_QADD, + ARM_INSTRUCTION_QDADD, + ARM_INSTRUCTION_QADD16, /* - */ + ARM_INSTRUCTION_QADDSUBX, /* | */ + ARM_INSTRUCTION_QSUBADDX, /* | */ + ARM_INSTRUCTION_QSUB16, /* | */ + ARM_INSTRUCTION_QADD8, /* | */ + ARM_INSTRUCTION_QSUB8, /* - */ + ARM_INSTRUCTION_QSUB, + ARM_INSTRUCTION_QDSUB, + ARM_INSTRUCTION_SADD16, /* - */ + ARM_INSTRUCTION_SADDSUBX, /* | */ + ARM_INSTRUCTION_SSUBADDX, /* | */ + ARM_INSTRUCTION_SSUB16, /* | */ + ARM_INSTRUCTION_SADD8, /* | */ + ARM_INSTRUCTION_SSUB8, /* - */ + ARM_INSTRUCTION_SHADD16, /* - */ + ARM_INSTRUCTION_SHADDSUBX, /* | */ + ARM_INSTRUCTION_SHSUBADDX, /* | */ + ARM_INSTRUCTION_SHSUB16, /* | */ + ARM_INSTRUCTION_SHADD8, /* | */ + ARM_INSTRUCTION_SHSUB8, /* - */ + ARM_INSTRUCTION_UADD16, /* - */ + ARM_INSTRUCTION_UADDSUBX, /* | */ + ARM_INSTRUCTION_USUBADDX, /* | */ + ARM_INSTRUCTION_USUB16, /* | */ + ARM_INSTRUCTION_UADD8, /* | */ + ARM_INSTRUCTION_USUB8, /* - */ + ARM_INSTRUCTION_UHADD16, /* - */ + ARM_INSTRUCTION_UHADDSUBX, /* | */ + ARM_INSTRUCTION_UHSUBADDX, /* | */ + ARM_INSTRUCTION_UHSUB16, /* | */ + ARM_INSTRUCTION_UHADD8, /* | */ + ARM_INSTRUCTION_UHSUB8, /* - */ + ARM_INSTRUCTION_UQADD16, /* - */ + ARM_INSTRUCTION_UQADDSUBX, /* | */ + ARM_INSTRUCTION_UQSUBADDX, /* | */ + ARM_INSTRUCTION_UQSUB16, /* | */ + ARM_INSTRUCTION_UQADD8, /* | */ + ARM_INSTRUCTION_UQSUB8, /* - */ + ARM_INSTRUCTION_SXTAB16, /* - */ + ARM_INSTRUCTION_SXTAB, /* | */ + ARM_INSTRUCTION_SXTAH, /* | */ + ARM_INSTRUCTION_SXTB16, /* | */ + ARM_INSTRUCTION_SXTB, /* | */ + ARM_INSTRUCTION_SXTH, /* - */ + ARM_INSTRUCTION_UXTAB16, /* - */ + ARM_INSTRUCTION_UXTAB, /* | */ + ARM_INSTRUCTION_UXTAH, /* | */ + ARM_INSTRUCTION_UXTB16, /* | */ + ARM_INSTRUCTION_UXTB, /* | */ + ARM_INSTRUCTION_UXTH, /* - */ + ARM_INSTRUCTION_CLZ, + ARM_INSTRUCTION_USAD8, + ARM_INSTRUCTION_USADA8, + ARM_INSTRUCTION_PKH, + ARM_INSTRUCTION_PKHBT, + ARM_INSTRUCTION_PKHTB, + ARM_INSTRUCTION_REV, + ARM_INSTRUCTION_REV16, + ARM_INSTRUCTION_REVSH, + ARM_INSTRUCTION_SEL, + ARM_INSTRUCTION_SSAT, + ARM_INSTRUCTION_SSAT16, + ARM_INSTRUCTION_USAT, + ARM_INSTRUCTION_USAT16, + ARM_INSTRUCTION_MRS, + ARM_INSTRUCTION_MSR, + ARM_INSTRUCTION_CPS, + ARM_INSTRUCTION_SETEND, + ARM_INSTRUCTION_LDR, + ARM_INSTRUCTION_LDRB, + ARM_INSTRUCTION_LDRBT, + ARM_INSTRUCTION_LDRD, + ARM_INSTRUCTION_LDREX, + ARM_INSTRUCTION_LDREXD, + ARM_INSTRUCTION_LDREXB, + ARM_INSTRUCTION_LDREXH, + ARM_INSTRUCTION_LDRH, + ARM_INSTRUCTION_LDRSB, + ARM_INSTRUCTION_LDRSH, + ARM_INSTRUCTION_LDRT, + ARM_INSTRUCTION_STR, + ARM_INSTRUCTION_STRB, + ARM_INSTRUCTION_STRBT, + ARM_INSTRUCTION_STRD, + ARM_INSTRUCTION_STREX, + ARM_INSTRUCTION_STREXD, + ARM_INSTRUCTION_STREXB, + ARM_INSTRUCTION_STREXH, + ARM_INSTRUCTION_STRH, + ARM_INSTRUCTION_STRT, + ARM_INSTRUCTION_LDM1, //See Arm manual ARM DDI 0100I page A3-27 + ARM_INSTRUCTION_LDM2, + ARM_INSTRUCTION_LDM3, + ARM_INSTRUCTION_STM1, + ARM_INSTRUCTION_STM2, + ARM_INSTRUCTION_SWP, + ARM_INSTRUCTION_SWPB, + ARM_INSTRUCTION_BKPT, + ARM_INSTRUCTION_SWI, + ARM_INSTRUCTION_CDP, + ARM_INSTRUCTION_LDC, + ARM_INSTRUCTION_MCR, + ARM_INSTRUCTION_MCRR, + ARM_INSTRUCTION_MRC, + ARM_INSTRUCTION_MRRC, + ARM_INSTRUCTION_STC, + ARM_INSTRUCTION_PLD, + ARM_INSTRUCTION_RFE, + ARM_INSTRUCTION_SRS, + ARM_INSTRUCTION_MCRR2, + ARM_INSTRUCTION_MRRC2, + ARM_INSTRUCTION_STC2, + ARM_INSTRUCTION_LDC2, + ARM_INSTRUCTION_CDP2, + ARM_INSTRUCTION_MCR2, + ARM_INSTRUCTION_MRC2, + ARM_INSTRUCTION_COPROCESSOR, + ARM_INSTRUCTION_UNKNOWN, + ARM_INSTRUCTION_NOT_INSTRUMENTED, + ARM_INSTRUCTION_TOTAL_COUNT, + ARM_INSTRUCTIONS +}; + +/* Do not change the order of the instructions in the blocks marked + * by - | -. */ +enum arm_vfp_instructions { + ARM_VFP_INSTRUCTION_FABSD, /* - */ + ARM_VFP_INSTRUCTION_FABSS, /* - */ + ARM_VFP_INSTRUCTION_FADDD, /* - */ + ARM_VFP_INSTRUCTION_FADDS, /* - */ + ARM_VFP_INSTRUCTION_FCMPD, /* - */ + ARM_VFP_INSTRUCTION_FCMPS, /* - */ + ARM_VFP_INSTRUCTION_FCMPED, /* - */ + ARM_VFP_INSTRUCTION_FCMPES, /* - */ + ARM_VFP_INSTRUCTION_FCMPEZD, /* - */ + ARM_VFP_INSTRUCTION_FCMPEZS, /* - */ + ARM_VFP_INSTRUCTION_FCMPZD, /* - */ + ARM_VFP_INSTRUCTION_FCMPZS, /* - */ + ARM_VFP_INSTRUCTION_FCPYD, /* - */ + ARM_VFP_INSTRUCTION_FCPYS, /* - */ + ARM_VFP_INSTRUCTION_FCVTDS, /* - */ + ARM_VFP_INSTRUCTION_FCVTSD, /* - */ + ARM_VFP_INSTRUCTION_FDIVD, /* - */ + ARM_VFP_INSTRUCTION_FDIVS, /* - */ + ARM_VFP_INSTRUCTION_FLDD, /* - */ + ARM_VFP_INSTRUCTION_FLDS, /* - */ + ARM_VFP_INSTRUCTION_FLDMD, /* - */ + ARM_VFP_INSTRUCTION_FLDMS, /* - */ + ARM_VFP_INSTRUCTION_FLDMX, + ARM_VFP_INSTRUCTION_FMACD, + ARM_VFP_INSTRUCTION_FMACS, + ARM_VFP_INSTRUCTION_FMDHR, + ARM_VFP_INSTRUCTION_FMDLR, + ARM_VFP_INSTRUCTION_FMDRR, + ARM_VFP_INSTRUCTION_FMRDH, + ARM_VFP_INSTRUCTION_FMRDL, + ARM_VFP_INSTRUCTION_FMRRD, /* - */ + ARM_VFP_INSTRUCTION_FMRRS, /* - */ + ARM_VFP_INSTRUCTION_FMRS, + ARM_VFP_INSTRUCTION_FMRX, + ARM_VFP_INSTRUCTION_FMSCD, /* - */ + ARM_VFP_INSTRUCTION_FMSCS, /* - */ + ARM_VFP_INSTRUCTION_FMSR, + ARM_VFP_INSTRUCTION_FMSRR, + ARM_VFP_INSTRUCTION_FMSTAT, + ARM_VFP_INSTRUCTION_FMULD, /* - */ + ARM_VFP_INSTRUCTION_FMULS, /* - */ + ARM_VFP_INSTRUCTION_FMXR, + ARM_VFP_INSTRUCTION_FNEGD, /* - */ + ARM_VFP_INSTRUCTION_FNEGS, /* - */ + ARM_VFP_INSTRUCTION_FNMACD, /* - */ + ARM_VFP_INSTRUCTION_FNMACS, /* - */ + ARM_VFP_INSTRUCTION_FNMSCD, /* - */ + ARM_VFP_INSTRUCTION_FNMSCS, /* - */ + ARM_VFP_INSTRUCTION_FNMULD, /* - */ + ARM_VFP_INSTRUCTION_FNMULS, /* - */ + ARM_VFP_INSTRUCTION_FSITOD, /* - */ + ARM_VFP_INSTRUCTION_FSITOS, /* - */ + ARM_VFP_INSTRUCTION_FSQRTD, /* - */ + ARM_VFP_INSTRUCTION_FSQRTS, /* - */ + ARM_VFP_INSTRUCTION_FSTD, /* - */ + ARM_VFP_INSTRUCTION_FSTS, /* - */ + ARM_VFP_INSTRUCTION_FSTMD, + ARM_VFP_INSTRUCTION_FSTMS, + ARM_VFP_INSTRUCTION_FSTMX, + ARM_VFP_INSTRUCTION_FSUBD, /* - */ + ARM_VFP_INSTRUCTION_FSUBS, /* - */ + ARM_VFP_INSTRUCTION_FTOSID, /* - */ + ARM_VFP_INSTRUCTION_FTOSIS, /* - */ + ARM_VFP_INSTRUCTION_FTOSIZD, /* - */ + ARM_VFP_INSTRUCTION_FTOSIZS, /* - */ + ARM_VFP_INSTRUCTION_FTOUID, /* - */ + ARM_VFP_INSTRUCTION_FTOUIS, /* - */ + ARM_VFP_INSTRUCTION_FTOUIZD, /* - */ + ARM_VFP_INSTRUCTION_FTOUIZS, /* - */ + ARM_VFP_INSTRUCTION_FUITOD, /* - */ + ARM_VFP_INSTRUCTION_FUITOS, /* - */ + ARM_VFP_INSTRUCTION_UNKNOWN, + ARM_VFP_INSTRUCTION_NOT_INSTRUMENTED, + ARM_VFP_INSTRUCTION_TOTAL_COUNT, + ARM_VFP_INSTRUCTIONS +}; + +/* Do not change the order of the instructions in the blocks marked + * by - | -. */ +enum arm_thumb_instructions { + ARM_THUMB_INSTRUCTION_ADC, + ARM_THUMB_INSTRUCTION_ADD1, /* - */ + ARM_THUMB_INSTRUCTION_ADD2, /* | */ + ARM_THUMB_INSTRUCTION_ADD3, /* - */ + ARM_THUMB_INSTRUCTION_ADD4, + ARM_THUMB_INSTRUCTION_ADD5, + ARM_THUMB_INSTRUCTION_ADD6, + ARM_THUMB_INSTRUCTION_ADD7, + ARM_THUMB_INSTRUCTION_AND, + ARM_THUMB_INSTRUCTION_ASR1, + ARM_THUMB_INSTRUCTION_ASR2, + ARM_THUMB_INSTRUCTION_B1, + ARM_THUMB_INSTRUCTION_B2, + ARM_THUMB_INSTRUCTION_BIC, + ARM_THUMB_INSTRUCTION_BKPT, + ARM_THUMB_INSTRUCTION_BL, + ARM_THUMB_INSTRUCTION_BLX1, + ARM_THUMB_INSTRUCTION_BLX2, + ARM_THUMB_INSTRUCTION_BL_BLX_HIGH_PART, + ARM_THUMB_INSTRUCTION_BX, + ARM_THUMB_INSTRUCTION_CMN, + ARM_THUMB_INSTRUCTION_CMP1, + ARM_THUMB_INSTRUCTION_CMP2, + ARM_THUMB_INSTRUCTION_CMP3, + ARM_THUMB_INSTRUCTION_CPS, + ARM_THUMB_INSTRUCTION_CPY, + ARM_THUMB_INSTRUCTION_EOR, + ARM_THUMB_INSTRUCTION_LDMIA, + ARM_THUMB_INSTRUCTION_LDR1, + ARM_THUMB_INSTRUCTION_LDR2, + ARM_THUMB_INSTRUCTION_LDR3, + ARM_THUMB_INSTRUCTION_LDR4, + ARM_THUMB_INSTRUCTION_LDRB1, + ARM_THUMB_INSTRUCTION_LDRB2, + ARM_THUMB_INSTRUCTION_LDRH1, + ARM_THUMB_INSTRUCTION_LDRH2, + ARM_THUMB_INSTRUCTION_LDRSB, + ARM_THUMB_INSTRUCTION_LDRSH, + ARM_THUMB_INSTRUCTION_LSL1, + ARM_THUMB_INSTRUCTION_LSL2, + ARM_THUMB_INSTRUCTION_LSR1, + ARM_THUMB_INSTRUCTION_LSR2, + ARM_THUMB_INSTRUCTION_MOV1, + ARM_THUMB_INSTRUCTION_MOV2, + ARM_THUMB_INSTRUCTION_MOV3, + ARM_THUMB_INSTRUCTION_MUL, + ARM_THUMB_INSTRUCTION_MVN, + ARM_THUMB_INSTRUCTION_NEG, + ARM_THUMB_INSTRUCTION_ORR, + ARM_THUMB_INSTRUCTION_POP, + ARM_THUMB_INSTRUCTION_PUSH, + ARM_THUMB_INSTRUCTION_REV, + ARM_THUMB_INSTRUCTION_REV16, + ARM_THUMB_INSTRUCTION_REVSH, + ARM_THUMB_INSTRUCTION_ROR, + ARM_THUMB_INSTRUCTION_SBC, + ARM_THUMB_INSTRUCTION_SETEND, + ARM_THUMB_INSTRUCTION_STMIA, + ARM_THUMB_INSTRUCTION_STR1, + ARM_THUMB_INSTRUCTION_STR2, + ARM_THUMB_INSTRUCTION_STR3, + ARM_THUMB_INSTRUCTION_STRB1, + ARM_THUMB_INSTRUCTION_STRB2, + ARM_THUMB_INSTRUCTION_STRH1, + ARM_THUMB_INSTRUCTION_STRH2, + ARM_THUMB_INSTRUCTION_SUB1, /* - */ + ARM_THUMB_INSTRUCTION_SUB2, /* | */ + ARM_THUMB_INSTRUCTION_SUB3, /* - */ + ARM_THUMB_INSTRUCTION_SUB4, + ARM_THUMB_INSTRUCTION_SWI, + ARM_THUMB_INSTRUCTION_SXTB, + ARM_THUMB_INSTRUCTION_SXTH, + ARM_THUMB_INSTRUCTION_TST, + ARM_THUMB_INSTRUCTION_UXTB, + ARM_THUMB_INSTRUCTION_UXTH, + ARM_THUMB_INSTRUCTION_UNKNOWN, + ARM_THUMB_INSTRUCTION_NOT_INSTRUMENTED, + ARM_THUMB_INSTRUCTION_TOTAL_COUNT, + ARM_THUMB_INSTRUCTIONS +}; + typedef void ARMWriteCPFunc(void *opaque, int cp_info, int srcreg, int operand, uint32_t value); typedef uint32_t ARMReadCPFunc(void *opaque, int cp_info, @@ -202,6 +542,12 @@ typedef struct CPUARMState { /* These fields after the common ones so they are preserved on reset. */ struct arm_boot_info *boot_info; + + /* Instruction counting "regs". */ + uint32_t arm_instr_count[ARM_INSTRUCTIONS]; + uint32_t arm_vfp_instr_count[ARM_VFP_INSTRUCTIONS]; + uint32_t arm_thumb_instr_count[ARM_THUMB_INSTRUCTIONS]; + } CPUARMState; CPUARMState *cpu_arm_init(const char *cpu_model); @@ -446,4 +792,8 @@ static inline void cpu_get_tb_cpu_state( *flags |= (1 << 7); } +extern const char const *arm_instr_names[]; +extern const char const *arm_vfp_instr_names[]; +extern const char const *arm_thumb_instr_names[]; + #endif diff -Nurp qemu-0.10.4/target-arm/translate.c qemu-0.10.4-instrcount/target-arm/translate.c --- qemu-0.10.4/target-arm/translate.c 2009-05-12 17:56:33.000000000 +0300 +++ qemu-0.10.4-instrcount/target-arm/translate.c 2009-06-29 11:16:23.217662358 +0300 @@ -31,6 +31,8 @@ #include "tcg-op.h" #include "qemu-log.h" +#include "instrumentation.h" + #include "helpers.h" #define GEN_HELPER 1 #include "helpers.h" @@ -235,6 +237,371 @@ static void store_reg(DisasContext *s, i /* Set NZCV flags from the high 4 bits of var. */ #define gen_set_nzcv(var) gen_set_cpsr(var, CPSR_NZCV) +/* string names for arm_instruction enum values */ +const char const *arm_instr_names[] = { + "b", + "bl", + "blx", + "bx", + "bxj", + "adc", + "add", + "and", + "bic", + "cmn", + "cmp", + "eor", + "mov", + "mvn", + "orr", + "rsb", + "rsc", + "sbc", + "sub", + "teq", + "tst", + "mul", + "muls", + "mla", + "mlas", + "smla<x><y>", + "smlal", + "smlals", + "smlal<x><y>", + "smlaw<y>", + "smuad", + "smusd", + "smlad", + "smlsd", + "smlald", + "smlsld", + "smmla", + "smmls", + "smmul", + "smul<x><y>", + "smull", + "smulls", + "smulw<y>", + "umaal", + "umlal", + "umlals", + "umull", + "umulls", + "qadd", + "qdadd", + "qadd16", + "qaddsubx", + "qsubaddx", + "qsub16", + "qadd8", + "qsub8", + "qsub", + "qdsub", + "sadd16", + "saddsubx", + "ssubaddx", + "ssub16", + "sadd8", + "ssub8", + "shadd16", + "shaddsubx", + "shsubaddx", + "shsub16", + "shadd8", + "shsub8", + "uadd16", + "uaddsubx", + "usubaddx", + "usub16", + "uadd8", + "usub8", + "uhadd16", + "uhaddsubx", + "uhsubaddx", + "uhsub16", + "uhadd8", + "uhsub8", + "uqadd16", + "uqaddsubx", + "uqsubaddx", + "uqsub16", + "uqadd8", + "uqsub8", + "sxtab16", + "sxtab", + "sxtah", + "sxtb16", + "sxtb", + "sxth", + "uxtab16", + "uxtab", + "uxtah", + "uxtb16", + "uxtb", + "uxth", + "clz", + "usad8", + "usada8", + "pkh", + "pkhbt", + "pkhtb", + "rev", + "rev16", + "revsh", + "sel", + "ssat", + "ssat16", + "usat", + "usat16", + "mrs", + "msr", + "cps", + "setend", + "ldr", + "ldrb", + "ldrbt", + "ldrd", + "ldrex", + "ldrexd", + "ldrexb", + "ldrexh", + "ldrh", + "ldrsb", + "ldrsh", + "ldrt", + "str", + "strb", + "strbt", + "strd", + "strex", + "strexd", + "strexb", + "strexh", + "strh", + "strt", + "ldm1", //see arm manual ARM DDI 0100I page A3-27 + "ldm2", + "ldm3", + "stm1", + "stm2", + "swp", + "swpb", + "bkpt", + "swi", + "cdp", + "ldc", + "mcr", + "mcrr", + "mrc", + "mrrc", + "stc", + "pld", + "rfe", + "srs", + "mcrr2", + "mrrc2", + "stc2", + "ldc2", + "cdp2", + "mcr2", + "mrc2", + "coprocessor", + "unknown", + "not_instrumented", + "total_instructions" +}; + +const char const *arm_vfp_instr_names[] = { /* string names for arm_vfp_instruction enum values */ + "fabsd", + "fabss", + "faddd", + "fadds", + "fcmpd", + "fcmps", + "fcmped", + "fcmpes", + "fcmpezd", + "fcmpezs", + "fcmpzd", + "fcmpzs", + "fcpyd", + "fcpys", + "fcvtds", + "fcvtsd", + "fdivd", + "fdivs", + "fldd", + "flds", + "fldmd", + "fldms", + "fldmx", + "fmacd", + "fmacs", + "fmdhr", + "fmdlr", + "fmdrr", + "fmrdh", + "fmrdl", + "fmrrd", + "fmrrs", + "fmrs", + "fmrx", + "fmscd", + "fmscs", + "fmsr", + "fmsrr", + "fmstat", + "fmuld", + "fmuls", + "fmxr", + "fnegd", + "fnegs", + "fnmacd", + "fnmacs", + "fnmscd", + "fnmscs", + "fnmuld", + "fnmuls", + "fsitod", + "fsitos", + "fsqrtd", + "fsqrts", + "fstd", + "fsts", + "fstmd", + "fstms", + "fstmx", + "fsubd", + "fsubs", + "ftosid", + "ftosis", + "ftosizd", + "ftosizs", + "ftouid", + "ftouis", + "ftouizd", + "ftouizs", + "fuitod", + "fuitos", + "unknown", + "not_instrumented", + "total_count" +}; + +/* string names for arm_thumb_instruction enum values */ +const char const *arm_thumb_instr_names[] = { + "adc", + "add1", + "add2", + "add3", + "add4", + "add5", + "add6", + "add7", + "and", + "asr1", + "asr2", + "b1", + "b2", + "bic", + "bkpt", + "bl", + "blx1", + "blx2", + "bl-blx_high", + "bx", + "cmn", + "cmp1", + "cmp2", + "cmp3", + "cps", + "cpy", + "eor", + "ldmia", + "ldr1", + "ldr2", + "ldr3", + "ldr4", + "ldrb1", + "ldrb2", + "ldrh1", + "ldrh2", + "ldrsb", + "ldrsh", + "lsl1", + "lsl2", + "lsr1", + "lsr2", + "mov1", + "mov2", + "mov3", + "mul", + "mvn", + "neg", + "orr", + "pop", + "push", + "rev", + "rev16", + "revsh", + "ror", + "sbc", + "setend", + "stmia", + "str1", + "str2", + "str3", + "strb1", + "strb2", + "strh1", + "strh2", + "sub1", + "sub2", + "sub3", + "sub4", + "swi", + "sxtb", + "sxth", + "tst", + "uxtb", + "uxth", + "unknown", + "not_instrumented", + "total_count", +}; + +#define ARM_INSTRUCTION_COUNTER_OFFSET offsetof(CPUState, arm_instr_count) +#define ARM_VFP_INSTRUCTION_COUNTER_OFFSET offsetof(CPUState, arm_vfp_instr_count) +#define ARM_THUMB_INSTRUCTION_COUNTER_OFFSET offsetof(CPUState, arm_thumb_instr_count) + +typedef struct instr_counter_offsets { + uint32_t cpustate_offset; + TCGArg *tcg_offset[2]; +} instr_counter_offsets; + +static instr_counter_offsets instr_offsets; + +static inline void instr_count_inc_init(uint32_t offset, int instr) +{ + if (!instrumentation_count_instructions) return; + instr_offsets.cpustate_offset = offset; + TCGv tmp = new_tmp(); + tcg_gen_ld_i32(tmp, cpu_env, instr_offsets.cpustate_offset + sizeof(uint32_t) * instr); + instr_offsets.tcg_offset[0] = gen_opparam_ptr - 1; + tcg_gen_addi_i32(tmp, tmp, 1); + tcg_gen_st_i32(tmp, cpu_env, instr_offsets.cpustate_offset + sizeof(uint32_t) * instr); + instr_offsets.tcg_offset[1] = gen_opparam_ptr - 1; + dead_tmp(tmp); +} + +/* Increment instruction counter */ +static inline void instr_count_inc(int instr) +{ + if (!instrumentation_count_instructions) return; + *(instr_offsets.tcg_offset[0]) = instr_offsets.cpustate_offset + sizeof(uint32_t) * instr; + *(instr_offsets.tcg_offset[1]) = instr_offsets.cpustate_offset + sizeof(uint32_t) * instr; +} + static void gen_exception(int excp) { TCGv tmp = new_tmp(); @@ -580,6 +947,7 @@ static inline void gen_arm_shift_reg(TCG static void gen_arm_parallel_addsub(int op1, int op2, TCGv a, TCGv b) { TCGv_ptr tmp; + unsigned int instr_index = 0; switch (op1) { #define gen_pas_helper(name) glue(gen_helper_,name)(a, a, b, tmp) @@ -587,28 +955,37 @@ static void gen_arm_parallel_addsub(int tmp = tcg_temp_new_ptr(); tcg_gen_addi_ptr(tmp, cpu_env, offsetof(CPUState, GE)); PAS_OP(s) + instr_index = ARM_INSTRUCTION_SADD16; break; case 5: tmp = tcg_temp_new_ptr(); tcg_gen_addi_ptr(tmp, cpu_env, offsetof(CPUState, GE)); PAS_OP(u) + instr_index = ARM_INSTRUCTION_UADD16; break; #undef gen_pas_helper #define gen_pas_helper(name) glue(gen_helper_,name)(a, a, b) case 2: PAS_OP(q); + instr_index = ARM_INSTRUCTION_QADD16; break; case 3: PAS_OP(sh); + instr_index = ARM_INSTRUCTION_SHADD16; break; case 6: PAS_OP(uq); + instr_index = ARM_INSTRUCTION_UQADD16; break; case 7: PAS_OP(uh); + instr_index = ARM_INSTRUCTION_UHADD16; break; #undef gen_pas_helper } + if (op2 == 7) instr_index += 5; + else instr_index += op2; + instr_count_inc(instr_index); } #undef PAS_OP @@ -2702,6 +3079,9 @@ static int disas_vfp_insn(CPUState * env TCGv tmp; TCGv tmp2; + instr_count_inc_init(ARM_VFP_INSTRUCTION_COUNTER_OFFSET, + ARM_VFP_INSTRUCTION_NOT_INSTRUMENTED); + if (!arm_feature(env, ARM_FEATURE_VFP)) return 1; @@ -2724,6 +3104,8 @@ static int disas_vfp_insn(CPUState * env int size; int pass; + instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN); + VFP_DREG_N(rn, insn); if (insn & 0xf) return 1; @@ -2770,6 +3152,11 @@ static int disas_vfp_insn(CPUState * env } break; case 2: + if (pass) { + instr_count_inc(ARM_VFP_INSTRUCTION_FMRDH); + } else { + instr_count_inc(ARM_VFP_INSTRUCTION_FMRDL); + } break; } store_reg(s, rd, tmp); @@ -2801,6 +3188,11 @@ static int disas_vfp_insn(CPUState * env dead_tmp(tmp2); break; case 2: + if (pass) { + instr_count_inc(ARM_VFP_INSTRUCTION_FMDHR); + } else { + instr_count_inc(ARM_VFP_INSTRUCTION_FMDLR); + } break; } neon_store_reg(rn, pass, tmp); @@ -2814,6 +3206,7 @@ static int disas_vfp_insn(CPUState * env /* vfp->arm */ if (insn & (1 << 21)) { /* system register */ + instr_count_inc(ARM_VFP_INSTRUCTION_FMRX); rn >>= 1; switch (rn) { @@ -2841,6 +3234,7 @@ static int disas_vfp_insn(CPUState * env break; case ARM_VFP_FPSCR: if (rd == 15) { + instr_count_inc(ARM_VFP_INSTRUCTION_FMSTAT); tmp = load_cpu_field(vfp.xregs[ARM_VFP_FPSCR]); tcg_gen_andi_i32(tmp, tmp, 0xf0000000); } else { @@ -2859,6 +3253,7 @@ static int disas_vfp_insn(CPUState * env return 1; } } else { + instr_count_inc(ARM_VFP_INSTRUCTION_FMRS); gen_mov_F0_vreg(0, rn); tmp = gen_vfp_mrs(); } @@ -2873,6 +3268,7 @@ static int disas_vfp_insn(CPUState * env /* arm->vfp */ tmp = load_reg(s, rd); if (insn & (1 << 21)) { + instr_count_inc(ARM_VFP_INSTRUCTION_FMXR); rn >>= 1; /* system register */ switch (rn) { @@ -2900,6 +3296,7 @@ static int disas_vfp_insn(CPUState * env return 1; } } else { + instr_count_inc(ARM_VFP_INSTRUCTION_FMSR); gen_vfp_msr(tmp); gen_mov_vreg_F0(0, rn); } @@ -3023,44 +3420,54 @@ static int disas_vfp_insn(CPUState * env /* Perform the calculation. */ switch (op) { case 0: /* mac: fd + (fn * fm) */ + instr_count_inc(ARM_VFP_INSTRUCTION_FMACD + (1 - dp)); gen_vfp_mul(dp); gen_mov_F1_vreg(dp, rd); gen_vfp_add(dp); break; case 1: /* nmac: fd - (fn * fm) */ + instr_count_inc(ARM_VFP_INSTRUCTION_FNMACD + (1 - dp)); gen_vfp_mul(dp); gen_vfp_neg(dp); gen_mov_F1_vreg(dp, rd); gen_vfp_add(dp); break; case 2: /* msc: -fd + (fn * fm) */ + instr_count_inc(ARM_VFP_INSTRUCTION_FMSCD + (1 - dp)); gen_vfp_mul(dp); gen_mov_F1_vreg(dp, rd); gen_vfp_sub(dp); break; case 3: /* nmsc: -fd - (fn * fm) */ + instr_count_inc(ARM_VFP_INSTRUCTION_FNMSCD + (1 - dp)); gen_vfp_mul(dp); gen_vfp_neg(dp); gen_mov_F1_vreg(dp, rd); gen_vfp_sub(dp); break; case 4: /* mul: fn * fm */ + instr_count_inc(ARM_VFP_INSTRUCTION_FMULD + (1 - dp)); gen_vfp_mul(dp); break; case 5: /* nmul: -(fn * fm) */ + instr_count_inc(ARM_VFP_INSTRUCTION_FNMULD + (1 - dp)); gen_vfp_mul(dp); gen_vfp_neg(dp); break; case 6: /* add: fn + fm */ + instr_count_inc(ARM_VFP_INSTRUCTION_FADDD + (1 - dp)); gen_vfp_add(dp); break; case 7: /* sub: fn - fm */ + instr_count_inc(ARM_VFP_INSTRUCTION_FSUBD + (1 - dp)); gen_vfp_sub(dp); break; case 8: /* div: fn / fm */ + instr_count_inc(ARM_VFP_INSTRUCTION_FDIVD + (1 - dp)); gen_vfp_div(dp); break; case 14: /* fconst */ + instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_VFP3)) return 1; @@ -3085,90 +3492,116 @@ static int disas_vfp_insn(CPUState * env case 15: /* extension space */ switch (rn) { case 0: /* cpy */ + instr_count_inc(ARM_VFP_INSTRUCTION_FCPYD + (1 - dp)); /* no-op */ break; case 1: /* abs */ + instr_count_inc(ARM_VFP_INSTRUCTION_FABSD + (1 - dp)); gen_vfp_abs(dp); break; case 2: /* neg */ + instr_count_inc(ARM_VFP_INSTRUCTION_FNEGD + (1 - dp)); gen_vfp_neg(dp); break; case 3: /* sqrt */ + instr_count_inc(ARM_VFP_INSTRUCTION_FSQRTD + (1 - dp)); gen_vfp_sqrt(dp); break; case 8: /* cmp */ + instr_count_inc(ARM_VFP_INSTRUCTION_FCMPD + (1 - dp)); gen_vfp_cmp(dp); break; case 9: /* cmpe */ + instr_count_inc(ARM_VFP_INSTRUCTION_FCMPED + (1 - dp)); gen_vfp_cmpe(dp); break; case 10: /* cmpz */ + instr_count_inc(ARM_VFP_INSTRUCTION_FCMPZD + (1 - dp)); gen_vfp_cmp(dp); break; case 11: /* cmpez */ + instr_count_inc(ARM_VFP_INSTRUCTION_FCMPEZD + (1 - dp)); gen_vfp_F1_ld0(dp); gen_vfp_cmpe(dp); break; case 15: /* single<->double conversion */ - if (dp) + if (dp) { + instr_count_inc(ARM_VFP_INSTRUCTION_FCVTSD); gen_helper_vfp_fcvtsd(cpu_F0s, cpu_F0d, cpu_env); - else + } + else { + instr_count_inc(ARM_VFP_INSTRUCTION_FCVTDS); gen_helper_vfp_fcvtds(cpu_F0d, cpu_F0s, cpu_env); + } break; case 16: /* fuito */ + instr_count_inc(ARM_VFP_INSTRUCTION_FUITOD + (1 - dp)); gen_vfp_uito(dp); break; case 17: /* fsito */ + instr_count_inc(ARM_VFP_INSTRUCTION_FSITOD + (1 - dp)); gen_vfp_sito(dp); break; case 20: /* fshto */ + instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_VFP3)) return 1; gen_vfp_shto(dp, 16 - rm); break; case 21: /* fslto */ + instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_VFP3)) return 1; gen_vfp_slto(dp, 32 - rm); break; case 22: /* fuhto */ + instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_VFP3)) return 1; gen_vfp_uhto(dp, 16 - rm); break; case 23: /* fulto */ + instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_VFP3)) return 1; gen_vfp_ulto(dp, 32 - rm); break; case 24: /* ftoui */ + instr_count_inc(ARM_VFP_INSTRUCTION_FTOUID + (1 - dp)); gen_vfp_toui(dp); break; case 25: /* ftouiz */ + instr_count_inc(ARM_VFP_INSTRUCTION_FTOUIZD + (1 - dp)); gen_vfp_touiz(dp); break; case 26: /* ftosi */ + instr_count_inc(ARM_VFP_INSTRUCTION_FTOSID + (1 - dp)); gen_vfp_tosi(dp); break; case 27: /* ftosiz */ + instr_count_inc(ARM_VFP_INSTRUCTION_FTOSIZD + (1 - dp)); gen_vfp_tosiz(dp); break; case 28: /* ftosh */ + instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_VFP3)) return 1; gen_vfp_tosh(dp, 16 - rm); break; case 29: /* ftosl */ + instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_VFP3)) return 1; gen_vfp_tosl(dp, 32 - rm); break; case 30: /* ftouh */ + instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_VFP3)) return 1; gen_vfp_touh(dp, 16 - rm); break; case 31: /* ftoul */ + instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_VFP3)) return 1; gen_vfp_toul(dp, 32 - rm); @@ -3247,6 +3680,7 @@ static int disas_vfp_insn(CPUState * env if (insn & ARM_CP_RW_BIT) { /* vfp->arm */ if (dp) { + instr_count_inc(ARM_VFP_INSTRUCTION_FMRRD); gen_mov_F0_vreg(0, rm * 2); tmp = gen_vfp_mrs(); store_reg(s, rd, tmp); @@ -3254,6 +3688,7 @@ static int disas_vfp_insn(CPUState * env tmp = gen_vfp_mrs(); store_reg(s, rn, tmp); } else { + instr_count_inc(ARM_VFP_INSTRUCTION_FMRRS); gen_mov_F0_vreg(0, rm); tmp = gen_vfp_mrs(); store_reg(s, rn, tmp); @@ -3264,6 +3699,7 @@ static int disas_vfp_insn(CPUState * env } else { /* arm->vfp */ if (dp) { + instr_count_inc(ARM_VFP_INSTRUCTION_FMDRR); tmp = load_reg(s, rd); gen_vfp_msr(tmp); gen_mov_vreg_F0(0, rm * 2); @@ -3271,6 +3707,7 @@ static int disas_vfp_insn(CPUState * env gen_vfp_msr(tmp); gen_mov_vreg_F0(0, rm * 2 + 1); } else { + instr_count_inc(ARM_VFP_INSTRUCTION_FMSRR); tmp = load_reg(s, rn); gen_vfp_msr(tmp); gen_mov_vreg_F0(0, rm); @@ -3298,9 +3735,11 @@ static int disas_vfp_insn(CPUState * env offset = -offset; gen_op_addl_T1_im(offset); if (insn & (1 << 20)) { + instr_count_inc(ARM_VFP_INSTRUCTION_FLDD + (1 - dp)); gen_vfp_ld(s, dp); gen_mov_vreg_F0(dp, rd); } else { + instr_count_inc(ARM_VFP_INSTRUCTION_FSTD + (1 - dp)); gen_mov_F0_vreg(dp, rd); gen_vfp_st(s, dp); } @@ -3321,10 +3760,12 @@ static int disas_vfp_insn(CPUState * env for (i = 0; i < n; i++) { if (insn & ARM_CP_RW_BIT) { /* load */ + instr_count_inc(ARM_VFP_INSTRUCTION_FLDMD + (1 - dp)); gen_vfp_ld(s, dp); gen_mov_vreg_F0(dp, rd + i); } else { /* store */ + instr_count_inc(ARM_VFP_INSTRUCTION_FSTMD + (1 - dp)); gen_mov_F0_vreg(dp, rd + i); gen_vfp_st(s, dp); } @@ -5697,6 +6138,7 @@ static void gen_logicq_cc(TCGv_i64 val) static void disas_arm_insn(CPUState * env, DisasContext *s) { unsigned int cond, insn, val, op1, i, shift, rm, rs, rn, rd, sh; + unsigned int instr_index = 0; TCGv tmp; TCGv tmp2; TCGv tmp3; @@ -5706,14 +6148,18 @@ static void disas_arm_insn(CPUState * en insn = ldl_code(s->pc); s->pc += 4; + instr_count_inc_init(ARM_INSTRUCTION_COUNTER_OFFSET, + ARM_INSTRUCTION_NOT_INSTRUMENTED); + /* M variants do not implement ARM mode. */ if (IS_M(env)) goto illegal_op; cond = insn >> 28; - if (cond == 0xf){ + if (cond == 0xf) { /* Unconditional instructions. */ if (((insn >> 25) & 7) == 1) { /* NEON Data processing. */ + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_NEON)) goto illegal_op; @@ -5723,6 +6169,7 @@ static void disas_arm_insn(CPUState * en } if ((insn & 0x0f100000) == 0x04000000) { /* NEON load/store. */ + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_NEON)) goto illegal_op; @@ -5734,6 +6181,7 @@ static void disas_arm_insn(CPUState * en return; /* PLD */ else if ((insn & 0x0ffffdff) == 0x01010000) { ARCH(6); + instr_count_inc(ARM_INSTRUCTION_SETEND); /* setend */ if (insn & (1 << 9)) { /* BE8 mode not implemented. */ @@ -5744,11 +6192,13 @@ static void disas_arm_insn(CPUState * en switch ((insn >> 4) & 0xf) { case 1: /* clrex */ ARCH(6K); + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); gen_helper_clrex(cpu_env); return; case 4: /* dsb */ case 5: /* dmb */ case 6: /* isb */ + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); ARCH(7); /* We don't emulate caches so these are a no-op. */ return; @@ -5758,6 +6208,7 @@ static void disas_arm_insn(CPUState * en } else if ((insn & 0x0e5fffe0) == 0x084d0500) { /* srs */ uint32_t offset; + instr_count_inc(ARM_INSTRUCTION_SRS); if (IS_USER(s)) goto illegal_op; ARCH(6); @@ -5808,6 +6259,7 @@ static void disas_arm_insn(CPUState * en uint32_t offset; if (IS_USER(s)) goto illegal_op; + instr_count_inc(ARM_INSTRUCTION_RFE); ARCH(6); rn = (insn >> 16) & 0xf; addr = load_reg(s, rn); @@ -5844,7 +6296,7 @@ static void disas_arm_insn(CPUState * en } else if ((insn & 0x0e000000) == 0x0a000000) { /* branch link and change to thumb (blx <offset>) */ int32_t offset; - + instr_count_inc(ARM_INSTRUCTION_BLX); val = (uint32_t)s->pc; tmp = new_tmp(); tcg_gen_movi_i32(tmp, val); @@ -5858,6 +6310,7 @@ static void disas_arm_insn(CPUState * en gen_bx_im(s, val); return; } else if ((insn & 0x0e000f00) == 0x0c000100) { + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); if (arm_feature(env, ARM_FEATURE_IWMMXT)) { /* iWMMXt register transfer. */ if (env->cp15.c15_cpar & (1 << 1)) @@ -5865,13 +6318,16 @@ static void disas_arm_insn(CPUState * en return; } } else if ((insn & 0x0fe00000) == 0x0c400000) { + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); /* Coprocessor double register transfer. */ } else if ((insn & 0x0f000010) == 0x0e000010) { + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); /* Additional coprocessor register transfer. */ } else if ((insn & 0x0ff10020) == 0x01000000) { uint32_t mask; uint32_t val; /* cps (privileged) */ + instr_count_inc(ARM_INSTRUCTION_CPS); if (IS_USER(s)) return; mask = val = 0; @@ -5911,10 +6367,12 @@ static void disas_arm_insn(CPUState * en val = ((insn >> 4) & 0xf000) | (insn & 0xfff); if ((insn & (1 << 22)) == 0) { /* MOVW */ + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); tmp = new_tmp(); tcg_gen_movi_i32(tmp, val); } else { /* MOVT */ + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); tmp = load_reg(s, rd); tcg_gen_ext16u_i32(tmp, tmp); tcg_gen_ori_i32(tmp, tmp, val << 16); @@ -5924,9 +6382,11 @@ static void disas_arm_insn(CPUState * en if (((insn >> 12) & 0xf) != 0xf) goto illegal_op; if (((insn >> 16) & 0xf) == 0) { + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); gen_nop_hint(s, insn & 0xff); } else { /* CPSR = immediate */ + instr_count_inc(ARM_INSTRUCTION_MSR); val = insn & 0xff; shift = ((insn >> 8) & 0xf) * 2; if (shift) @@ -5947,12 +6407,14 @@ static void disas_arm_insn(CPUState * en case 0x0: /* move program status register */ if (op1 & 1) { /* PSR = reg */ + instr_count_inc(ARM_INSTRUCTION_MSR); gen_movl_T0_reg(s, rm); i = ((op1 & 2) != 0); if (gen_set_psr_T0(s, msr_mask(env, s, (insn >> 16) & 0xf, i), i)) goto illegal_op; } else { /* reg = PSR */ + instr_count_inc(ARM_INSTRUCTION_MRS); rd = (insn >> 12) & 0xf; if (op1 & 2) { if (IS_USER(s)) @@ -5968,10 +6430,12 @@ static void disas_arm_insn(CPUState * en case 0x1: if (op1 == 1) { /* branch/exchange thumb (bx). */ + instr_count_inc(ARM_INSTRUCTION_BX); tmp = load_reg(s, rm); gen_bx(s, tmp); } else if (op1 == 3) { /* clz */ + instr_count_inc(ARM_INSTRUCTION_CLZ); rd = (insn >> 12) & 0xf; tmp = load_reg(s, rm); gen_helper_clz(tmp, tmp); @@ -5982,6 +6446,7 @@ static void disas_arm_insn(CPUState * en break; case 0x2: if (op1 == 1) { + instr_count_inc(ARM_INSTRUCTION_BXJ); ARCH(5J); /* bxj */ /* Trivial implementation equivalent to bx. */ tmp = load_reg(s, rm); @@ -5994,6 +6459,7 @@ static void disas_arm_insn(CPUState * en if (op1 != 1) goto illegal_op; + instr_count_inc(ARM_INSTRUCTION_BLX); /* branch link/exchange thumb (blx) */ tmp = load_reg(s, rm); tmp2 = new_tmp(); @@ -6006,16 +6472,32 @@ static void disas_arm_insn(CPUState * en rn = (insn >> 16) & 0xf; tmp = load_reg(s, rm); tmp2 = load_reg(s, rn); - if (op1 & 2) + if (op1 & 2) { gen_helper_double_saturate(tmp2, tmp2); - if (op1 & 1) + } + if (op1 & 1) { gen_helper_sub_saturate(tmp, tmp, tmp2); - else + if (op1 & 2) { + instr_count_inc(ARM_INSTRUCTION_QDSUB); + } + else { + instr_count_inc(ARM_INSTRUCTION_QSUB); + } + } + else { gen_helper_add_saturate(tmp, tmp, tmp2); + if (op1 & 2) { + instr_count_inc(ARM_INSTRUCTION_QDADD); + } + else { + instr_count_inc(ARM_INSTRUCTION_QADD); + } + } dead_tmp(tmp2); store_reg(s, rd, tmp); break; case 7: /* bkpt */ + instr_count_inc(ARM_INSTRUCTION_BKPT); gen_set_condexec(s); gen_set_pc_im(s->pc - 4); gen_exception(EXCP_BKPT); @@ -6041,18 +6523,22 @@ static void disas_arm_insn(CPUState * en tmp = new_tmp(); tcg_gen_trunc_i64_i32(tmp, tmp64); if ((sh & 2) == 0) { + instr_count_inc(ARM_INSTRUCTION_SMLAWY); tmp2 = load_reg(s, rn); gen_helper_add_setq(tmp, tmp, tmp2); dead_tmp(tmp2); } + else instr_count_inc(ARM_INSTRUCTION_SMULWY); store_reg(s, rd, tmp); } else { /* 16 * 16 */ + if (op1 == 3) instr_count_inc(ARM_INSTRUCTION_SMULXY); tmp = load_reg(s, rm); tmp2 = load_reg(s, rs); gen_mulxy(tmp, tmp2, sh & 2, sh & 4); dead_tmp(tmp2); if (op1 == 2) { + instr_count_inc(ARM_INSTRUCTION_SMLALXY); tmp64 = tcg_temp_new_i64(); tcg_gen_ext_i32_i64(tmp64, tmp); dead_tmp(tmp); @@ -6060,6 +6546,7 @@ static void disas_arm_insn(CPUState * en gen_storeq_reg(s, rn, rd, tmp64); } else { if (op1 == 0) { + instr_count_inc(ARM_INSTRUCTION_SMLAXY); tmp2 = load_reg(s, rn); gen_helper_add_setq(tmp, tmp, tmp2); dead_tmp(tmp2); @@ -6111,18 +6598,21 @@ static void disas_arm_insn(CPUState * en rd = (insn >> 12) & 0xf; switch(op1) { case 0x00: + instr_count_inc(ARM_INSTRUCTION_AND); gen_op_andl_T0_T1(); gen_movl_reg_T0(s, rd); if (logic_cc) gen_op_logic_T0_cc(); break; case 0x01: + instr_count_inc(ARM_INSTRUCTION_EOR); gen_op_xorl_T0_T1(); gen_movl_reg_T0(s, rd); if (logic_cc) gen_op_logic_T0_cc(); break; case 0x02: + instr_count_inc(ARM_INSTRUCTION_SUB); if (set_cc && rd == 15) { /* SUBS r15, ... is used for exception return. */ if (IS_USER(s)) @@ -6138,6 +6628,7 @@ static void disas_arm_insn(CPUState * en } break; case 0x03: + instr_count_inc(ARM_INSTRUCTION_RSB); if (set_cc) gen_op_rsbl_T0_T1_cc(); else @@ -6145,6 +6636,7 @@ static void disas_arm_insn(CPUState * en gen_movl_reg_T0(s, rd); break; case 0x04: + instr_count_inc(ARM_INSTRUCTION_ADD); if (set_cc) gen_op_addl_T0_T1_cc(); else @@ -6152,6 +6644,7 @@ static void disas_arm_insn(CPUState * en gen_movl_reg_T0(s, rd); break; case 0x05: + instr_count_inc(ARM_INSTRUCTION_ADC); if (set_cc) gen_op_adcl_T0_T1_cc(); else @@ -6159,6 +6652,7 @@ static void disas_arm_insn(CPUState * en gen_movl_reg_T0(s, rd); break; case 0x06: + instr_count_inc(ARM_INSTRUCTION_SBC); if (set_cc) gen_op_sbcl_T0_T1_cc(); else @@ -6166,6 +6660,7 @@ static void disas_arm_insn(CPUState * en gen_movl_reg_T0(s, rd); break; case 0x07: + instr_count_inc(ARM_INSTRUCTION_RSC); if (set_cc) gen_op_rscl_T0_T1_cc(); else @@ -6173,34 +6668,40 @@ static void disas_arm_insn(CPUState * en gen_movl_reg_T0(s, rd); break; case 0x08: + instr_count_inc(ARM_INSTRUCTION_TST); if (set_cc) { gen_op_andl_T0_T1(); gen_op_logic_T0_cc(); } break; case 0x09: + instr_count_inc(ARM_INSTRUCTION_TEQ); if (set_cc) { gen_op_xorl_T0_T1(); gen_op_logic_T0_cc(); } break; case 0x0a: + instr_count_inc(ARM_INSTRUCTION_CMP); if (set_cc) { gen_op_subl_T0_T1_cc(); } break; case 0x0b: + instr_count_inc(ARM_INSTRUCTION_CMN); if (set_cc) { gen_op_addl_T0_T1_cc(); } break; case 0x0c: + instr_count_inc(ARM_INSTRUCTION_ORR); gen_op_orl_T0_T1(); gen_movl_reg_T0(s, rd); if (logic_cc) gen_op_logic_T0_cc(); break; case 0x0d: + instr_count_inc(ARM_INSTRUCTION_MOV); if (logic_cc && rd == 15) { /* MOVS r15, ... is used for exception return. */ if (IS_USER(s)) @@ -6214,6 +6715,7 @@ static void disas_arm_insn(CPUState * en } break; case 0x0e: + instr_count_inc(ARM_INSTRUCTION_BIC); gen_op_bicl_T0_T1(); gen_movl_reg_T0(s, rd); if (logic_cc) @@ -6221,6 +6723,7 @@ static void disas_arm_insn(CPUState * en break; default: case 0x0f: + instr_count_inc(ARM_INSTRUCTION_MVN); gen_op_notl_T1(); gen_movl_reg_T1(s, rd); if (logic_cc) @@ -6245,43 +6748,63 @@ static void disas_arm_insn(CPUState * en switch (op1) { case 0: case 1: case 2: case 3: case 6: /* 32 bit mul */ + instr_index = ARM_INSTRUCTION_MUL; tmp = load_reg(s, rs); tmp2 = load_reg(s, rm); tcg_gen_mul_i32(tmp, tmp, tmp2); dead_tmp(tmp2); if (insn & (1 << 22)) { /* Subtract (mls) */ + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); ARCH(6T2); tmp2 = load_reg(s, rn); tcg_gen_sub_i32(tmp, tmp2, tmp); dead_tmp(tmp2); } else if (insn & (1 << 21)) { /* Add */ + instr_index = ARM_INSTRUCTION_MLA; tmp2 = load_reg(s, rn); tcg_gen_add_i32(tmp, tmp, tmp2); dead_tmp(tmp2); } - if (insn & (1 << 20)) + if (insn & (1 << 20)) { gen_logic_CC(tmp); + instr_index++; /* MULS and MLAS */ + } + instr_count_inc(instr_index); store_reg(s, rd, tmp); break; default: /* 64 bit mul */ tmp = load_reg(s, rs); tmp2 = load_reg(s, rm); - if (insn & (1 << 22)) + if (insn & (1 << 22)) { tmp64 = gen_muls_i64_i32(tmp, tmp2); - else + instr_index = ARM_INSTRUCTION_SMULL; + } + else { tmp64 = gen_mulu_i64_i32(tmp, tmp2); - if (insn & (1 << 21)) /* mult accumulate */ + instr_index = ARM_INSTRUCTION_UMULL; + } + if (insn & (1 << 21)) { + /* mult accumulate */ gen_addq(s, tmp64, rn, rd); + if (insn & (1 << 22)) { + instr_index = ARM_INSTRUCTION_SMLAL; + } else { + instr_index = ARM_INSTRUCTION_UMLAL; + } + } if (!(insn & (1 << 23))) { /* double accumulate */ ARCH(6); gen_addq_lo(s, tmp64, rn); gen_addq_lo(s, tmp64, rd); } - if (insn & (1 << 20)) + if (insn & (1 << 20)) { gen_logicq_cc(tmp64); + instr_index++; /* SMULLS, UMULLS, SMLALS, UMLALS */ + } + instr_count_inc(instr_index); gen_storeq_reg(s, rn, rd, tmp64); break; } @@ -6301,9 +6824,11 @@ static void disas_arm_insn(CPUState * en gen_helper_mark_exclusive(cpu_env, cpu_T[1]); switch (op1) { case 0: /* ldrex */ + instr_count_inc(ARM_INSTRUCTION_LDREX); tmp = gen_ld32(addr, IS_USER(s)); break; case 1: /* ldrexd */ + instr_count_inc(ARM_INSTRUCTION_LDREXD); tmp = gen_ld32(addr, IS_USER(s)); store_reg(s, rd, tmp); tcg_gen_addi_i32(addr, addr, 4); @@ -6311,9 +6836,11 @@ static void disas_arm_insn(CPUState * en rd++; break; case 2: /* ldrexb */ + instr_count_inc(ARM_INSTRUCTION_LDREXB); tmp = gen_ld8u(addr, IS_USER(s)); break; case 3: /* ldrexh */ + instr_count_inc(ARM_INSTRUCTION_LDREXH); tmp = gen_ld16u(addr, IS_USER(s)); break; default: @@ -6329,18 +6856,22 @@ static void disas_arm_insn(CPUState * en tmp = load_reg(s,rm); switch (op1) { case 0: /* strex */ + instr_count_inc(ARM_INSTRUCTION_STREX); gen_st32(tmp, addr, IS_USER(s)); break; case 1: /* strexd */ + instr_count_inc(ARM_INSTRUCTION_STREXD); gen_st32(tmp, addr, IS_USER(s)); tcg_gen_addi_i32(addr, addr, 4); tmp = load_reg(s, rm + 1); gen_st32(tmp, addr, IS_USER(s)); break; case 2: /* strexb */ + instr_count_inc(ARM_INSTRUCTION_STREXB); gen_st8(tmp, addr, IS_USER(s)); break; case 3: /* strexh */ + instr_count_inc(ARM_INSTRUCTION_STREXH); gen_st16(tmp, addr, IS_USER(s)); break; default: @@ -6359,9 +6890,11 @@ static void disas_arm_insn(CPUState * en addr = load_reg(s, rn); tmp = load_reg(s, rm); if (insn & (1 << 22)) { + instr_count_inc(ARM_INSTRUCTION_SWPB); tmp2 = gen_ld8u(addr, IS_USER(s)); gen_st8(tmp, addr, IS_USER(s)); } else { + instr_count_inc(ARM_INSTRUCTION_SWP); tmp2 = gen_ld32(addr, IS_USER(s)); gen_st32(tmp, addr, IS_USER(s)); } @@ -6383,13 +6916,16 @@ static void disas_arm_insn(CPUState * en /* load */ switch(sh) { case 1: + instr_count_inc(ARM_INSTRUCTION_LDRH); tmp = gen_ld16u(addr, IS_USER(s)); break; case 2: + instr_count_inc(ARM_INSTRUCTION_LDRSB); tmp = gen_ld8s(addr, IS_USER(s)); break; default: case 3: + instr_count_inc(ARM_INSTRUCTION_LDRSH); tmp = gen_ld16s(addr, IS_USER(s)); break; } @@ -6398,6 +6934,7 @@ static void disas_arm_insn(CPUState * en /* doubleword */ if (sh & 1) { /* store */ + instr_count_inc(ARM_INSTRUCTION_STRD); tmp = load_reg(s, rd); gen_st32(tmp, addr, IS_USER(s)); tcg_gen_addi_i32(addr, addr, 4); @@ -6406,6 +6943,7 @@ static void disas_arm_insn(CPUState * en load = 0; } else { /* load */ + instr_count_inc(ARM_INSTRUCTION_LDRD); tmp = gen_ld32(addr, IS_USER(s)); store_reg(s, rd, tmp); tcg_gen_addi_i32(addr, addr, 4); @@ -6417,6 +6955,7 @@ static void disas_arm_insn(CPUState * en } else { /* store */ tmp = load_reg(s, rd); + instr_count_inc(ARM_INSTRUCTION_STRH); gen_st16(tmp, addr, IS_USER(s)); load = 0; } @@ -6454,6 +6993,7 @@ static void disas_arm_insn(CPUState * en rs = (insn >> 8) & 0xf; switch ((insn >> 23) & 3) { case 0: /* Parallel add/subtract. */ + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); op1 = (insn >> 20) & 7; tmp = load_reg(s, rn); tmp2 = load_reg(s, rm); @@ -6472,6 +7012,7 @@ static void disas_arm_insn(CPUState * en shift = (insn >> 7) & 0x1f; if (insn & (1 << 6)) { /* pkhtb */ + instr_count_inc(ARM_INSTRUCTION_PKHTB); if (shift == 0) shift = 31; tcg_gen_sari_i32(tmp2, tmp2, shift); @@ -6479,6 +7020,7 @@ static void disas_arm_insn(CPUState * en tcg_gen_ext16u_i32(tmp2, tmp2); } else { /* pkhbt */ + instr_count_inc(ARM_INSTRUCTION_PKHBT); if (shift) tcg_gen_shli_i32(tmp2, tmp2, shift); tcg_gen_ext16u_i32(tmp, tmp); @@ -6500,10 +7042,14 @@ static void disas_arm_insn(CPUState * en } sh = (insn >> 16) & 0x1f; if (sh != 0) { - if (insn & (1 << 22)) + if (insn & (1 << 22)) { + instr_count_inc(ARM_INSTRUCTION_USAT); gen_helper_usat(tmp, tmp, tcg_const_i32(sh)); - else + } + else { + instr_count_inc(ARM_INSTRUCTION_SSAT); gen_helper_ssat(tmp, tmp, tcg_const_i32(sh)); + } } store_reg(s, rd, tmp); } else if ((insn & 0x00300fe0) == 0x00200f20) { @@ -6511,14 +7057,19 @@ static void disas_arm_insn(CPUState * en tmp = load_reg(s, rm); sh = (insn >> 16) & 0x1f; if (sh != 0) { - if (insn & (1 << 22)) + if (insn & (1 << 22)) { + instr_count_inc(ARM_INSTRUCTION_USAT16); gen_helper_usat16(tmp, tmp, tcg_const_i32(sh)); - else + } + else { + instr_count_inc(ARM_INSTRUCTION_SSAT16); gen_helper_ssat16(tmp, tmp, tcg_const_i32(sh)); + } } store_reg(s, rd, tmp); } else if ((insn & 0x00700fe0) == 0x00000fa0) { /* Select bytes. */ + instr_count_inc(ARM_INSTRUCTION_SEL); tmp = load_reg(s, rn); tmp2 = load_reg(s, rm); tmp3 = new_tmp(); @@ -6536,12 +7087,30 @@ static void disas_arm_insn(CPUState * en tcg_gen_rori_i32(tmp, tmp, shift * 8); op1 = (insn >> 20) & 7; switch (op1) { - case 0: gen_sxtb16(tmp); break; - case 2: gen_sxtb(tmp); break; - case 3: gen_sxth(tmp); break; - case 4: gen_uxtb16(tmp); break; - case 6: gen_uxtb(tmp); break; - case 7: gen_uxth(tmp); break; + case 0: + instr_index = ARM_INSTRUCTION_SXTB16; + gen_sxtb16(tmp); + break; + case 2: + instr_index = ARM_INSTRUCTION_SXTB; + gen_sxtb(tmp); + break; + case 3: + instr_index = ARM_INSTRUCTION_SXTH; + gen_sxth(tmp); + break; + case 4: + instr_index = ARM_INSTRUCTION_UXTB16; + gen_uxtb16(tmp); + break; + case 6: + instr_index = ARM_INSTRUCTION_UXTB; + gen_uxtb(tmp); + break; + case 7: + instr_index = ARM_INSTRUCTION_UXTH; + gen_uxth(tmp); + break; default: goto illegal_op; } if (rn != 15) { @@ -6552,23 +7121,30 @@ static void disas_arm_insn(CPUState * en tcg_gen_add_i32(tmp, tmp, tmp2); dead_tmp(tmp2); } + instr_index -= 3; /* add variants */ } + instr_count_inc(instr_index); store_reg(s, rd, tmp); } else if ((insn & 0x003f0f60) == 0x003f0f20) { /* rev */ tmp = load_reg(s, rm); if (insn & (1 << 22)) { if (insn & (1 << 7)) { + instr_count_inc(ARM_INSTRUCTION_REVSH); gen_revsh(tmp); } else { ARCH(6T2); gen_helper_rbit(tmp, tmp); } } else { - if (insn & (1 << 7)) + if (insn & (1 << 7)) { + instr_count_inc(ARM_INSTRUCTION_REV16); gen_rev16(tmp); - else + } + else { + instr_count_inc(ARM_INSTRUCTION_REV); tcg_gen_bswap_i32(tmp, tmp); + } } store_reg(s, rd, tmp); } else { @@ -6590,11 +7166,16 @@ static void disas_arm_insn(CPUState * en tmp2 = load_reg(s, rd); if (insn & (1 << 6)) { tcg_gen_sub_i32(tmp, tmp, tmp2); + instr_count_inc(ARM_INSTRUCTION_SMMLS); } else { tcg_gen_add_i32(tmp, tmp, tmp2); + instr_count_inc(ARM_INSTRUCTION_SMMLA); } dead_tmp(tmp2); } + else { + instr_count_inc(ARM_INSTRUCTION_SMMUL); + } store_reg(s, rn, tmp); } else { if (insn & (1 << 5)) @@ -6603,8 +7184,10 @@ static void disas_arm_insn(CPUState * en /* This addition cannot overflow. */ if (insn & (1 << 6)) { tcg_gen_sub_i32(tmp, tmp, tmp2); + instr_index = 1; } else { tcg_gen_add_i32(tmp, tmp, tmp2); + instr_index = 0; } dead_tmp(tmp2); if (insn & (1 << 22)) { @@ -6614,6 +7197,8 @@ static void disas_arm_insn(CPUState * en dead_tmp(tmp); gen_addq(s, tmp64, rd, rn); gen_storeq_reg(s, rd, rn, tmp64); + instr_index += ARM_INSTRUCTION_SMLALD; + instr_count_inc(instr_index); } else { /* smuad, smusd, smlad, smlsd */ if (rd != 15) @@ -6621,8 +7206,11 @@ static void disas_arm_insn(CPUState * en tmp2 = load_reg(s, rd); gen_helper_add_setq(tmp, tmp, tmp2); dead_tmp(tmp2); + instr_index += 2; /* SMLAD, SMLSD */ } store_reg(s, rn, tmp); + instr_index += ARM_INSTRUCTION_SMUAD; + instr_count_inc(instr_index); } } break; @@ -6639,12 +7227,15 @@ static void disas_arm_insn(CPUState * en tmp2 = load_reg(s, rd); tcg_gen_add_i32(tmp, tmp, tmp2); dead_tmp(tmp2); + instr_count_inc(ARM_INSTRUCTION_USADA8); } + else instr_count_inc(ARM_INSTRUCTION_USAD8); store_reg(s, rn, tmp); break; case 0x20: case 0x24: case 0x28: case 0x2c: /* Bitfield insert/clear. */ ARCH(6T2); + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); shift = (insn >> 7) & 0x1f; i = (insn >> 16) & 0x1f; i = i + 1 - shift; @@ -6664,6 +7255,7 @@ static void disas_arm_insn(CPUState * en case 0x12: case 0x16: case 0x1a: case 0x1e: /* sbfx */ case 0x32: case 0x36: case 0x3a: case 0x3e: /* ubfx */ ARCH(6T2); + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); tmp = load_reg(s, rm); shift = (insn >> 7) & 0x1f; i = ((insn >> 16) & 0x1f) + 1; @@ -6705,17 +7297,23 @@ static void disas_arm_insn(CPUState * en if (insn & (1 << 20)) { /* load */ if (insn & (1 << 22)) { + instr_count_inc(ARM_INSTRUCTION_LDRB); tmp = gen_ld8u(tmp2, i); } else { + instr_count_inc(ARM_INSTRUCTION_LDR); tmp = gen_ld32(tmp2, i); } } else { /* store */ tmp = load_reg(s, rd); - if (insn & (1 << 22)) + if (insn & (1 << 22)) { + instr_count_inc(ARM_INSTRUCTION_STRB); gen_st8(tmp, tmp2, i); - else + } + else { + instr_count_inc(ARM_INSTRUCTION_STR); gen_st32(tmp, tmp2, i); + } } if (!(insn & (1 << 24))) { gen_add_data_offset(s, insn, tmp2); @@ -6740,6 +7338,18 @@ static void disas_arm_insn(CPUState * en TCGv loaded_var; /* load/store multiple words */ /* XXX: store correct base if write back */ + switch (insn & 0x00500000 >> 20) { + case 0x0: instr_count_inc(ARM_INSTRUCTION_STM1); break; + case 0x1: instr_count_inc(ARM_INSTRUCTION_LDM1); break; + case 0x4: instr_count_inc(ARM_INSTRUCTION_STM2); break; + case 0x5: + if (insn & (1 << 15)) { + instr_count_inc(ARM_INSTRUCTION_LDM3); + } else { + instr_count_inc(ARM_INSTRUCTION_LDM2); + } + break; + } user = 0; if (insn & (1 << 22)) { if (IS_USER(s)) @@ -6854,14 +7464,15 @@ static void disas_arm_insn(CPUState * en case 0xb: { int32_t offset; - /* branch (and link) */ val = (int32_t)s->pc; if (insn & (1 << 24)) { + instr_count_inc(ARM_INSTRUCTION_B); tmp = new_tmp(); tcg_gen_movi_i32(tmp, val); store_reg(s, 14, tmp); } + else instr_count_inc(ARM_INSTRUCTION_B); offset = (((int32_t)insn << 8) >> 8); val += (offset << 2) + 4; gen_jmp(s, val); @@ -6871,11 +7482,13 @@ static void disas_arm_insn(CPUState * en case 0xd: case 0xe: /* Coprocessor. */ + instr_count_inc(ARM_INSTRUCTION_COPROCESSOR); if (disas_coproc_insn(env, s, insn)) goto illegal_op; break; case 0xf: /* swi */ + instr_count_inc(ARM_INSTRUCTION_SWI); gen_set_pc_im(s->pc); s->is_jmp = DISAS_SWI; break; @@ -6988,6 +7601,9 @@ static int disas_thumb2_insn(CPUState *e int conds; int logic_cc; + instr_count_inc_init(ARM_THUMB_INSTRUCTION_COUNTER_OFFSET, + ARM_THUMB_INSTRUCTION_NOT_INSTRUMENTED); + if (!(arm_feature(env, ARM_FEATURE_THUMB2) || arm_feature (env, ARM_FEATURE_M))) { /* Thumb-1 cores may need to treat bl and blx as a pair of @@ -7601,10 +8217,12 @@ static int disas_thumb2_insn(CPUState *e if (insn & (1 << 12)) { /* b/bl */ gen_jmp(s, offset); + instr_count_inc(ARM_THUMB_INSTRUCTION_BL); } else { /* blx */ offset &= ~(uint32_t)2; gen_bx_im(s, offset); + instr_count_inc(ARM_THUMB_INSTRUCTION_BLX1); } } else if (((insn >> 23) & 7) == 7) { /* Misc control */ @@ -7995,13 +8613,19 @@ illegal_op: static void disas_thumb_insn(CPUState *env, DisasContext *s) { - uint32_t val, insn, op, rm, rn, rd, shift, cond; + uint32_t val, insn, op, rm, rn, rd, shift, cond, instr_index; int32_t offset; int i; TCGv tmp; TCGv tmp2; TCGv addr; + instr_index = 0; + + instr_count_inc_init(ARM_THUMB_INSTRUCTION_COUNTER_OFFSET, + ARM_THUMB_INSTRUCTION_NOT_INSTRUMENTED); + + if (s->condexec_mask) { cond = s->condexec_cond; s->condlabel = gen_new_label(); @@ -8022,18 +8646,26 @@ static void disas_thumb_insn(CPUState *e gen_movl_T0_reg(s, rn); if (insn & (1 << 10)) { /* immediate */ + instr_index = 0; gen_op_movl_T1_im((insn >> 6) & 7); } else { /* reg */ + instr_index = 2; /* ADD3 / SUB3 */ rm = (insn >> 6) & 7; gen_movl_T1_reg(s, rm); } if (insn & (1 << 9)) { + instr_count_inc(ARM_THUMB_INSTRUCTION_SUB1 + instr_index); if (s->condexec_mask) gen_op_subl_T0_T1(); else gen_op_subl_T0_T1_cc(); } else { + if ((insn >> 6) & 7) { + instr_count_inc(ARM_THUMB_INSTRUCTION_ADD1 + instr_index); + } else { + instr_count_inc(ARM_THUMB_INSTRUCTION_MOV2); + } if (s->condexec_mask) gen_op_addl_T0_T1(); else @@ -8042,6 +8674,17 @@ static void disas_thumb_insn(CPUState *e gen_movl_reg_T0(s, rd); } else { /* shift immediate */ + switch (op) { + case 0x0: + instr_count_inc(ARM_THUMB_INSTRUCTION_LSL1); + break; + case 0x1: + instr_count_inc(ARM_THUMB_INSTRUCTION_LSR1); + break; + case 0x2: + instr_count_inc(ARM_THUMB_INSTRUCTION_ASR1); + break; + } rm = (insn >> 3) & 7; shift = (insn >> 6) & 0x1f; tmp = load_reg(s, rm); @@ -8063,19 +8706,23 @@ static void disas_thumb_insn(CPUState *e } switch (op) { case 0: /* mov */ + instr_count_inc(ARM_THUMB_INSTRUCTION_MOV1); if (!s->condexec_mask) gen_op_logic_T0_cc(); break; case 1: /* cmp */ + instr_count_inc(ARM_THUMB_INSTRUCTION_CMP1); gen_op_subl_T0_T1_cc(); break; case 2: /* add */ + instr_count_inc(ARM_THUMB_INSTRUCTION_ADD2); if (s->condexec_mask) gen_op_addl_T0_T1(); else gen_op_addl_T0_T1_cc(); break; case 3: /* sub */ + instr_count_inc(ARM_THUMB_INSTRUCTION_SUB2); if (s->condexec_mask) gen_op_subl_T0_T1(); else @@ -8087,6 +8734,7 @@ static void disas_thumb_insn(CPUState *e break; case 4: if (insn & (1 << 11)) { + instr_count_inc(ARM_THUMB_INSTRUCTION_LDR3); rd = (insn >> 8) & 7; /* load pc-relative. Bit 1 of PC is ignored. */ val = s->pc + 2 + ((insn & 0xff) * 4); @@ -8105,23 +8753,28 @@ static void disas_thumb_insn(CPUState *e op = (insn >> 8) & 3; switch (op) { case 0: /* add */ + instr_count_inc(ARM_THUMB_INSTRUCTION_ADD4); gen_movl_T0_reg(s, rd); gen_movl_T1_reg(s, rm); gen_op_addl_T0_T1(); gen_movl_reg_T0(s, rd); break; case 1: /* cmp */ + instr_count_inc(ARM_THUMB_INSTRUCTION_CMP3); gen_movl_T0_reg(s, rd); gen_movl_T1_reg(s, rm); gen_op_subl_T0_T1_cc(); break; case 2: /* mov/cpy */ + instr_count_inc(ARM_THUMB_INSTRUCTION_MOV3); gen_movl_T0_reg(s, rm); gen_movl_reg_T0(s, rd); break; case 3:/* branch [and link] exchange thumb register */ + instr_count_inc(ARM_THUMB_INSTRUCTION_BX); tmp = load_reg(s, rm); if (insn & (1 << 7)) { + instr_count_inc(ARM_THUMB_INSTRUCTION_BLX2); val = (uint32_t)s->pc | 1; tmp2 = new_tmp(); tcg_gen_movi_i32(tmp2, val); @@ -8155,16 +8808,19 @@ static void disas_thumb_insn(CPUState *e gen_movl_T1_reg(s, rm); switch (op) { case 0x0: /* and */ + instr_count_inc(ARM_THUMB_INSTRUCTION_AND); gen_op_andl_T0_T1(); if (!s->condexec_mask) gen_op_logic_T0_cc(); break; case 0x1: /* eor */ + instr_count_inc(ARM_THUMB_INSTRUCTION_EOR); gen_op_xorl_T0_T1(); if (!s->condexec_mask) gen_op_logic_T0_cc(); break; case 0x2: /* lsl */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LSL2); if (s->condexec_mask) { gen_helper_shl(cpu_T[1], cpu_T[1], cpu_T[0]); } else { @@ -8173,6 +8829,7 @@ static void disas_thumb_insn(CPUState *e } break; case 0x3: /* lsr */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LSR2); if (s->condexec_mask) { gen_helper_shr(cpu_T[1], cpu_T[1], cpu_T[0]); } else { @@ -8181,6 +8838,7 @@ static void disas_thumb_insn(CPUState *e } break; case 0x4: /* asr */ + instr_count_inc(ARM_THUMB_INSTRUCTION_ASR2); if (s->condexec_mask) { gen_helper_sar(cpu_T[1], cpu_T[1], cpu_T[0]); } else { @@ -8189,18 +8847,21 @@ static void disas_thumb_insn(CPUState *e } break; case 0x5: /* adc */ + instr_count_inc(ARM_THUMB_INSTRUCTION_ADC); if (s->condexec_mask) gen_adc_T0_T1(); else gen_op_adcl_T0_T1_cc(); break; case 0x6: /* sbc */ + instr_count_inc(ARM_THUMB_INSTRUCTION_SBC); if (s->condexec_mask) gen_sbc_T0_T1(); else gen_op_sbcl_T0_T1_cc(); break; case 0x7: /* ror */ + instr_count_inc(ARM_THUMB_INSTRUCTION_ROR); if (s->condexec_mask) { gen_helper_ror(cpu_T[1], cpu_T[1], cpu_T[0]); } else { @@ -8209,40 +8870,48 @@ static void disas_thumb_insn(CPUState *e } break; case 0x8: /* tst */ + instr_count_inc(ARM_THUMB_INSTRUCTION_TST); gen_op_andl_T0_T1(); gen_op_logic_T0_cc(); rd = 16; break; case 0x9: /* neg */ + instr_count_inc(ARM_THUMB_INSTRUCTION_NEG); if (s->condexec_mask) tcg_gen_neg_i32(cpu_T[0], cpu_T[1]); else gen_op_subl_T0_T1_cc(); break; case 0xa: /* cmp */ + instr_count_inc(ARM_THUMB_INSTRUCTION_CMP2); gen_op_subl_T0_T1_cc(); rd = 16; break; case 0xb: /* cmn */ + instr_count_inc(ARM_THUMB_INSTRUCTION_CMN); gen_op_addl_T0_T1_cc(); rd = 16; break; case 0xc: /* orr */ + instr_count_inc(ARM_THUMB_INSTRUCTION_ORR); gen_op_orl_T0_T1(); if (!s->condexec_mask) gen_op_logic_T0_cc(); break; case 0xd: /* mul */ + instr_count_inc(ARM_THUMB_INSTRUCTION_MUL); gen_op_mull_T0_T1(); if (!s->condexec_mask) gen_op_logic_T0_cc(); break; case 0xe: /* bic */ + instr_count_inc(ARM_THUMB_INSTRUCTION_BIC); gen_op_bicl_T0_T1(); if (!s->condexec_mask) gen_op_logic_T0_cc(); break; case 0xf: /* mvn */ + instr_count_inc(ARM_THUMB_INSTRUCTION_MVN); gen_op_notl_T1(); if (!s->condexec_mask) gen_op_logic_T1_cc(); @@ -8274,27 +8943,35 @@ static void disas_thumb_insn(CPUState *e switch (op) { case 0: /* str */ + instr_count_inc(ARM_THUMB_INSTRUCTION_STR2); gen_st32(tmp, addr, IS_USER(s)); break; case 1: /* strh */ + instr_count_inc(ARM_THUMB_INSTRUCTION_STRH2); gen_st16(tmp, addr, IS_USER(s)); break; case 2: /* strb */ + instr_count_inc(ARM_THUMB_INSTRUCTION_STRB2); gen_st8(tmp, addr, IS_USER(s)); break; case 3: /* ldrsb */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LDRSB); tmp = gen_ld8s(addr, IS_USER(s)); break; case 4: /* ldr */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LDR2); tmp = gen_ld32(addr, IS_USER(s)); break; case 5: /* ldrh */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LDRH2); tmp = gen_ld16u(addr, IS_USER(s)); break; case 6: /* ldrb */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LDRB2); tmp = gen_ld8u(addr, IS_USER(s)); break; case 7: /* ldrsh */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LDRSH); tmp = gen_ld16s(addr, IS_USER(s)); break; } @@ -8313,10 +8990,12 @@ static void disas_thumb_insn(CPUState *e if (insn & (1 << 11)) { /* load */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LDR1); tmp = gen_ld32(addr, IS_USER(s)); store_reg(s, rd, tmp); } else { /* store */ + instr_count_inc(ARM_THUMB_INSTRUCTION_STR1); tmp = load_reg(s, rd); gen_st32(tmp, addr, IS_USER(s)); } @@ -8333,10 +9012,12 @@ static void disas_thumb_insn(CPUState *e if (insn & (1 << 11)) { /* load */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LDRB1); tmp = gen_ld8u(addr, IS_USER(s)); store_reg(s, rd, tmp); } else { /* store */ + instr_count_inc(ARM_THUMB_INSTRUCTION_STRB1); tmp = load_reg(s, rd); gen_st8(tmp, addr, IS_USER(s)); } @@ -8353,10 +9034,12 @@ static void disas_thumb_insn(CPUState *e if (insn & (1 << 11)) { /* load */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LDRH1); tmp = gen_ld16u(addr, IS_USER(s)); store_reg(s, rd, tmp); } else { /* store */ + instr_count_inc(ARM_THUMB_INSTRUCTION_STRH1); tmp = load_reg(s, rd); gen_st16(tmp, addr, IS_USER(s)); } @@ -8372,10 +9055,12 @@ static void disas_thumb_insn(CPUState *e if (insn & (1 << 11)) { /* load */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LDR4); tmp = gen_ld32(addr, IS_USER(s)); store_reg(s, rd, tmp); } else { /* store */ + instr_count_inc(ARM_THUMB_INSTRUCTION_STR3); tmp = load_reg(s, rd); gen_st32(tmp, addr, IS_USER(s)); } @@ -8387,9 +9072,11 @@ static void disas_thumb_insn(CPUState *e rd = (insn >> 8) & 7; if (insn & (1 << 11)) { /* SP */ + instr_count_inc(ARM_THUMB_INSTRUCTION_ADD6); tmp = load_reg(s, 13); } else { /* PC. bit 1 is ignored. */ + instr_count_inc(ARM_THUMB_INSTRUCTION_ADD5); tmp = new_tmp(); tcg_gen_movi_i32(tmp, (s->pc + 2) & ~(uint32_t)2); } @@ -8406,8 +9093,11 @@ static void disas_thumb_insn(CPUState *e /* adjust stack pointer */ tmp = load_reg(s, 13); val = (insn & 0x7f) * 4; - if (insn & (1 << 7)) + if (insn & (1 << 7)) { + instr_count_inc(ARM_THUMB_INSTRUCTION_ADD7); val = -(int32_t)val; + } + else instr_count_inc(ARM_THUMB_INSTRUCTION_SUB4); tcg_gen_addi_i32(tmp, tmp, val); store_reg(s, 13, tmp); break; @@ -8418,10 +9108,22 @@ static void disas_thumb_insn(CPUState *e rm = (insn >> 3) & 7; tmp = load_reg(s, rm); switch ((insn >> 6) & 3) { - case 0: gen_sxth(tmp); break; - case 1: gen_sxtb(tmp); break; - case 2: gen_uxth(tmp); break; - case 3: gen_uxtb(tmp); break; + case 0: + instr_count_inc(ARM_THUMB_INSTRUCTION_SXTH); + gen_sxth(tmp); + break; + case 1: + instr_count_inc(ARM_THUMB_INSTRUCTION_SXTB); + gen_sxtb(tmp); + break; + case 2: + instr_count_inc(ARM_THUMB_INSTRUCTION_UXTH); + gen_uxth(tmp); + break; + case 3: + instr_count_inc(ARM_THUMB_INSTRUCTION_UXTB); + gen_uxtb(tmp); + break; } store_reg(s, rd, tmp); break; @@ -8443,10 +9145,12 @@ static void disas_thumb_insn(CPUState *e if (insn & (1 << i)) { if (insn & (1 << 11)) { /* pop */ + instr_count_inc(ARM_THUMB_INSTRUCTION_POP); tmp = gen_ld32(addr, IS_USER(s)); store_reg(s, i, tmp); } else { /* push */ + instr_count_inc(ARM_THUMB_INSTRUCTION_PUSH); tmp = load_reg(s, i); gen_st32(tmp, addr, IS_USER(s)); } @@ -8458,11 +9162,13 @@ static void disas_thumb_insn(CPUState *e if (insn & (1 << 8)) { if (insn & (1 << 11)) { /* pop pc */ + instr_count_inc(ARM_THUMB_INSTRUCTION_POP); tmp = gen_ld32(addr, IS_USER(s)); /* don't set the pc until the rest of the instruction has completed */ } else { /* push lr */ + instr_count_inc(ARM_THUMB_INSTRUCTION_PUSH); tmp = load_reg(s, 14); gen_st32(tmp, addr, IS_USER(s)); } @@ -8506,6 +9212,7 @@ static void disas_thumb_insn(CPUState *e break; case 0xe: /* bkpt */ + instr_count_inc(ARM_THUMB_INSTRUCTION_BKPT); gen_set_condexec(s); gen_set_pc_im(s->pc - 2); gen_exception(EXCP_BKPT); @@ -8518,15 +9225,25 @@ static void disas_thumb_insn(CPUState *e rd = insn & 0x7; tmp = load_reg(s, rn); switch ((insn >> 6) & 3) { - case 0: tcg_gen_bswap_i32(tmp, tmp); break; - case 1: gen_rev16(tmp); break; - case 3: gen_revsh(tmp); break; + case 0: + instr_count_inc(ARM_THUMB_INSTRUCTION_REV); + tcg_gen_bswap_i32(tmp, tmp); + break; + case 1: + instr_count_inc(ARM_THUMB_INSTRUCTION_REV16); + gen_rev16(tmp); + break; + case 3: + instr_count_inc(ARM_THUMB_INSTRUCTION_REVSH); + gen_revsh(tmp); + break; default: goto illegal_op; } store_reg(s, rd, tmp); break; case 6: /* cps */ + instr_count_inc(ARM_THUMB_INSTRUCTION_CPS); ARCH(6); if (IS_USER(s)) break; @@ -8568,10 +9285,12 @@ static void disas_thumb_insn(CPUState *e if (insn & (1 << i)) { if (insn & (1 << 11)) { /* load */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LDMIA); tmp = gen_ld32(addr, IS_USER(s)); store_reg(s, i, tmp); } else { /* store */ + instr_count_inc(ARM_THUMB_INSTRUCTION_STMIA); tmp = load_reg(s, i); gen_st32(tmp, addr, IS_USER(s)); } @@ -8595,6 +9314,7 @@ static void disas_thumb_insn(CPUState *e if (cond == 0xf) { /* swi */ + instr_count_inc(ARM_THUMB_INSTRUCTION_SWI); gen_set_condexec(s); gen_set_pc_im(s->pc); s->is_jmp = DISAS_SWI; @@ -8607,6 +9327,7 @@ static void disas_thumb_insn(CPUState *e gen_movl_T1_reg(s, 15); /* jump to the offset */ + instr_count_inc(ARM_THUMB_INSTRUCTION_B1); val = (uint32_t)s->pc + 2; offset = ((int32_t)insn << 24) >> 24; val += offset << 1; @@ -8615,11 +9336,14 @@ static void disas_thumb_insn(CPUState *e case 14: if (insn & (1 << 11)) { + printf("BLX1\n"); + instr_count_inc(ARM_THUMB_INSTRUCTION_BLX1); if (disas_thumb2_insn(env, s, insn)) goto undef32; break; } /* unconditional branch */ + instr_count_inc(ARM_THUMB_INSTRUCTION_B2); val = (uint32_t)s->pc; offset = ((int32_t)insn << 21) >> 21; val += (offset << 1) + 2; @@ -8627,6 +9351,11 @@ static void disas_thumb_insn(CPUState *e break; case 15: + if (insn & (1 << 11)) { + instr_count_inc(ARM_THUMB_INSTRUCTION_BL); + } else { + instr_count_inc(ARM_THUMB_INSTRUCTION_BL_BLX_HIGH_PART); + } if (disas_thumb2_insn(env, s, insn)) goto undef32; break; ^ permalink raw reply [flat|nested] 6+ messages in thread
[parent not found: <761ea48b0906150531j6cf88fa2v5652322efcc7469c@mail.gmail.com>]
* Re: [Qemu-devel] [PATCH] Instruction counting instrumentation for ARM, 2nd version & 2nd try [not found] ` <761ea48b0906150531j6cf88fa2v5652322efcc7469c@mail.gmail.com> @ 2009-06-15 13:31 ` Sami Kiminki 0 siblings, 0 replies; 6+ messages in thread From: Sami Kiminki @ 2009-06-15 13:31 UTC (permalink / raw) To: Laurent Desnogues; +Cc: qemu-devel [-- Attachment #1: Type: text/plain, Size: 275 bytes --] Apparently I succeeded in forgetting a switch when diffing and 2 files were missing. Attached is a new attempt. - Sami On Mon, 2009-06-15 at 14:31 +0200, Laurent Desnogues wrote: > Hi Sami, > > instruction.[ch] are not in your patch it seems :) > > Cheers, > > Laurent [-- Attachment #2: qemu-0.10.4-instrcount.patch --] [-- Type: text/x-patch, Size: 97798 bytes --] diff -Nurp qemu-0.10.4/Makefile qemu-0.10.4-instrcount/Makefile --- qemu-0.10.4/Makefile 2009-05-12 17:56:04.000000000 +0300 +++ qemu-0.10.4-instrcount/Makefile 2009-06-15 16:12:52.453488382 +0300 @@ -179,6 +179,10 @@ libqemu_common.a: $(OBJS) # USER_OBJS is code used by qemu userspace emulation USER_OBJS=cutils.o cache-utils.o +# instruction count instrumentation +USER_OBJS+=instrumentation.o + + libqemu_user.a: $(USER_OBJS) ###################################################################### diff -Nurp qemu-0.10.4/Makefile.target qemu-0.10.4-instrcount/Makefile.target --- qemu-0.10.4/Makefile.target 2009-05-12 17:56:04.000000000 +0300 +++ qemu-0.10.4-instrcount/Makefile.target 2009-06-15 16:12:52.450155174 +0300 @@ -208,8 +208,10 @@ ifeq ($(findstring s390, $(TARGET_ARCH) LIBOBJS+=s390-dis.o endif -# libqemu +# instrumentation support +LIBOBJS+=instrumentation.o +# libqemu libqemu.a: $(LIBOBJS) translate.o: translate.c cpu.h diff -Nurp qemu-0.10.4/instrumentation.c qemu-0.10.4-instrcount/instrumentation.c --- qemu-0.10.4/instrumentation.c 1970-01-01 02:00:00.000000000 +0200 +++ qemu-0.10.4-instrcount/instrumentation.c 2009-06-15 16:12:52.453488382 +0300 @@ -0,0 +1,37 @@ +/* + * instrument.c + * + * Created on: May 14, 2009 + * Author: ttoyry + */ + +#include "instrumentation.h" +unsigned int instrumentation_count_instructions = 0; +unsigned int instrumentation_count_instructions_log = 0; + +/* +static instr_counter_offsets instr_offsets; + +static inline void instr_count_inc_init(uint32_t offset, int instr) +{ + if (!instrumentation_count_instructions) return; + instr_offsets.cpustate_offset = offset; + TCGv tmp = new_tmp(); + tcg_gen_ld_i32(tmp, cpu_env, instr_offsets.cpustate_offset + sizeof(uint32_t) * instr); + instr_offsets.tcg_offset[0] = gen_opparam_ptr - 1; + tcg_gen_addi_i32(tmp, tmp, 1); + tcg_gen_st_i32(tmp, cpu_env, instr_offsets.cpustate_offset + sizeof(uint32_t) * instr); + instr_offsets.tcg_offset[1] = gen_opparam_ptr - 1; + dead_tmp(tmp); +} + + Increment instruction counter +static inline void instr_count_inc(int instr) +{ + if (!instrumentation_count_instructions) return; + *(instr_offsets.tcg_offset[0]) = instr_offsets.cpustate_offset + sizeof(uint32_t) * instr; + *(instr_offsets.tcg_offset[1]) = instr_offsets.cpustate_offset + sizeof(uint32_t) * instr; +} +*/ + + diff -Nurp qemu-0.10.4/instrumentation.h qemu-0.10.4-instrcount/instrumentation.h --- qemu-0.10.4/instrumentation.h 1970-01-01 02:00:00.000000000 +0200 +++ qemu-0.10.4-instrcount/instrumentation.h 2009-06-15 16:12:52.453488382 +0300 @@ -0,0 +1,47 @@ +/* + * instrumentation.h + * + * Author: Timo Toyry + */ + +#ifndef INSTRUMENTATION_H +#define INSTRUMENTATION_H + +#include <stdarg.h> +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <inttypes.h> + +/* + * 0 to disable (default) + * nonzero to enable + */ +extern unsigned int instrumentation_count_instructions; + +/* + * 0 output counters to stderr (default) + * nonzero output counters to qemulog-file + */ +extern unsigned int instrumentation_count_instructions_log; + +/* +extern TCGv_ptr cpu_env; +extern TCGv_i32 new_tmp(void); +extern void dead_tmp(TCGv tmp); + +#define ARM_INSTRUCTION_COUNTER_OFFSET offsetof(CPUState, arm_instr_count) +#define ARM_VFP_INSTRUCTION_COUNTER_OFFSET offsetof(CPUState, arm_vfp_instr_count) +#define ARM_THUMB_INSTRUCTION_COUNTER_OFFSET offsetof(CPUState, arm_thumb_instr_count) + +static inline void instr_count_inc_init(uint32_t offset, int instr); +static inline void instr_count_inc(int instr); + +typedef struct instr_counter_offsets { + uint32_t cpustate_offset; + TCGArg *tcg_offset[2]; +} instr_counter_offsets; +*/ + + +#endif /* INSTRUMENTATION_H */ diff -Nurp qemu-0.10.4/linux-user/main.c qemu-0.10.4-instrcount/linux-user/main.c --- qemu-0.10.4/linux-user/main.c 2009-05-12 17:56:03.000000000 +0300 +++ qemu-0.10.4-instrcount/linux-user/main.c 2009-06-15 16:12:52.453488382 +0300 @@ -35,6 +35,8 @@ #include "envlist.h" +#include "instrumentation.h" + #define DEBUG_LOGFILE "/tmp/qemu.log" char *exec_path; @@ -2199,6 +2201,12 @@ static void usage(void) "-p pagesize set the host page size to 'pagesize'\n" "-strace log system calls\n" "\n" +#ifdef TARGET_ARM + "Other:\n" + "-instrcount Count instructions\n" + "-instrcountlog=qemu_log Output counters to qemu-log file\n" + "\n" +#endif "Environment variables:\n" "QEMU_STRACE Print system calls and arguments similar to the\n" " 'strace' program. Enable by setting to any value.\n" @@ -2341,8 +2349,11 @@ int main(int argc, char **argv, char **e (void) envlist_unsetenv(envlist, "LD_PRELOAD"); } else if (!strcmp(r, "strace")) { do_strace = 1; - } else - { + } else if (!strcmp(r, "instrcount")) { + instrumentation_count_instructions = 1; + } else if (!strcmp(r, "instrcountlog=qemu_log")) { + instrumentation_count_instructions_log = 1; + } else { usage(); } } diff -Nurp qemu-0.10.4/linux-user/syscall.c qemu-0.10.4-instrcount/linux-user/syscall.c --- qemu-0.10.4/linux-user/syscall.c 2009-05-12 17:56:03.000000000 +0300 +++ qemu-0.10.4-instrcount/linux-user/syscall.c 2009-06-15 16:12:52.453488382 +0300 @@ -79,6 +79,9 @@ #include "qemu.h" #include "qemu-common.h" +#include "qemu-log.h" +#include "instrumentation.h" + #if defined(USE_NPTL) #include <linux/futex.h> #define CLONE_NPTL_FLAGS2 (CLONE_SETTLS | \ @@ -300,6 +303,67 @@ extern int setfsuid(int); extern int setfsgid(int); extern int setgroups(int, gid_t *); + +inline static void print_counters(const char *buf) +{ + if (!instrumentation_count_instructions_log) { + fprintf(stderr, "%s", buf); + } else { + qemu_log("%s", buf); + } +} + +inline static void print_instruction_counters_helper( + const char **instr_names, int no_instructions, const uint32_t *counters) +{ + char buf[256]; + int i1; + uint32_t counted = 0; + for (i1 = 0; i1 < no_instructions; i1++) { + if (counters[i1] > 0) { + sprintf(buf, "%s: %d\n", instr_names[i1], + counters[i1]); + print_counters(buf); + if (i1 < (no_instructions - 2)) { + counted += counters[i1]; + } + } + } + sprintf(buf, "Counted instructions: %d\n", counted); + print_counters(buf); +} + +inline static void print_instruction_counters(CPUState *env) +{ + char buf[256]; +#ifdef TARGET_ARM + if (!instrumentation_count_instructions) return; + if (instrumentation_count_instructions_log && !logfile) { + fprintf(stderr, "Setting log file to \"qemu_instr_count.log\"\n"); + cpu_set_log_filename("qemu_instr_count.log"); + cpu_set_log(1); + } + + sprintf(buf, "Arm instructions:\n"); + print_counters(buf); + print_instruction_counters_helper(arm_instr_names, ARM_INSTRUCTIONS, + env->arm_instr_count); + + sprintf(buf, "VFP instructions:\n"); + print_counters(buf); + print_instruction_counters_helper(arm_vfp_instr_names, + ARM_VFP_INSTRUCTIONS, env->arm_vfp_instr_count); + + sprintf(buf, "Thumb instructions:\n"); + print_counters(buf); + print_instruction_counters_helper(arm_thumb_instr_names, + ARM_THUMB_INSTRUCTIONS, env->arm_thumb_instr_count); +#else + sprintf(buf, "Instruction counting not supported in this platform.\n"); + print_counters(buf); +#endif +} + #define ERRNO_TABLE_SIZE 1200 /* target_to_host_errno_table[] is initialized from @@ -3431,6 +3495,7 @@ abi_long do_syscall(void *cpu_env, int n #ifdef HAVE_GPROF _mcleanup(); #endif + print_instruction_counters(cpu_env); gdb_exit(cpu_env, arg1); /* XXX: should free thread stack and CPU env */ sys_exit(arg1); @@ -4923,6 +4988,7 @@ abi_long do_syscall(void *cpu_env, int n #ifdef HAVE_GPROF _mcleanup(); #endif + print_instruction_counters(cpu_env); gdb_exit(cpu_env, arg1); ret = get_errno(exit_group(arg1)); break; diff -Nurp qemu-0.10.4/target-arm/cpu.h qemu-0.10.4-instrcount/target-arm/cpu.h --- qemu-0.10.4/target-arm/cpu.h 2009-05-12 17:56:33.000000000 +0300 +++ qemu-0.10.4-instrcount/target-arm/cpu.h 2009-06-15 16:12:52.453488382 +0300 @@ -51,6 +51,340 @@ #define ARMV7M_EXCP_PENDSV 14 #define ARMV7M_EXCP_SYSTICK 15 +/* Do not change the order of the instructions in the blocks marked + * by - | -. */ +enum arm_instructions { + ARM_INSTRUCTION_B, + ARM_INSTRUCTION_BL, + ARM_INSTRUCTION_BLX, + ARM_INSTRUCTION_BX, + ARM_INSTRUCTION_BXJ, + ARM_INSTRUCTION_ADC, + ARM_INSTRUCTION_ADD, + ARM_INSTRUCTION_AND, + ARM_INSTRUCTION_BIC, + ARM_INSTRUCTION_CMN, + ARM_INSTRUCTION_CMP, + ARM_INSTRUCTION_EOR, + ARM_INSTRUCTION_MOV, + ARM_INSTRUCTION_MVN, + ARM_INSTRUCTION_ORR, + ARM_INSTRUCTION_RSB, + ARM_INSTRUCTION_RSC, + ARM_INSTRUCTION_SBC, + ARM_INSTRUCTION_SUB, + ARM_INSTRUCTION_TEQ, + ARM_INSTRUCTION_TST, + ARM_INSTRUCTION_MUL, /* - */ + ARM_INSTRUCTION_MULS, /* - */ + ARM_INSTRUCTION_MLA, /* - */ + ARM_INSTRUCTION_MLAS, /* - */ + ARM_INSTRUCTION_SMLAXY, + ARM_INSTRUCTION_SMLAL, /* - */ + ARM_INSTRUCTION_SMLALS, /* - */ + ARM_INSTRUCTION_SMLALXY, + ARM_INSTRUCTION_SMLAWY, + ARM_INSTRUCTION_SMUAD, /* - */ + ARM_INSTRUCTION_SMUSD, /* | */ + ARM_INSTRUCTION_SMLAD, /* | */ + ARM_INSTRUCTION_SMLSD, /* - */ + ARM_INSTRUCTION_SMLALD, /* - */ + ARM_INSTRUCTION_SMLSLD, /* - */ + ARM_INSTRUCTION_SMMLA, + ARM_INSTRUCTION_SMMLS, + ARM_INSTRUCTION_SMMUL, + ARM_INSTRUCTION_SMULXY, + ARM_INSTRUCTION_SMULL, /* - */ + ARM_INSTRUCTION_SMULLS, /* - */ + ARM_INSTRUCTION_SMULWY, + ARM_INSTRUCTION_UMAAL, + ARM_INSTRUCTION_UMLAL, /* - */ + ARM_INSTRUCTION_UMLALS, /* - */ + ARM_INSTRUCTION_UMULL, /* - */ + ARM_INSTRUCTION_UMULLS, /* - */ + ARM_INSTRUCTION_QADD, + ARM_INSTRUCTION_QDADD, + ARM_INSTRUCTION_QADD16, /* - */ + ARM_INSTRUCTION_QADDSUBX, /* | */ + ARM_INSTRUCTION_QSUBADDX, /* | */ + ARM_INSTRUCTION_QSUB16, /* | */ + ARM_INSTRUCTION_QADD8, /* | */ + ARM_INSTRUCTION_QSUB8, /* - */ + ARM_INSTRUCTION_QSUB, + ARM_INSTRUCTION_QDSUB, + ARM_INSTRUCTION_SADD16, /* - */ + ARM_INSTRUCTION_SADDSUBX, /* | */ + ARM_INSTRUCTION_SSUBADDX, /* | */ + ARM_INSTRUCTION_SSUB16, /* | */ + ARM_INSTRUCTION_SADD8, /* | */ + ARM_INSTRUCTION_SSUB8, /* - */ + ARM_INSTRUCTION_SHADD16, /* - */ + ARM_INSTRUCTION_SHADDSUBX, /* | */ + ARM_INSTRUCTION_SHSUBADDX, /* | */ + ARM_INSTRUCTION_SHSUB16, /* | */ + ARM_INSTRUCTION_SHADD8, /* | */ + ARM_INSTRUCTION_SHSUB8, /* - */ + ARM_INSTRUCTION_UADD16, /* - */ + ARM_INSTRUCTION_UADDSUBX, /* | */ + ARM_INSTRUCTION_USUBADDX, /* | */ + ARM_INSTRUCTION_USUB16, /* | */ + ARM_INSTRUCTION_UADD8, /* | */ + ARM_INSTRUCTION_USUB8, /* - */ + ARM_INSTRUCTION_UHADD16, /* - */ + ARM_INSTRUCTION_UHADDSUBX, /* | */ + ARM_INSTRUCTION_UHSUBADDX, /* | */ + ARM_INSTRUCTION_UHSUB16, /* | */ + ARM_INSTRUCTION_UHADD8, /* | */ + ARM_INSTRUCTION_UHSUB8, /* - */ + ARM_INSTRUCTION_UQADD16, /* - */ + ARM_INSTRUCTION_UQADDSUBX, /* | */ + ARM_INSTRUCTION_UQSUBADDX, /* | */ + ARM_INSTRUCTION_UQSUB16, /* | */ + ARM_INSTRUCTION_UQADD8, /* | */ + ARM_INSTRUCTION_UQSUB8, /* - */ + ARM_INSTRUCTION_SXTAB16, /* - */ + ARM_INSTRUCTION_SXTAB, /* | */ + ARM_INSTRUCTION_SXTAH, /* | */ + ARM_INSTRUCTION_SXTB16, /* | */ + ARM_INSTRUCTION_SXTB, /* | */ + ARM_INSTRUCTION_SXTH, /* - */ + ARM_INSTRUCTION_UXTAB16, /* - */ + ARM_INSTRUCTION_UXTAB, /* | */ + ARM_INSTRUCTION_UXTAH, /* | */ + ARM_INSTRUCTION_UXTB16, /* | */ + ARM_INSTRUCTION_UXTB, /* | */ + ARM_INSTRUCTION_UXTH, /* - */ + ARM_INSTRUCTION_CLZ, + ARM_INSTRUCTION_USAD8, + ARM_INSTRUCTION_USADA8, + ARM_INSTRUCTION_PKH, + ARM_INSTRUCTION_PKHBT, + ARM_INSTRUCTION_PKHTB, + ARM_INSTRUCTION_REV, + ARM_INSTRUCTION_REV16, + ARM_INSTRUCTION_REVSH, + ARM_INSTRUCTION_SEL, + ARM_INSTRUCTION_SSAT, + ARM_INSTRUCTION_SSAT16, + ARM_INSTRUCTION_USAT, + ARM_INSTRUCTION_USAT16, + ARM_INSTRUCTION_MRS, + ARM_INSTRUCTION_MSR, + ARM_INSTRUCTION_CPS, + ARM_INSTRUCTION_SETEND, + ARM_INSTRUCTION_LDR, + ARM_INSTRUCTION_LDRB, + ARM_INSTRUCTION_LDRBT, + ARM_INSTRUCTION_LDRD, + ARM_INSTRUCTION_LDREX, + ARM_INSTRUCTION_LDRH, + ARM_INSTRUCTION_LDRSB, + ARM_INSTRUCTION_LDRSH, + ARM_INSTRUCTION_LDRT, + ARM_INSTRUCTION_STR, + ARM_INSTRUCTION_STRB, + ARM_INSTRUCTION_STRBT, + ARM_INSTRUCTION_STRD, + ARM_INSTRUCTION_STREX, + ARM_INSTRUCTION_STRH, + ARM_INSTRUCTION_STRT, + ARM_INSTRUCTION_LDM1, //See Arm manual ARM DDI 0100I page A3-27 + ARM_INSTRUCTION_LDM2, + ARM_INSTRUCTION_LDM3, + ARM_INSTRUCTION_STM1, + ARM_INSTRUCTION_STM2, + ARM_INSTRUCTION_SWP, + ARM_INSTRUCTION_SWPB, + ARM_INSTRUCTION_BKPT, + ARM_INSTRUCTION_SWI, + ARM_INSTRUCTION_CDP, + ARM_INSTRUCTION_LDC, + ARM_INSTRUCTION_MCR, + ARM_INSTRUCTION_MCRR, + ARM_INSTRUCTION_MRC, + ARM_INSTRUCTION_MRRC, + ARM_INSTRUCTION_STC, + ARM_INSTRUCTION_PLD, + ARM_INSTRUCTION_RFE, + ARM_INSTRUCTION_SRS, + ARM_INSTRUCTION_MCRR2, + ARM_INSTRUCTION_MRRC2, + ARM_INSTRUCTION_STC2, + ARM_INSTRUCTION_LDC2, + ARM_INSTRUCTION_CDP2, + ARM_INSTRUCTION_MCR2, + ARM_INSTRUCTION_MRC2, + ARM_INSTRUCTION_COPROCESSOR, + ARM_INSTRUCTION_UNKNOWN, + ARM_INSTRUCTION_NOT_INSTRUMENTED, + ARM_INSTRUCTION_TOTAL_COUNT, + ARM_INSTRUCTIONS +}; + +/* Do not change the order of the instructions in the blocks marked + * by - | -. */ +enum arm_vfp_instructions { + ARM_VFP_INSTRUCTION_FABSD, /* - */ + ARM_VFP_INSTRUCTION_FABSS, /* - */ + ARM_VFP_INSTRUCTION_FADDD, /* - */ + ARM_VFP_INSTRUCTION_FADDS, /* - */ + ARM_VFP_INSTRUCTION_FCMPD, /* - */ + ARM_VFP_INSTRUCTION_FCMPS, /* - */ + ARM_VFP_INSTRUCTION_FCMPED, /* - */ + ARM_VFP_INSTRUCTION_FCMPES, /* - */ + ARM_VFP_INSTRUCTION_FCMPEZD, /* - */ + ARM_VFP_INSTRUCTION_FCMPEZS, /* - */ + ARM_VFP_INSTRUCTION_FCMPZD, /* - */ + ARM_VFP_INSTRUCTION_FCMPZS, /* - */ + ARM_VFP_INSTRUCTION_FCPYD, /* - */ + ARM_VFP_INSTRUCTION_FCPYS, /* - */ + ARM_VFP_INSTRUCTION_FCVTDS, /* - */ + ARM_VFP_INSTRUCTION_FCVTSD, /* - */ + ARM_VFP_INSTRUCTION_FDIVD, /* - */ + ARM_VFP_INSTRUCTION_FDIVS, /* - */ + ARM_VFP_INSTRUCTION_FLDD, /* - */ + ARM_VFP_INSTRUCTION_FLDS, /* - */ + ARM_VFP_INSTRUCTION_FLDMD, /* - */ + ARM_VFP_INSTRUCTION_FLDMS, /* - */ + ARM_VFP_INSTRUCTION_FLDMX, + ARM_VFP_INSTRUCTION_FMACD, + ARM_VFP_INSTRUCTION_FMACS, + ARM_VFP_INSTRUCTION_FMDHR, + ARM_VFP_INSTRUCTION_FMDLR, + ARM_VFP_INSTRUCTION_FMDRR, + ARM_VFP_INSTRUCTION_FMRDH, + ARM_VFP_INSTRUCTION_FMRDL, + ARM_VFP_INSTRUCTION_FMRRD, /* - */ + ARM_VFP_INSTRUCTION_FMRRS, /* - */ + ARM_VFP_INSTRUCTION_FMRS, + ARM_VFP_INSTRUCTION_FMRX, + ARM_VFP_INSTRUCTION_FMSCD, /* - */ + ARM_VFP_INSTRUCTION_FMSCS, /* - */ + ARM_VFP_INSTRUCTION_FMSR, + ARM_VFP_INSTRUCTION_FMSRR, + ARM_VFP_INSTRUCTION_FMSTAT, + ARM_VFP_INSTRUCTION_FMULD, /* - */ + ARM_VFP_INSTRUCTION_FMULS, /* - */ + ARM_VFP_INSTRUCTION_FMXR, + ARM_VFP_INSTRUCTION_FNEGD, /* - */ + ARM_VFP_INSTRUCTION_FNEGS, /* - */ + ARM_VFP_INSTRUCTION_FNMACD, /* - */ + ARM_VFP_INSTRUCTION_FNMACS, /* - */ + ARM_VFP_INSTRUCTION_FNMSCD, /* - */ + ARM_VFP_INSTRUCTION_FNMSCS, /* - */ + ARM_VFP_INSTRUCTION_FNMULD, /* - */ + ARM_VFP_INSTRUCTION_FNMULS, /* - */ + ARM_VFP_INSTRUCTION_FSITOD, /* - */ + ARM_VFP_INSTRUCTION_FSITOS, /* - */ + ARM_VFP_INSTRUCTION_FSQRTD, /* - */ + ARM_VFP_INSTRUCTION_FSQRTS, /* - */ + ARM_VFP_INSTRUCTION_FSTD, /* - */ + ARM_VFP_INSTRUCTION_FSTS, /* - */ + ARM_VFP_INSTRUCTION_FSTMD, + ARM_VFP_INSTRUCTION_FSTMS, + ARM_VFP_INSTRUCTION_FSTMX, + ARM_VFP_INSTRUCTION_FSUBD, /* - */ + ARM_VFP_INSTRUCTION_FSUBS, /* - */ + ARM_VFP_INSTRUCTION_FTOSID, /* - */ + ARM_VFP_INSTRUCTION_FTOSIS, /* - */ + ARM_VFP_INSTRUCTION_FTOSIZD, /* - */ + ARM_VFP_INSTRUCTION_FTOSIZS, /* - */ + ARM_VFP_INSTRUCTION_FTOUID, /* - */ + ARM_VFP_INSTRUCTION_FTOUIS, /* - */ + ARM_VFP_INSTRUCTION_FTOUIZD, /* - */ + ARM_VFP_INSTRUCTION_FTOUIZS, /* - */ + ARM_VFP_INSTRUCTION_FUITOD, /* - */ + ARM_VFP_INSTRUCTION_FUITOS, /* - */ + ARM_VFP_INSTRUCTION_UNKNOWN, + ARM_VFP_INSTRUCTION_NOT_INSTRUMENTED, + ARM_VFP_INSTRUCTION_TOTAL_COUNT, + ARM_VFP_INSTRUCTIONS +}; + +/* Do not change the order of the instructions in the blocks marked + * by - | -. */ +enum arm_thumb_instructions { + ARM_THUMB_INSTRUCTION_ADC, + ARM_THUMB_INSTRUCTION_ADD1, /* - */ + ARM_THUMB_INSTRUCTION_ADD2, /* | */ + ARM_THUMB_INSTRUCTION_ADD3, /* - */ + ARM_THUMB_INSTRUCTION_ADD4, + ARM_THUMB_INSTRUCTION_ADD5, + ARM_THUMB_INSTRUCTION_ADD6, + ARM_THUMB_INSTRUCTION_ADD7, + ARM_THUMB_INSTRUCTION_AND, + ARM_THUMB_INSTRUCTION_ASR1, + ARM_THUMB_INSTRUCTION_ASR2, + ARM_THUMB_INSTRUCTION_B1, + ARM_THUMB_INSTRUCTION_B2, + ARM_THUMB_INSTRUCTION_BIC, + ARM_THUMB_INSTRUCTION_BKPT, + ARM_THUMB_INSTRUCTION_BL, + ARM_THUMB_INSTRUCTION_BLX1, + ARM_THUMB_INSTRUCTION_BLX2, + ARM_THUMB_INSTRUCTION_BL_BLX_HIGH_PART, + ARM_THUMB_INSTRUCTION_BX, + ARM_THUMB_INSTRUCTION_CMN, + ARM_THUMB_INSTRUCTION_CMP1, + ARM_THUMB_INSTRUCTION_CMP2, + ARM_THUMB_INSTRUCTION_CMP3, + ARM_THUMB_INSTRUCTION_CPS, + ARM_THUMB_INSTRUCTION_CPY, + ARM_THUMB_INSTRUCTION_EOR, + ARM_THUMB_INSTRUCTION_LDMIA, + ARM_THUMB_INSTRUCTION_LDR1, + ARM_THUMB_INSTRUCTION_LDR2, + ARM_THUMB_INSTRUCTION_LDR3, + ARM_THUMB_INSTRUCTION_LDR4, + ARM_THUMB_INSTRUCTION_LDRB1, + ARM_THUMB_INSTRUCTION_LDRB2, + ARM_THUMB_INSTRUCTION_LDRH1, + ARM_THUMB_INSTRUCTION_LDRH2, + ARM_THUMB_INSTRUCTION_LDRSB, + ARM_THUMB_INSTRUCTION_LDRSH, + ARM_THUMB_INSTRUCTION_LSL1, + ARM_THUMB_INSTRUCTION_LSL2, + ARM_THUMB_INSTRUCTION_LSR1, + ARM_THUMB_INSTRUCTION_LSR2, + ARM_THUMB_INSTRUCTION_MOV1, + ARM_THUMB_INSTRUCTION_MOV2, + ARM_THUMB_INSTRUCTION_MOV3, + ARM_THUMB_INSTRUCTION_MUL, + ARM_THUMB_INSTRUCTION_MVN, + ARM_THUMB_INSTRUCTION_NEG, + ARM_THUMB_INSTRUCTION_ORR, + ARM_THUMB_INSTRUCTION_POP, + ARM_THUMB_INSTRUCTION_PUSH, + ARM_THUMB_INSTRUCTION_REV, + ARM_THUMB_INSTRUCTION_REV16, + ARM_THUMB_INSTRUCTION_REVSH, + ARM_THUMB_INSTRUCTION_ROR, + ARM_THUMB_INSTRUCTION_SBC, + ARM_THUMB_INSTRUCTION_SETEND, + ARM_THUMB_INSTRUCTION_STMIA, + ARM_THUMB_INSTRUCTION_STR1, + ARM_THUMB_INSTRUCTION_STR2, + ARM_THUMB_INSTRUCTION_STR3, + ARM_THUMB_INSTRUCTION_STRB1, + ARM_THUMB_INSTRUCTION_STRB2, + ARM_THUMB_INSTRUCTION_STRH1, + ARM_THUMB_INSTRUCTION_STRH2, + ARM_THUMB_INSTRUCTION_SUB1, /* - */ + ARM_THUMB_INSTRUCTION_SUB2, /* | */ + ARM_THUMB_INSTRUCTION_SUB3, /* - */ + ARM_THUMB_INSTRUCTION_SUB4, + ARM_THUMB_INSTRUCTION_SWI, + ARM_THUMB_INSTRUCTION_SXTB, + ARM_THUMB_INSTRUCTION_SXTH, + ARM_THUMB_INSTRUCTION_TST, + ARM_THUMB_INSTRUCTION_UXTB, + ARM_THUMB_INSTRUCTION_UXTH, + ARM_THUMB_INSTRUCTION_UNKNOWN, + ARM_THUMB_INSTRUCTION_NOT_INSTRUMENTED, + ARM_THUMB_INSTRUCTION_TOTAL_COUNT, + ARM_THUMB_INSTRUCTIONS +}; + typedef void ARMWriteCPFunc(void *opaque, int cp_info, int srcreg, int operand, uint32_t value); typedef uint32_t ARMReadCPFunc(void *opaque, int cp_info, @@ -202,6 +536,12 @@ typedef struct CPUARMState { /* These fields after the common ones so they are preserved on reset. */ struct arm_boot_info *boot_info; + + /* Instruction counting "regs". */ + uint32_t arm_instr_count[ARM_INSTRUCTIONS]; + uint32_t arm_vfp_instr_count[ARM_VFP_INSTRUCTIONS]; + uint32_t arm_thumb_instr_count[ARM_THUMB_INSTRUCTIONS]; + } CPUARMState; CPUARMState *cpu_arm_init(const char *cpu_model); @@ -446,4 +786,8 @@ static inline void cpu_get_tb_cpu_state( *flags |= (1 << 7); } +extern const char const *arm_instr_names[]; +extern const char const *arm_vfp_instr_names[]; +extern const char const *arm_thumb_instr_names[]; + #endif diff -Nurp qemu-0.10.4/target-arm/translate.c qemu-0.10.4-instrcount/target-arm/translate.c --- qemu-0.10.4/target-arm/translate.c 2009-05-12 17:56:33.000000000 +0300 +++ qemu-0.10.4-instrcount/target-arm/translate.c 2009-06-15 16:12:52.481605127 +0300 @@ -31,6 +31,8 @@ #include "tcg-op.h" #include "qemu-log.h" +#include "instrumentation.h" + #include "helpers.h" #define GEN_HELPER 1 #include "helpers.h" @@ -235,6 +237,365 @@ static void store_reg(DisasContext *s, i /* Set NZCV flags from the high 4 bits of var. */ #define gen_set_nzcv(var) gen_set_cpsr(var, CPSR_NZCV) +/* string names for arm_instruction enum values */ +const char const *arm_instr_names[] = { + "b", + "bl", + "blx", + "bx", + "bxj", + "adc", + "add", + "and", + "bic", + "cmn", + "cmp", + "eor", + "mov", + "mvn", + "orr", + "rsb", + "rsc", + "sbc", + "sub", + "teq", + "tst", + "mul", + "muls", + "mla", + "mlas", + "smla<x><y>", + "smlal", + "smlals", + "smlal<x><y>", + "smlaw<y>", + "smuad", + "smusd", + "smlad", + "smlsd", + "smlald", + "smlsld", + "smmla", + "smmls", + "smmul", + "smul<x><y>", + "smull", + "smulls", + "smulw<y>", + "umaal", + "umlal", + "umlals", + "umull", + "umulls", + "qadd", + "qdadd", + "qadd16", + "qaddsubx", + "qsubaddx", + "qsub16", + "qadd8", + "qsub8", + "qsub", + "qdsub", + "sadd16", + "saddsubx", + "ssubaddx", + "ssub16", + "sadd8", + "ssub8", + "shadd16", + "shaddsubx", + "shsubaddx", + "shsub16", + "shadd8", + "shsub8", + "uadd16", + "uaddsubx", + "usubaddx", + "usub16", + "uadd8", + "usub8", + "uhadd16", + "uhaddsubx", + "uhsubaddx", + "uhsub16", + "uhadd8", + "uhsub8", + "uqadd16", + "uqaddsubx", + "uqsubaddx", + "uqsub16", + "uqadd8", + "uqsub8", + "sxtab16", + "sxtab", + "sxtah", + "sxtb16", + "sxtb", + "sxth", + "uxtab16", + "uxtab", + "uxtah", + "uxtb16", + "uxtb", + "uxth", + "clz", + "usad8", + "usada8", + "pkh", + "pkhbt", + "pkhtb", + "rev", + "rev16", + "revsh", + "sel", + "ssat", + "ssat16", + "usat", + "usat16", + "mrs", + "msr", + "cps", + "setend", + "ldr", + "ldrb", + "ldrbt", + "ldrd", + "ldrex", + "ldrh", + "ldrsb", + "ldrsh", + "ldrt", + "str", + "strb", + "strbt", + "strd", + "strex", + "strh", + "strt", + "ldm1", //see arm manual ARM DDI 0100I page A3-27 + "ldm2", + "ldm3", + "stm1", + "stm2", + "swp", + "swpb", + "bkpt", + "swi", + "cdp", + "ldc", + "mcr", + "mcrr", + "mrc", + "mrrc", + "stc", + "pld", + "rfe", + "srs", + "mcrr2", + "mrrc2", + "stc2", + "ldc2", + "cdp2", + "mcr2", + "mrc2", + "coprocessor", + "unknown", + "not_instrumented", + "total_instructions" +}; + +const char const *arm_vfp_instr_names[] = { /* string names for arm_vfp_instruction enum values */ + "fabsd", + "fabss", + "faddd", + "fadds", + "fcmpd", + "fcmps", + "fcmped", + "fcmpes", + "fcmpezd", + "fcmpezs", + "fcmpzd", + "fcmpzs", + "fcpyd", + "fcpys", + "fcvtds", + "fcvtsd", + "fdivd", + "fdivs", + "fldd", + "flds", + "fldmd", + "fldms", + "fldmx", + "fmacd", + "fmacs", + "fmdhr", + "fmdlr", + "fmdrr", + "fmrdh", + "fmrdl", + "fmrrd", + "fmrrs", + "fmrs", + "fmrx", + "fmscd", + "fmscs", + "fmsr", + "fmsrr", + "fmstat", + "fmuld", + "fmuls", + "fmxr", + "fnegd", + "fnegs", + "fnmacd", + "fnmacs", + "fnmscd", + "fnmscs", + "fnmuld", + "fnmuls", + "fsitod", + "fsitos", + "fsqrtd", + "fsqrts", + "fstd", + "fsts", + "fstmd", + "fstms", + "fstmx", + "fsubd", + "fsubs", + "ftosid", + "ftosis", + "ftosizd", + "ftosizs", + "ftouid", + "ftouis", + "ftouizd", + "ftouizs", + "fuitod", + "fuitos", + "unknown", + "not_instrumented", + "total_count" +}; + +/* string names for arm_thumb_instruction enum values */ +const char const *arm_thumb_instr_names[] = { + "adc", + "add1", + "add2", + "add3", + "add4", + "add5", + "add6", + "add7", + "and", + "asr1", + "asr2", + "b1", + "b2", + "bic", + "bkpt", + "bl", + "blx1", + "blx2", + "bl-blx_high", + "bx", + "cmn", + "cmp1", + "cmp2", + "cmp3", + "cps", + "cpy", + "eor", + "ldmia", + "ldr1", + "ldr2", + "ldr3", + "ldr4", + "ldrb1", + "ldrb2", + "ldrh1", + "ldrh2", + "ldrsb", + "ldrsh", + "lsl1", + "lsl2", + "lsr1", + "lsr2", + "mov1", + "mov2", + "mov3", + "mul", + "mvn", + "neg", + "orr", + "pop", + "push", + "rev", + "rev16", + "revsh", + "ror", + "sbc", + "setend", + "stmia", + "str1", + "str2", + "str3", + "strb1", + "strb2", + "strh1", + "strh2", + "sub1", + "sub2", + "sub3", + "sub4", + "swi", + "sxtb", + "sxth", + "tst", + "uxtb", + "uxth", + "unknown", + "not_instrumented", + "total_count", +}; + +#define ARM_INSTRUCTION_COUNTER_OFFSET offsetof(CPUState, arm_instr_count) +#define ARM_VFP_INSTRUCTION_COUNTER_OFFSET offsetof(CPUState, arm_vfp_instr_count) +#define ARM_THUMB_INSTRUCTION_COUNTER_OFFSET offsetof(CPUState, arm_thumb_instr_count) + +typedef struct instr_counter_offsets { + uint32_t cpustate_offset; + TCGArg *tcg_offset[2]; +} instr_counter_offsets; + +static instr_counter_offsets instr_offsets; + +static inline void instr_count_inc_init(uint32_t offset, int instr) +{ + if (!instrumentation_count_instructions) return; + instr_offsets.cpustate_offset = offset; + TCGv tmp = new_tmp(); + tcg_gen_ld_i32(tmp, cpu_env, instr_offsets.cpustate_offset + sizeof(uint32_t) * instr); + instr_offsets.tcg_offset[0] = gen_opparam_ptr - 1; + tcg_gen_addi_i32(tmp, tmp, 1); + tcg_gen_st_i32(tmp, cpu_env, instr_offsets.cpustate_offset + sizeof(uint32_t) * instr); + instr_offsets.tcg_offset[1] = gen_opparam_ptr - 1; + dead_tmp(tmp); +} + +/* Increment instruction counter */ +static inline void instr_count_inc(int instr) +{ + if (!instrumentation_count_instructions) return; + *(instr_offsets.tcg_offset[0]) = instr_offsets.cpustate_offset + sizeof(uint32_t) * instr; + *(instr_offsets.tcg_offset[1]) = instr_offsets.cpustate_offset + sizeof(uint32_t) * instr; +} + static void gen_exception(int excp) { TCGv tmp = new_tmp(); @@ -580,6 +941,7 @@ static inline void gen_arm_shift_reg(TCG static void gen_arm_parallel_addsub(int op1, int op2, TCGv a, TCGv b) { TCGv_ptr tmp; + unsigned int instr_index = 0; switch (op1) { #define gen_pas_helper(name) glue(gen_helper_,name)(a, a, b, tmp) @@ -587,28 +949,37 @@ static void gen_arm_parallel_addsub(int tmp = tcg_temp_new_ptr(); tcg_gen_addi_ptr(tmp, cpu_env, offsetof(CPUState, GE)); PAS_OP(s) + instr_index = ARM_INSTRUCTION_SADD16; break; case 5: tmp = tcg_temp_new_ptr(); tcg_gen_addi_ptr(tmp, cpu_env, offsetof(CPUState, GE)); PAS_OP(u) + instr_index = ARM_INSTRUCTION_UADD16; break; #undef gen_pas_helper #define gen_pas_helper(name) glue(gen_helper_,name)(a, a, b) case 2: PAS_OP(q); + instr_index = ARM_INSTRUCTION_QADD16; break; case 3: PAS_OP(sh); + instr_index = ARM_INSTRUCTION_SHADD16; break; case 6: PAS_OP(uq); + instr_index = ARM_INSTRUCTION_UQADD16; break; case 7: PAS_OP(uh); + instr_index = ARM_INSTRUCTION_UHADD16; break; #undef gen_pas_helper } + if (op2 == 7) instr_index += 5; + else instr_index += op2; + instr_count_inc(instr_index); } #undef PAS_OP @@ -2702,6 +3073,9 @@ static int disas_vfp_insn(CPUState * env TCGv tmp; TCGv tmp2; + instr_count_inc_init(ARM_VFP_INSTRUCTION_COUNTER_OFFSET, + ARM_VFP_INSTRUCTION_NOT_INSTRUMENTED); + if (!arm_feature(env, ARM_FEATURE_VFP)) return 1; @@ -2724,6 +3098,8 @@ static int disas_vfp_insn(CPUState * env int size; int pass; + instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN); + VFP_DREG_N(rn, insn); if (insn & 0xf) return 1; @@ -2770,6 +3146,11 @@ static int disas_vfp_insn(CPUState * env } break; case 2: + if (pass) { + instr_count_inc(ARM_VFP_INSTRUCTION_FMRDH); + } else { + instr_count_inc(ARM_VFP_INSTRUCTION_FMRDL); + } break; } store_reg(s, rd, tmp); @@ -2801,6 +3182,11 @@ static int disas_vfp_insn(CPUState * env dead_tmp(tmp2); break; case 2: + if (pass) { + instr_count_inc(ARM_VFP_INSTRUCTION_FMDHR); + } else { + instr_count_inc(ARM_VFP_INSTRUCTION_FMDLR); + } break; } neon_store_reg(rn, pass, tmp); @@ -2814,6 +3200,7 @@ static int disas_vfp_insn(CPUState * env /* vfp->arm */ if (insn & (1 << 21)) { /* system register */ + instr_count_inc(ARM_VFP_INSTRUCTION_FMRX); rn >>= 1; switch (rn) { @@ -2841,6 +3228,7 @@ static int disas_vfp_insn(CPUState * env break; case ARM_VFP_FPSCR: if (rd == 15) { + instr_count_inc(ARM_VFP_INSTRUCTION_FMSTAT); tmp = load_cpu_field(vfp.xregs[ARM_VFP_FPSCR]); tcg_gen_andi_i32(tmp, tmp, 0xf0000000); } else { @@ -2859,6 +3247,7 @@ static int disas_vfp_insn(CPUState * env return 1; } } else { + instr_count_inc(ARM_VFP_INSTRUCTION_FMRS); gen_mov_F0_vreg(0, rn); tmp = gen_vfp_mrs(); } @@ -2873,6 +3262,7 @@ static int disas_vfp_insn(CPUState * env /* arm->vfp */ tmp = load_reg(s, rd); if (insn & (1 << 21)) { + instr_count_inc(ARM_VFP_INSTRUCTION_FMXR); rn >>= 1; /* system register */ switch (rn) { @@ -2900,6 +3290,7 @@ static int disas_vfp_insn(CPUState * env return 1; } } else { + instr_count_inc(ARM_VFP_INSTRUCTION_FMSR); gen_vfp_msr(tmp); gen_mov_vreg_F0(0, rn); } @@ -3023,44 +3414,54 @@ static int disas_vfp_insn(CPUState * env /* Perform the calculation. */ switch (op) { case 0: /* mac: fd + (fn * fm) */ + instr_count_inc(ARM_VFP_INSTRUCTION_FMACD + (1 - dp)); gen_vfp_mul(dp); gen_mov_F1_vreg(dp, rd); gen_vfp_add(dp); break; case 1: /* nmac: fd - (fn * fm) */ + instr_count_inc(ARM_VFP_INSTRUCTION_FNMACD + (1 - dp)); gen_vfp_mul(dp); gen_vfp_neg(dp); gen_mov_F1_vreg(dp, rd); gen_vfp_add(dp); break; case 2: /* msc: -fd + (fn * fm) */ + instr_count_inc(ARM_VFP_INSTRUCTION_FMSCD + (1 - dp)); gen_vfp_mul(dp); gen_mov_F1_vreg(dp, rd); gen_vfp_sub(dp); break; case 3: /* nmsc: -fd - (fn * fm) */ + instr_count_inc(ARM_VFP_INSTRUCTION_FNMSCD + (1 - dp)); gen_vfp_mul(dp); gen_vfp_neg(dp); gen_mov_F1_vreg(dp, rd); gen_vfp_sub(dp); break; case 4: /* mul: fn * fm */ + instr_count_inc(ARM_VFP_INSTRUCTION_FMULD + (1 - dp)); gen_vfp_mul(dp); break; case 5: /* nmul: -(fn * fm) */ + instr_count_inc(ARM_VFP_INSTRUCTION_FNMULD + (1 - dp)); gen_vfp_mul(dp); gen_vfp_neg(dp); break; case 6: /* add: fn + fm */ + instr_count_inc(ARM_VFP_INSTRUCTION_FADDD + (1 - dp)); gen_vfp_add(dp); break; case 7: /* sub: fn - fm */ + instr_count_inc(ARM_VFP_INSTRUCTION_FSUBD + (1 - dp)); gen_vfp_sub(dp); break; case 8: /* div: fn / fm */ + instr_count_inc(ARM_VFP_INSTRUCTION_FDIVD + (1 - dp)); gen_vfp_div(dp); break; case 14: /* fconst */ + instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_VFP3)) return 1; @@ -3085,90 +3486,116 @@ static int disas_vfp_insn(CPUState * env case 15: /* extension space */ switch (rn) { case 0: /* cpy */ + instr_count_inc(ARM_VFP_INSTRUCTION_FCPYD + (1 - dp)); /* no-op */ break; case 1: /* abs */ + instr_count_inc(ARM_VFP_INSTRUCTION_FABSD + (1 - dp)); gen_vfp_abs(dp); break; case 2: /* neg */ + instr_count_inc(ARM_VFP_INSTRUCTION_FNEGD + (1 - dp)); gen_vfp_neg(dp); break; case 3: /* sqrt */ + instr_count_inc(ARM_VFP_INSTRUCTION_FSQRTD + (1 - dp)); gen_vfp_sqrt(dp); break; case 8: /* cmp */ + instr_count_inc(ARM_VFP_INSTRUCTION_FCMPD + (1 - dp)); gen_vfp_cmp(dp); break; case 9: /* cmpe */ + instr_count_inc(ARM_VFP_INSTRUCTION_FCMPED + (1 - dp)); gen_vfp_cmpe(dp); break; case 10: /* cmpz */ + instr_count_inc(ARM_VFP_INSTRUCTION_FCMPZD + (1 - dp)); gen_vfp_cmp(dp); break; case 11: /* cmpez */ + instr_count_inc(ARM_VFP_INSTRUCTION_FCMPEZD + (1 - dp)); gen_vfp_F1_ld0(dp); gen_vfp_cmpe(dp); break; case 15: /* single<->double conversion */ - if (dp) + if (dp) { + instr_count_inc(ARM_VFP_INSTRUCTION_FCVTSD); gen_helper_vfp_fcvtsd(cpu_F0s, cpu_F0d, cpu_env); - else + } + else { + instr_count_inc(ARM_VFP_INSTRUCTION_FCVTDS); gen_helper_vfp_fcvtds(cpu_F0d, cpu_F0s, cpu_env); + } break; case 16: /* fuito */ + instr_count_inc(ARM_VFP_INSTRUCTION_FUITOD + (1 - dp)); gen_vfp_uito(dp); break; case 17: /* fsito */ + instr_count_inc(ARM_VFP_INSTRUCTION_FSITOD + (1 - dp)); gen_vfp_sito(dp); break; case 20: /* fshto */ + instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_VFP3)) return 1; gen_vfp_shto(dp, 16 - rm); break; case 21: /* fslto */ + instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_VFP3)) return 1; gen_vfp_slto(dp, 32 - rm); break; case 22: /* fuhto */ + instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_VFP3)) return 1; gen_vfp_uhto(dp, 16 - rm); break; case 23: /* fulto */ + instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_VFP3)) return 1; gen_vfp_ulto(dp, 32 - rm); break; case 24: /* ftoui */ + instr_count_inc(ARM_VFP_INSTRUCTION_FTOUID + (1 - dp)); gen_vfp_toui(dp); break; case 25: /* ftouiz */ + instr_count_inc(ARM_VFP_INSTRUCTION_FTOUIZD + (1 - dp)); gen_vfp_touiz(dp); break; case 26: /* ftosi */ + instr_count_inc(ARM_VFP_INSTRUCTION_FTOSID + (1 - dp)); gen_vfp_tosi(dp); break; case 27: /* ftosiz */ + instr_count_inc(ARM_VFP_INSTRUCTION_FTOSIZD + (1 - dp)); gen_vfp_tosiz(dp); break; case 28: /* ftosh */ + instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_VFP3)) return 1; gen_vfp_tosh(dp, 16 - rm); break; case 29: /* ftosl */ + instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_VFP3)) return 1; gen_vfp_tosl(dp, 32 - rm); break; case 30: /* ftouh */ + instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_VFP3)) return 1; gen_vfp_touh(dp, 16 - rm); break; case 31: /* ftoul */ + instr_count_inc(ARM_VFP_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_VFP3)) return 1; gen_vfp_toul(dp, 32 - rm); @@ -3247,6 +3674,7 @@ static int disas_vfp_insn(CPUState * env if (insn & ARM_CP_RW_BIT) { /* vfp->arm */ if (dp) { + instr_count_inc(ARM_VFP_INSTRUCTION_FMRRD); gen_mov_F0_vreg(0, rm * 2); tmp = gen_vfp_mrs(); store_reg(s, rd, tmp); @@ -3254,6 +3682,7 @@ static int disas_vfp_insn(CPUState * env tmp = gen_vfp_mrs(); store_reg(s, rn, tmp); } else { + instr_count_inc(ARM_VFP_INSTRUCTION_FMRRS); gen_mov_F0_vreg(0, rm); tmp = gen_vfp_mrs(); store_reg(s, rn, tmp); @@ -3264,6 +3693,7 @@ static int disas_vfp_insn(CPUState * env } else { /* arm->vfp */ if (dp) { + instr_count_inc(ARM_VFP_INSTRUCTION_FMDRR); tmp = load_reg(s, rd); gen_vfp_msr(tmp); gen_mov_vreg_F0(0, rm * 2); @@ -3271,6 +3701,7 @@ static int disas_vfp_insn(CPUState * env gen_vfp_msr(tmp); gen_mov_vreg_F0(0, rm * 2 + 1); } else { + instr_count_inc(ARM_VFP_INSTRUCTION_FMSRR); tmp = load_reg(s, rn); gen_vfp_msr(tmp); gen_mov_vreg_F0(0, rm); @@ -3298,9 +3729,11 @@ static int disas_vfp_insn(CPUState * env offset = -offset; gen_op_addl_T1_im(offset); if (insn & (1 << 20)) { + instr_count_inc(ARM_VFP_INSTRUCTION_FLDD + (1 - dp)); gen_vfp_ld(s, dp); gen_mov_vreg_F0(dp, rd); } else { + instr_count_inc(ARM_VFP_INSTRUCTION_FSTD + (1 - dp)); gen_mov_F0_vreg(dp, rd); gen_vfp_st(s, dp); } @@ -3321,10 +3754,12 @@ static int disas_vfp_insn(CPUState * env for (i = 0; i < n; i++) { if (insn & ARM_CP_RW_BIT) { /* load */ + instr_count_inc(ARM_VFP_INSTRUCTION_FLDMD + (1 - dp)); gen_vfp_ld(s, dp); gen_mov_vreg_F0(dp, rd + i); } else { /* store */ + instr_count_inc(ARM_VFP_INSTRUCTION_FSTMD + (1 - dp)); gen_mov_F0_vreg(dp, rd + i); gen_vfp_st(s, dp); } @@ -5697,6 +6132,7 @@ static void gen_logicq_cc(TCGv_i64 val) static void disas_arm_insn(CPUState * env, DisasContext *s) { unsigned int cond, insn, val, op1, i, shift, rm, rs, rn, rd, sh; + unsigned int instr_index = 0; TCGv tmp; TCGv tmp2; TCGv tmp3; @@ -5706,14 +6142,18 @@ static void disas_arm_insn(CPUState * en insn = ldl_code(s->pc); s->pc += 4; + instr_count_inc_init(ARM_INSTRUCTION_COUNTER_OFFSET, + ARM_INSTRUCTION_NOT_INSTRUMENTED); + /* M variants do not implement ARM mode. */ if (IS_M(env)) goto illegal_op; cond = insn >> 28; - if (cond == 0xf){ + if (cond == 0xf) { /* Unconditional instructions. */ if (((insn >> 25) & 7) == 1) { /* NEON Data processing. */ + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_NEON)) goto illegal_op; @@ -5723,6 +6163,7 @@ static void disas_arm_insn(CPUState * en } if ((insn & 0x0f100000) == 0x04000000) { /* NEON load/store. */ + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); if (!arm_feature(env, ARM_FEATURE_NEON)) goto illegal_op; @@ -5734,6 +6175,7 @@ static void disas_arm_insn(CPUState * en return; /* PLD */ else if ((insn & 0x0ffffdff) == 0x01010000) { ARCH(6); + instr_count_inc(ARM_INSTRUCTION_SETEND); /* setend */ if (insn & (1 << 9)) { /* BE8 mode not implemented. */ @@ -5744,11 +6186,13 @@ static void disas_arm_insn(CPUState * en switch ((insn >> 4) & 0xf) { case 1: /* clrex */ ARCH(6K); + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); gen_helper_clrex(cpu_env); return; case 4: /* dsb */ case 5: /* dmb */ case 6: /* isb */ + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); ARCH(7); /* We don't emulate caches so these are a no-op. */ return; @@ -5758,6 +6202,7 @@ static void disas_arm_insn(CPUState * en } else if ((insn & 0x0e5fffe0) == 0x084d0500) { /* srs */ uint32_t offset; + instr_count_inc(ARM_INSTRUCTION_SRS); if (IS_USER(s)) goto illegal_op; ARCH(6); @@ -5808,6 +6253,7 @@ static void disas_arm_insn(CPUState * en uint32_t offset; if (IS_USER(s)) goto illegal_op; + instr_count_inc(ARM_INSTRUCTION_RFE); ARCH(6); rn = (insn >> 16) & 0xf; addr = load_reg(s, rn); @@ -5844,7 +6290,7 @@ static void disas_arm_insn(CPUState * en } else if ((insn & 0x0e000000) == 0x0a000000) { /* branch link and change to thumb (blx <offset>) */ int32_t offset; - + instr_count_inc(ARM_INSTRUCTION_BLX); val = (uint32_t)s->pc; tmp = new_tmp(); tcg_gen_movi_i32(tmp, val); @@ -5858,6 +6304,7 @@ static void disas_arm_insn(CPUState * en gen_bx_im(s, val); return; } else if ((insn & 0x0e000f00) == 0x0c000100) { + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); if (arm_feature(env, ARM_FEATURE_IWMMXT)) { /* iWMMXt register transfer. */ if (env->cp15.c15_cpar & (1 << 1)) @@ -5865,13 +6312,16 @@ static void disas_arm_insn(CPUState * en return; } } else if ((insn & 0x0fe00000) == 0x0c400000) { + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); /* Coprocessor double register transfer. */ } else if ((insn & 0x0f000010) == 0x0e000010) { + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); /* Additional coprocessor register transfer. */ } else if ((insn & 0x0ff10020) == 0x01000000) { uint32_t mask; uint32_t val; /* cps (privileged) */ + instr_count_inc(ARM_INSTRUCTION_CPS); if (IS_USER(s)) return; mask = val = 0; @@ -5911,10 +6361,12 @@ static void disas_arm_insn(CPUState * en val = ((insn >> 4) & 0xf000) | (insn & 0xfff); if ((insn & (1 << 22)) == 0) { /* MOVW */ + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); tmp = new_tmp(); tcg_gen_movi_i32(tmp, val); } else { /* MOVT */ + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); tmp = load_reg(s, rd); tcg_gen_ext16u_i32(tmp, tmp); tcg_gen_ori_i32(tmp, tmp, val << 16); @@ -5924,9 +6376,11 @@ static void disas_arm_insn(CPUState * en if (((insn >> 12) & 0xf) != 0xf) goto illegal_op; if (((insn >> 16) & 0xf) == 0) { + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); gen_nop_hint(s, insn & 0xff); } else { /* CPSR = immediate */ + instr_count_inc(ARM_INSTRUCTION_MSR); val = insn & 0xff; shift = ((insn >> 8) & 0xf) * 2; if (shift) @@ -5947,12 +6401,14 @@ static void disas_arm_insn(CPUState * en case 0x0: /* move program status register */ if (op1 & 1) { /* PSR = reg */ + instr_count_inc(ARM_INSTRUCTION_MSR); gen_movl_T0_reg(s, rm); i = ((op1 & 2) != 0); if (gen_set_psr_T0(s, msr_mask(env, s, (insn >> 16) & 0xf, i), i)) goto illegal_op; } else { /* reg = PSR */ + instr_count_inc(ARM_INSTRUCTION_MRS); rd = (insn >> 12) & 0xf; if (op1 & 2) { if (IS_USER(s)) @@ -5968,10 +6424,12 @@ static void disas_arm_insn(CPUState * en case 0x1: if (op1 == 1) { /* branch/exchange thumb (bx). */ + instr_count_inc(ARM_INSTRUCTION_BX); tmp = load_reg(s, rm); gen_bx(s, tmp); } else if (op1 == 3) { /* clz */ + instr_count_inc(ARM_INSTRUCTION_CLZ); rd = (insn >> 12) & 0xf; tmp = load_reg(s, rm); gen_helper_clz(tmp, tmp); @@ -5982,6 +6440,7 @@ static void disas_arm_insn(CPUState * en break; case 0x2: if (op1 == 1) { + instr_count_inc(ARM_INSTRUCTION_BXJ); ARCH(5J); /* bxj */ /* Trivial implementation equivalent to bx. */ tmp = load_reg(s, rm); @@ -5994,6 +6453,7 @@ static void disas_arm_insn(CPUState * en if (op1 != 1) goto illegal_op; + instr_count_inc(ARM_INSTRUCTION_BLX); /* branch link/exchange thumb (blx) */ tmp = load_reg(s, rm); tmp2 = new_tmp(); @@ -6006,16 +6466,24 @@ static void disas_arm_insn(CPUState * en rn = (insn >> 16) & 0xf; tmp = load_reg(s, rm); tmp2 = load_reg(s, rn); - if (op1 & 2) + if (op1 & 2) { gen_helper_double_saturate(tmp2, tmp2); - if (op1 & 1) + if (op1 & 1) instr_count_inc(ARM_INSTRUCTION_QDSUB); + else instr_count_inc(ARM_INSTRUCTION_QDADD); + } + if (op1 & 1) { gen_helper_sub_saturate(tmp, tmp, tmp2); - else + instr_count_inc(ARM_INSTRUCTION_QSUB); + } + else { gen_helper_add_saturate(tmp, tmp, tmp2); + instr_count_inc(ARM_INSTRUCTION_QADD); + } dead_tmp(tmp2); store_reg(s, rd, tmp); break; case 7: /* bkpt */ + instr_count_inc(ARM_INSTRUCTION_BKPT); gen_set_condexec(s); gen_set_pc_im(s->pc - 4); gen_exception(EXCP_BKPT); @@ -6041,18 +6509,22 @@ static void disas_arm_insn(CPUState * en tmp = new_tmp(); tcg_gen_trunc_i64_i32(tmp, tmp64); if ((sh & 2) == 0) { + instr_count_inc(ARM_INSTRUCTION_SMLAWY); tmp2 = load_reg(s, rn); gen_helper_add_setq(tmp, tmp, tmp2); dead_tmp(tmp2); } + else instr_count_inc(ARM_INSTRUCTION_SMULWY); store_reg(s, rd, tmp); } else { /* 16 * 16 */ + if (op1 == 3) instr_count_inc(ARM_INSTRUCTION_SMULXY); tmp = load_reg(s, rm); tmp2 = load_reg(s, rs); gen_mulxy(tmp, tmp2, sh & 2, sh & 4); dead_tmp(tmp2); if (op1 == 2) { + instr_count_inc(ARM_INSTRUCTION_SMLALXY); tmp64 = tcg_temp_new_i64(); tcg_gen_ext_i32_i64(tmp64, tmp); dead_tmp(tmp); @@ -6060,6 +6532,7 @@ static void disas_arm_insn(CPUState * en gen_storeq_reg(s, rn, rd, tmp64); } else { if (op1 == 0) { + instr_count_inc(ARM_INSTRUCTION_SMLAXY); tmp2 = load_reg(s, rn); gen_helper_add_setq(tmp, tmp, tmp2); dead_tmp(tmp2); @@ -6111,18 +6584,21 @@ static void disas_arm_insn(CPUState * en rd = (insn >> 12) & 0xf; switch(op1) { case 0x00: + instr_count_inc(ARM_INSTRUCTION_AND); gen_op_andl_T0_T1(); gen_movl_reg_T0(s, rd); if (logic_cc) gen_op_logic_T0_cc(); break; case 0x01: + instr_count_inc(ARM_INSTRUCTION_EOR); gen_op_xorl_T0_T1(); gen_movl_reg_T0(s, rd); if (logic_cc) gen_op_logic_T0_cc(); break; case 0x02: + instr_count_inc(ARM_INSTRUCTION_SUB); if (set_cc && rd == 15) { /* SUBS r15, ... is used for exception return. */ if (IS_USER(s)) @@ -6138,6 +6614,7 @@ static void disas_arm_insn(CPUState * en } break; case 0x03: + instr_count_inc(ARM_INSTRUCTION_RSB); if (set_cc) gen_op_rsbl_T0_T1_cc(); else @@ -6145,6 +6622,7 @@ static void disas_arm_insn(CPUState * en gen_movl_reg_T0(s, rd); break; case 0x04: + instr_count_inc(ARM_INSTRUCTION_ADD); if (set_cc) gen_op_addl_T0_T1_cc(); else @@ -6152,6 +6630,7 @@ static void disas_arm_insn(CPUState * en gen_movl_reg_T0(s, rd); break; case 0x05: + instr_count_inc(ARM_INSTRUCTION_ADC); if (set_cc) gen_op_adcl_T0_T1_cc(); else @@ -6159,6 +6638,7 @@ static void disas_arm_insn(CPUState * en gen_movl_reg_T0(s, rd); break; case 0x06: + instr_count_inc(ARM_INSTRUCTION_SBC); if (set_cc) gen_op_sbcl_T0_T1_cc(); else @@ -6166,6 +6646,7 @@ static void disas_arm_insn(CPUState * en gen_movl_reg_T0(s, rd); break; case 0x07: + instr_count_inc(ARM_INSTRUCTION_RSC); if (set_cc) gen_op_rscl_T0_T1_cc(); else @@ -6173,34 +6654,40 @@ static void disas_arm_insn(CPUState * en gen_movl_reg_T0(s, rd); break; case 0x08: + instr_count_inc(ARM_INSTRUCTION_TST); if (set_cc) { gen_op_andl_T0_T1(); gen_op_logic_T0_cc(); } break; case 0x09: + instr_count_inc(ARM_INSTRUCTION_TEQ); if (set_cc) { gen_op_xorl_T0_T1(); gen_op_logic_T0_cc(); } break; case 0x0a: + instr_count_inc(ARM_INSTRUCTION_CMP); if (set_cc) { gen_op_subl_T0_T1_cc(); } break; case 0x0b: + instr_count_inc(ARM_INSTRUCTION_CMN); if (set_cc) { gen_op_addl_T0_T1_cc(); } break; case 0x0c: + instr_count_inc(ARM_INSTRUCTION_ORR); gen_op_orl_T0_T1(); gen_movl_reg_T0(s, rd); if (logic_cc) gen_op_logic_T0_cc(); break; case 0x0d: + instr_count_inc(ARM_INSTRUCTION_MOV); if (logic_cc && rd == 15) { /* MOVS r15, ... is used for exception return. */ if (IS_USER(s)) @@ -6214,6 +6701,7 @@ static void disas_arm_insn(CPUState * en } break; case 0x0e: + instr_count_inc(ARM_INSTRUCTION_BIC); gen_op_bicl_T0_T1(); gen_movl_reg_T0(s, rd); if (logic_cc) @@ -6221,6 +6709,7 @@ static void disas_arm_insn(CPUState * en break; default: case 0x0f: + instr_count_inc(ARM_INSTRUCTION_MVN); gen_op_notl_T1(); gen_movl_reg_T1(s, rd); if (logic_cc) @@ -6245,43 +6734,63 @@ static void disas_arm_insn(CPUState * en switch (op1) { case 0: case 1: case 2: case 3: case 6: /* 32 bit mul */ + instr_index = ARM_INSTRUCTION_MUL; tmp = load_reg(s, rs); tmp2 = load_reg(s, rm); tcg_gen_mul_i32(tmp, tmp, tmp2); dead_tmp(tmp2); if (insn & (1 << 22)) { /* Subtract (mls) */ + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); ARCH(6T2); tmp2 = load_reg(s, rn); tcg_gen_sub_i32(tmp, tmp2, tmp); dead_tmp(tmp2); } else if (insn & (1 << 21)) { /* Add */ + instr_index = ARM_INSTRUCTION_MLA; tmp2 = load_reg(s, rn); tcg_gen_add_i32(tmp, tmp, tmp2); dead_tmp(tmp2); } - if (insn & (1 << 20)) + if (insn & (1 << 20)) { gen_logic_CC(tmp); + instr_index++; /* MULS and MLAS */ + } + instr_count_inc(instr_index); store_reg(s, rd, tmp); break; default: /* 64 bit mul */ tmp = load_reg(s, rs); tmp2 = load_reg(s, rm); - if (insn & (1 << 22)) + if (insn & (1 << 22)) { tmp64 = gen_muls_i64_i32(tmp, tmp2); - else + instr_index = ARM_INSTRUCTION_SMULL; + } + else { tmp64 = gen_mulu_i64_i32(tmp, tmp2); - if (insn & (1 << 21)) /* mult accumulate */ + instr_index = ARM_INSTRUCTION_UMULL; + } + if (insn & (1 << 21)) { + /* mult accumulate */ gen_addq(s, tmp64, rn, rd); + if (insn & (1 << 22)) { + instr_index = ARM_INSTRUCTION_SMLAL; + } else { + instr_index = ARM_INSTRUCTION_UMLAL; + } + } if (!(insn & (1 << 23))) { /* double accumulate */ ARCH(6); gen_addq_lo(s, tmp64, rn); gen_addq_lo(s, tmp64, rd); } - if (insn & (1 << 20)) + if (insn & (1 << 20)) { gen_logicq_cc(tmp64); + instr_index++; /* SMULLS, UMULLS, SMLALS, UMLALS */ + } + instr_count_inc(instr_index); gen_storeq_reg(s, rn, rd, tmp64); break; } @@ -6300,6 +6809,7 @@ static void disas_arm_insn(CPUState * en if (insn & (1 << 20)) { gen_helper_mark_exclusive(cpu_env, cpu_T[1]); switch (op1) { + instr_count_inc(ARM_INSTRUCTION_LDREX); case 0: /* ldrex */ tmp = gen_ld32(addr, IS_USER(s)); break; @@ -6327,6 +6837,7 @@ static void disas_arm_insn(CPUState * en tcg_gen_brcondi_i32(TCG_COND_NE, cpu_T[0], 0, label); tmp = load_reg(s,rm); + instr_count_inc(ARM_INSTRUCTION_STREX); switch (op1) { case 0: /* strex */ gen_st32(tmp, addr, IS_USER(s)); @@ -6359,9 +6870,11 @@ static void disas_arm_insn(CPUState * en addr = load_reg(s, rn); tmp = load_reg(s, rm); if (insn & (1 << 22)) { + instr_count_inc(ARM_INSTRUCTION_SWPB); tmp2 = gen_ld8u(addr, IS_USER(s)); gen_st8(tmp, addr, IS_USER(s)); } else { + instr_count_inc(ARM_INSTRUCTION_SWP); tmp2 = gen_ld32(addr, IS_USER(s)); gen_st32(tmp, addr, IS_USER(s)); } @@ -6383,13 +6896,16 @@ static void disas_arm_insn(CPUState * en /* load */ switch(sh) { case 1: + instr_count_inc(ARM_INSTRUCTION_LDRH); tmp = gen_ld16u(addr, IS_USER(s)); break; case 2: + instr_count_inc(ARM_INSTRUCTION_LDRSB); tmp = gen_ld8s(addr, IS_USER(s)); break; default: case 3: + instr_count_inc(ARM_INSTRUCTION_LDRSH); tmp = gen_ld16s(addr, IS_USER(s)); break; } @@ -6398,6 +6914,7 @@ static void disas_arm_insn(CPUState * en /* doubleword */ if (sh & 1) { /* store */ + instr_count_inc(ARM_INSTRUCTION_STRD); tmp = load_reg(s, rd); gen_st32(tmp, addr, IS_USER(s)); tcg_gen_addi_i32(addr, addr, 4); @@ -6406,6 +6923,7 @@ static void disas_arm_insn(CPUState * en load = 0; } else { /* load */ + instr_count_inc(ARM_INSTRUCTION_LDRD); tmp = gen_ld32(addr, IS_USER(s)); store_reg(s, rd, tmp); tcg_gen_addi_i32(addr, addr, 4); @@ -6417,6 +6935,7 @@ static void disas_arm_insn(CPUState * en } else { /* store */ tmp = load_reg(s, rd); + instr_count_inc(ARM_INSTRUCTION_STRH); gen_st16(tmp, addr, IS_USER(s)); load = 0; } @@ -6454,6 +6973,7 @@ static void disas_arm_insn(CPUState * en rs = (insn >> 8) & 0xf; switch ((insn >> 23) & 3) { case 0: /* Parallel add/subtract. */ + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); op1 = (insn >> 20) & 7; tmp = load_reg(s, rn); tmp2 = load_reg(s, rm); @@ -6472,6 +6992,7 @@ static void disas_arm_insn(CPUState * en shift = (insn >> 7) & 0x1f; if (insn & (1 << 6)) { /* pkhtb */ + instr_count_inc(ARM_INSTRUCTION_PKHTB); if (shift == 0) shift = 31; tcg_gen_sari_i32(tmp2, tmp2, shift); @@ -6479,6 +7000,7 @@ static void disas_arm_insn(CPUState * en tcg_gen_ext16u_i32(tmp2, tmp2); } else { /* pkhbt */ + instr_count_inc(ARM_INSTRUCTION_PKHBT); if (shift) tcg_gen_shli_i32(tmp2, tmp2, shift); tcg_gen_ext16u_i32(tmp, tmp); @@ -6500,10 +7022,14 @@ static void disas_arm_insn(CPUState * en } sh = (insn >> 16) & 0x1f; if (sh != 0) { - if (insn & (1 << 22)) + if (insn & (1 << 22)) { + instr_count_inc(ARM_INSTRUCTION_USAT); gen_helper_usat(tmp, tmp, tcg_const_i32(sh)); - else + } + else { + instr_count_inc(ARM_INSTRUCTION_SSAT); gen_helper_ssat(tmp, tmp, tcg_const_i32(sh)); + } } store_reg(s, rd, tmp); } else if ((insn & 0x00300fe0) == 0x00200f20) { @@ -6511,14 +7037,19 @@ static void disas_arm_insn(CPUState * en tmp = load_reg(s, rm); sh = (insn >> 16) & 0x1f; if (sh != 0) { - if (insn & (1 << 22)) + if (insn & (1 << 22)) { + instr_count_inc(ARM_INSTRUCTION_USAT16); gen_helper_usat16(tmp, tmp, tcg_const_i32(sh)); - else + } + else { + instr_count_inc(ARM_INSTRUCTION_SSAT16); gen_helper_ssat16(tmp, tmp, tcg_const_i32(sh)); + } } store_reg(s, rd, tmp); } else if ((insn & 0x00700fe0) == 0x00000fa0) { /* Select bytes. */ + instr_count_inc(ARM_INSTRUCTION_SEL); tmp = load_reg(s, rn); tmp2 = load_reg(s, rm); tmp3 = new_tmp(); @@ -6536,12 +7067,30 @@ static void disas_arm_insn(CPUState * en tcg_gen_rori_i32(tmp, tmp, shift * 8); op1 = (insn >> 20) & 7; switch (op1) { - case 0: gen_sxtb16(tmp); break; - case 2: gen_sxtb(tmp); break; - case 3: gen_sxth(tmp); break; - case 4: gen_uxtb16(tmp); break; - case 6: gen_uxtb(tmp); break; - case 7: gen_uxth(tmp); break; + case 0: + instr_index = ARM_INSTRUCTION_SXTB16; + gen_sxtb16(tmp); + break; + case 2: + instr_index = ARM_INSTRUCTION_SXTB; + gen_sxtb(tmp); + break; + case 3: + instr_index = ARM_INSTRUCTION_SXTH; + gen_sxth(tmp); + break; + case 4: + instr_index = ARM_INSTRUCTION_UXTB16; + gen_uxtb16(tmp); + break; + case 6: + instr_index = ARM_INSTRUCTION_UXTB; + gen_uxtb(tmp); + break; + case 7: + instr_index = ARM_INSTRUCTION_UXTH; + gen_uxth(tmp); + break; default: goto illegal_op; } if (rn != 15) { @@ -6552,23 +7101,30 @@ static void disas_arm_insn(CPUState * en tcg_gen_add_i32(tmp, tmp, tmp2); dead_tmp(tmp2); } + instr_index -= 3; /* add variants */ } + instr_count_inc(instr_index); store_reg(s, rd, tmp); } else if ((insn & 0x003f0f60) == 0x003f0f20) { /* rev */ tmp = load_reg(s, rm); if (insn & (1 << 22)) { if (insn & (1 << 7)) { + instr_count_inc(ARM_INSTRUCTION_REVSH); gen_revsh(tmp); } else { ARCH(6T2); gen_helper_rbit(tmp, tmp); } } else { - if (insn & (1 << 7)) + if (insn & (1 << 7)) { + instr_count_inc(ARM_INSTRUCTION_REV16); gen_rev16(tmp); - else + } + else { + instr_count_inc(ARM_INSTRUCTION_REV); tcg_gen_bswap_i32(tmp, tmp); + } } store_reg(s, rd, tmp); } else { @@ -6590,11 +7146,16 @@ static void disas_arm_insn(CPUState * en tmp2 = load_reg(s, rd); if (insn & (1 << 6)) { tcg_gen_sub_i32(tmp, tmp, tmp2); + instr_count_inc(ARM_INSTRUCTION_SMMLS); } else { tcg_gen_add_i32(tmp, tmp, tmp2); + instr_count_inc(ARM_INSTRUCTION_SMMLA); } dead_tmp(tmp2); } + else { + instr_count_inc(ARM_INSTRUCTION_SMMUL); + } store_reg(s, rn, tmp); } else { if (insn & (1 << 5)) @@ -6603,8 +7164,10 @@ static void disas_arm_insn(CPUState * en /* This addition cannot overflow. */ if (insn & (1 << 6)) { tcg_gen_sub_i32(tmp, tmp, tmp2); + instr_index = 1; } else { tcg_gen_add_i32(tmp, tmp, tmp2); + instr_index = 0; } dead_tmp(tmp2); if (insn & (1 << 22)) { @@ -6614,6 +7177,8 @@ static void disas_arm_insn(CPUState * en dead_tmp(tmp); gen_addq(s, tmp64, rd, rn); gen_storeq_reg(s, rd, rn, tmp64); + instr_index += ARM_INSTRUCTION_SMLALD; + instr_count_inc(instr_index); } else { /* smuad, smusd, smlad, smlsd */ if (rd != 15) @@ -6621,8 +7186,11 @@ static void disas_arm_insn(CPUState * en tmp2 = load_reg(s, rd); gen_helper_add_setq(tmp, tmp, tmp2); dead_tmp(tmp2); + instr_index += 2; /* SMLAD, SMLSD */ } store_reg(s, rn, tmp); + instr_index += ARM_INSTRUCTION_SMUAD; + instr_count_inc(instr_index); } } break; @@ -6639,12 +7207,15 @@ static void disas_arm_insn(CPUState * en tmp2 = load_reg(s, rd); tcg_gen_add_i32(tmp, tmp, tmp2); dead_tmp(tmp2); + instr_count_inc(ARM_INSTRUCTION_USADA8); } + else instr_count_inc(ARM_INSTRUCTION_USAD8); store_reg(s, rn, tmp); break; case 0x20: case 0x24: case 0x28: case 0x2c: /* Bitfield insert/clear. */ ARCH(6T2); + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); shift = (insn >> 7) & 0x1f; i = (insn >> 16) & 0x1f; i = i + 1 - shift; @@ -6664,6 +7235,7 @@ static void disas_arm_insn(CPUState * en case 0x12: case 0x16: case 0x1a: case 0x1e: /* sbfx */ case 0x32: case 0x36: case 0x3a: case 0x3e: /* ubfx */ ARCH(6T2); + instr_count_inc(ARM_INSTRUCTION_UNKNOWN); tmp = load_reg(s, rm); shift = (insn >> 7) & 0x1f; i = ((insn >> 16) & 0x1f) + 1; @@ -6705,17 +7277,23 @@ static void disas_arm_insn(CPUState * en if (insn & (1 << 20)) { /* load */ if (insn & (1 << 22)) { + instr_count_inc(ARM_INSTRUCTION_LDRB); tmp = gen_ld8u(tmp2, i); } else { + instr_count_inc(ARM_INSTRUCTION_LDR); tmp = gen_ld32(tmp2, i); } } else { /* store */ tmp = load_reg(s, rd); - if (insn & (1 << 22)) + if (insn & (1 << 22)) { + instr_count_inc(ARM_INSTRUCTION_STRB); gen_st8(tmp, tmp2, i); - else + } + else { + instr_count_inc(ARM_INSTRUCTION_STR); gen_st32(tmp, tmp2, i); + } } if (!(insn & (1 << 24))) { gen_add_data_offset(s, insn, tmp2); @@ -6740,6 +7318,18 @@ static void disas_arm_insn(CPUState * en TCGv loaded_var; /* load/store multiple words */ /* XXX: store correct base if write back */ + switch (insn & 0x00500000 >> 20) { + case 0x0: instr_count_inc(ARM_INSTRUCTION_STM1); break; + case 0x1: instr_count_inc(ARM_INSTRUCTION_LDM1); break; + case 0x4: instr_count_inc(ARM_INSTRUCTION_STM2); break; + case 0x5: + if (insn & (1 << 15)) { + instr_count_inc(ARM_INSTRUCTION_LDM3); + } else { + instr_count_inc(ARM_INSTRUCTION_LDM2); + } + break; + } user = 0; if (insn & (1 << 22)) { if (IS_USER(s)) @@ -6854,14 +7444,15 @@ static void disas_arm_insn(CPUState * en case 0xb: { int32_t offset; - /* branch (and link) */ val = (int32_t)s->pc; if (insn & (1 << 24)) { + instr_count_inc(ARM_INSTRUCTION_B); tmp = new_tmp(); tcg_gen_movi_i32(tmp, val); store_reg(s, 14, tmp); } + else instr_count_inc(ARM_INSTRUCTION_B); offset = (((int32_t)insn << 8) >> 8); val += (offset << 2) + 4; gen_jmp(s, val); @@ -6871,11 +7462,13 @@ static void disas_arm_insn(CPUState * en case 0xd: case 0xe: /* Coprocessor. */ + instr_count_inc(ARM_INSTRUCTION_COPROCESSOR); if (disas_coproc_insn(env, s, insn)) goto illegal_op; break; case 0xf: /* swi */ + instr_count_inc(ARM_INSTRUCTION_SWI); gen_set_pc_im(s->pc); s->is_jmp = DISAS_SWI; break; @@ -6988,6 +7581,9 @@ static int disas_thumb2_insn(CPUState *e int conds; int logic_cc; + instr_count_inc_init(ARM_THUMB_INSTRUCTION_COUNTER_OFFSET, + ARM_THUMB_INSTRUCTION_NOT_INSTRUMENTED); + if (!(arm_feature(env, ARM_FEATURE_THUMB2) || arm_feature (env, ARM_FEATURE_M))) { /* Thumb-1 cores may need to treat bl and blx as a pair of @@ -7601,10 +8197,12 @@ static int disas_thumb2_insn(CPUState *e if (insn & (1 << 12)) { /* b/bl */ gen_jmp(s, offset); + instr_count_inc(ARM_THUMB_INSTRUCTION_BL); } else { /* blx */ offset &= ~(uint32_t)2; gen_bx_im(s, offset); + instr_count_inc(ARM_THUMB_INSTRUCTION_BLX1); } } else if (((insn >> 23) & 7) == 7) { /* Misc control */ @@ -7995,13 +8593,19 @@ illegal_op: static void disas_thumb_insn(CPUState *env, DisasContext *s) { - uint32_t val, insn, op, rm, rn, rd, shift, cond; + uint32_t val, insn, op, rm, rn, rd, shift, cond, instr_index; int32_t offset; int i; TCGv tmp; TCGv tmp2; TCGv addr; + instr_index = 0; + + instr_count_inc_init(ARM_THUMB_INSTRUCTION_COUNTER_OFFSET, + ARM_THUMB_INSTRUCTION_NOT_INSTRUMENTED); + + if (s->condexec_mask) { cond = s->condexec_cond; s->condlabel = gen_new_label(); @@ -8022,18 +8626,26 @@ static void disas_thumb_insn(CPUState *e gen_movl_T0_reg(s, rn); if (insn & (1 << 10)) { /* immediate */ + instr_index = 0; gen_op_movl_T1_im((insn >> 6) & 7); } else { /* reg */ + instr_index = 2; /* ADD3 / SUB3 */ rm = (insn >> 6) & 7; gen_movl_T1_reg(s, rm); } if (insn & (1 << 9)) { + instr_count_inc(ARM_THUMB_INSTRUCTION_SUB1 + instr_index); if (s->condexec_mask) gen_op_subl_T0_T1(); else gen_op_subl_T0_T1_cc(); } else { + if ((insn >> 6) & 7) { + instr_count_inc(ARM_THUMB_INSTRUCTION_ADD1 + instr_index); + } else { + instr_count_inc(ARM_THUMB_INSTRUCTION_MOV2); + } if (s->condexec_mask) gen_op_addl_T0_T1(); else @@ -8042,6 +8654,17 @@ static void disas_thumb_insn(CPUState *e gen_movl_reg_T0(s, rd); } else { /* shift immediate */ + switch (op) { + case 0x0: + instr_count_inc(ARM_THUMB_INSTRUCTION_LSL1); + break; + case 0x1: + instr_count_inc(ARM_THUMB_INSTRUCTION_LSR1); + break; + case 0x2: + instr_count_inc(ARM_THUMB_INSTRUCTION_ASR1); + break; + } rm = (insn >> 3) & 7; shift = (insn >> 6) & 0x1f; tmp = load_reg(s, rm); @@ -8063,19 +8686,23 @@ static void disas_thumb_insn(CPUState *e } switch (op) { case 0: /* mov */ + instr_count_inc(ARM_THUMB_INSTRUCTION_MOV1); if (!s->condexec_mask) gen_op_logic_T0_cc(); break; case 1: /* cmp */ + instr_count_inc(ARM_THUMB_INSTRUCTION_CMP1); gen_op_subl_T0_T1_cc(); break; case 2: /* add */ + instr_count_inc(ARM_THUMB_INSTRUCTION_ADD2); if (s->condexec_mask) gen_op_addl_T0_T1(); else gen_op_addl_T0_T1_cc(); break; case 3: /* sub */ + instr_count_inc(ARM_THUMB_INSTRUCTION_SUB2); if (s->condexec_mask) gen_op_subl_T0_T1(); else @@ -8087,6 +8714,7 @@ static void disas_thumb_insn(CPUState *e break; case 4: if (insn & (1 << 11)) { + instr_count_inc(ARM_THUMB_INSTRUCTION_LDR3); rd = (insn >> 8) & 7; /* load pc-relative. Bit 1 of PC is ignored. */ val = s->pc + 2 + ((insn & 0xff) * 4); @@ -8105,23 +8733,28 @@ static void disas_thumb_insn(CPUState *e op = (insn >> 8) & 3; switch (op) { case 0: /* add */ + instr_count_inc(ARM_THUMB_INSTRUCTION_ADD4); gen_movl_T0_reg(s, rd); gen_movl_T1_reg(s, rm); gen_op_addl_T0_T1(); gen_movl_reg_T0(s, rd); break; case 1: /* cmp */ + instr_count_inc(ARM_THUMB_INSTRUCTION_CMP3); gen_movl_T0_reg(s, rd); gen_movl_T1_reg(s, rm); gen_op_subl_T0_T1_cc(); break; case 2: /* mov/cpy */ + instr_count_inc(ARM_THUMB_INSTRUCTION_MOV3); gen_movl_T0_reg(s, rm); gen_movl_reg_T0(s, rd); break; case 3:/* branch [and link] exchange thumb register */ + instr_count_inc(ARM_THUMB_INSTRUCTION_BX); tmp = load_reg(s, rm); if (insn & (1 << 7)) { + instr_count_inc(ARM_THUMB_INSTRUCTION_BLX2); val = (uint32_t)s->pc | 1; tmp2 = new_tmp(); tcg_gen_movi_i32(tmp2, val); @@ -8155,16 +8788,19 @@ static void disas_thumb_insn(CPUState *e gen_movl_T1_reg(s, rm); switch (op) { case 0x0: /* and */ + instr_count_inc(ARM_THUMB_INSTRUCTION_AND); gen_op_andl_T0_T1(); if (!s->condexec_mask) gen_op_logic_T0_cc(); break; case 0x1: /* eor */ + instr_count_inc(ARM_THUMB_INSTRUCTION_EOR); gen_op_xorl_T0_T1(); if (!s->condexec_mask) gen_op_logic_T0_cc(); break; case 0x2: /* lsl */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LSL2); if (s->condexec_mask) { gen_helper_shl(cpu_T[1], cpu_T[1], cpu_T[0]); } else { @@ -8173,6 +8809,7 @@ static void disas_thumb_insn(CPUState *e } break; case 0x3: /* lsr */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LSR2); if (s->condexec_mask) { gen_helper_shr(cpu_T[1], cpu_T[1], cpu_T[0]); } else { @@ -8181,6 +8818,7 @@ static void disas_thumb_insn(CPUState *e } break; case 0x4: /* asr */ + instr_count_inc(ARM_THUMB_INSTRUCTION_ASR2); if (s->condexec_mask) { gen_helper_sar(cpu_T[1], cpu_T[1], cpu_T[0]); } else { @@ -8189,18 +8827,21 @@ static void disas_thumb_insn(CPUState *e } break; case 0x5: /* adc */ + instr_count_inc(ARM_THUMB_INSTRUCTION_ADC); if (s->condexec_mask) gen_adc_T0_T1(); else gen_op_adcl_T0_T1_cc(); break; case 0x6: /* sbc */ + instr_count_inc(ARM_THUMB_INSTRUCTION_SBC); if (s->condexec_mask) gen_sbc_T0_T1(); else gen_op_sbcl_T0_T1_cc(); break; case 0x7: /* ror */ + instr_count_inc(ARM_THUMB_INSTRUCTION_ROR); if (s->condexec_mask) { gen_helper_ror(cpu_T[1], cpu_T[1], cpu_T[0]); } else { @@ -8209,40 +8850,48 @@ static void disas_thumb_insn(CPUState *e } break; case 0x8: /* tst */ + instr_count_inc(ARM_THUMB_INSTRUCTION_TST); gen_op_andl_T0_T1(); gen_op_logic_T0_cc(); rd = 16; break; case 0x9: /* neg */ + instr_count_inc(ARM_THUMB_INSTRUCTION_NEG); if (s->condexec_mask) tcg_gen_neg_i32(cpu_T[0], cpu_T[1]); else gen_op_subl_T0_T1_cc(); break; case 0xa: /* cmp */ + instr_count_inc(ARM_THUMB_INSTRUCTION_CMP2); gen_op_subl_T0_T1_cc(); rd = 16; break; case 0xb: /* cmn */ + instr_count_inc(ARM_THUMB_INSTRUCTION_CMN); gen_op_addl_T0_T1_cc(); rd = 16; break; case 0xc: /* orr */ + instr_count_inc(ARM_THUMB_INSTRUCTION_ORR); gen_op_orl_T0_T1(); if (!s->condexec_mask) gen_op_logic_T0_cc(); break; case 0xd: /* mul */ + instr_count_inc(ARM_THUMB_INSTRUCTION_MUL); gen_op_mull_T0_T1(); if (!s->condexec_mask) gen_op_logic_T0_cc(); break; case 0xe: /* bic */ + instr_count_inc(ARM_THUMB_INSTRUCTION_BIC); gen_op_bicl_T0_T1(); if (!s->condexec_mask) gen_op_logic_T0_cc(); break; case 0xf: /* mvn */ + instr_count_inc(ARM_THUMB_INSTRUCTION_MVN); gen_op_notl_T1(); if (!s->condexec_mask) gen_op_logic_T1_cc(); @@ -8274,27 +8923,35 @@ static void disas_thumb_insn(CPUState *e switch (op) { case 0: /* str */ + instr_count_inc(ARM_THUMB_INSTRUCTION_STR2); gen_st32(tmp, addr, IS_USER(s)); break; case 1: /* strh */ + instr_count_inc(ARM_THUMB_INSTRUCTION_STRH2); gen_st16(tmp, addr, IS_USER(s)); break; case 2: /* strb */ + instr_count_inc(ARM_THUMB_INSTRUCTION_STRB2); gen_st8(tmp, addr, IS_USER(s)); break; case 3: /* ldrsb */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LDRSB); tmp = gen_ld8s(addr, IS_USER(s)); break; case 4: /* ldr */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LDR2); tmp = gen_ld32(addr, IS_USER(s)); break; case 5: /* ldrh */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LDRH2); tmp = gen_ld16u(addr, IS_USER(s)); break; case 6: /* ldrb */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LDRB2); tmp = gen_ld8u(addr, IS_USER(s)); break; case 7: /* ldrsh */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LDRSH); tmp = gen_ld16s(addr, IS_USER(s)); break; } @@ -8313,10 +8970,12 @@ static void disas_thumb_insn(CPUState *e if (insn & (1 << 11)) { /* load */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LDR1); tmp = gen_ld32(addr, IS_USER(s)); store_reg(s, rd, tmp); } else { /* store */ + instr_count_inc(ARM_THUMB_INSTRUCTION_STR1); tmp = load_reg(s, rd); gen_st32(tmp, addr, IS_USER(s)); } @@ -8333,10 +8992,12 @@ static void disas_thumb_insn(CPUState *e if (insn & (1 << 11)) { /* load */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LDRB1); tmp = gen_ld8u(addr, IS_USER(s)); store_reg(s, rd, tmp); } else { /* store */ + instr_count_inc(ARM_THUMB_INSTRUCTION_STRB1); tmp = load_reg(s, rd); gen_st8(tmp, addr, IS_USER(s)); } @@ -8353,10 +9014,12 @@ static void disas_thumb_insn(CPUState *e if (insn & (1 << 11)) { /* load */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LDRH1); tmp = gen_ld16u(addr, IS_USER(s)); store_reg(s, rd, tmp); } else { /* store */ + instr_count_inc(ARM_THUMB_INSTRUCTION_STRH1); tmp = load_reg(s, rd); gen_st16(tmp, addr, IS_USER(s)); } @@ -8372,10 +9035,12 @@ static void disas_thumb_insn(CPUState *e if (insn & (1 << 11)) { /* load */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LDR4); tmp = gen_ld32(addr, IS_USER(s)); store_reg(s, rd, tmp); } else { /* store */ + instr_count_inc(ARM_THUMB_INSTRUCTION_STR3); tmp = load_reg(s, rd); gen_st32(tmp, addr, IS_USER(s)); } @@ -8387,9 +9052,11 @@ static void disas_thumb_insn(CPUState *e rd = (insn >> 8) & 7; if (insn & (1 << 11)) { /* SP */ + instr_count_inc(ARM_THUMB_INSTRUCTION_ADD6); tmp = load_reg(s, 13); } else { /* PC. bit 1 is ignored. */ + instr_count_inc(ARM_THUMB_INSTRUCTION_ADD5); tmp = new_tmp(); tcg_gen_movi_i32(tmp, (s->pc + 2) & ~(uint32_t)2); } @@ -8406,8 +9073,11 @@ static void disas_thumb_insn(CPUState *e /* adjust stack pointer */ tmp = load_reg(s, 13); val = (insn & 0x7f) * 4; - if (insn & (1 << 7)) + if (insn & (1 << 7)) { + instr_count_inc(ARM_THUMB_INSTRUCTION_ADD7); val = -(int32_t)val; + } + else instr_count_inc(ARM_THUMB_INSTRUCTION_SUB4); tcg_gen_addi_i32(tmp, tmp, val); store_reg(s, 13, tmp); break; @@ -8418,10 +9088,22 @@ static void disas_thumb_insn(CPUState *e rm = (insn >> 3) & 7; tmp = load_reg(s, rm); switch ((insn >> 6) & 3) { - case 0: gen_sxth(tmp); break; - case 1: gen_sxtb(tmp); break; - case 2: gen_uxth(tmp); break; - case 3: gen_uxtb(tmp); break; + case 0: + instr_count_inc(ARM_THUMB_INSTRUCTION_SXTH); + gen_sxth(tmp); + break; + case 1: + instr_count_inc(ARM_THUMB_INSTRUCTION_SXTB); + gen_sxtb(tmp); + break; + case 2: + instr_count_inc(ARM_THUMB_INSTRUCTION_UXTH); + gen_uxth(tmp); + break; + case 3: + instr_count_inc(ARM_THUMB_INSTRUCTION_UXTB); + gen_uxtb(tmp); + break; } store_reg(s, rd, tmp); break; @@ -8443,10 +9125,12 @@ static void disas_thumb_insn(CPUState *e if (insn & (1 << i)) { if (insn & (1 << 11)) { /* pop */ + instr_count_inc(ARM_THUMB_INSTRUCTION_POP); tmp = gen_ld32(addr, IS_USER(s)); store_reg(s, i, tmp); } else { /* push */ + instr_count_inc(ARM_THUMB_INSTRUCTION_PUSH); tmp = load_reg(s, i); gen_st32(tmp, addr, IS_USER(s)); } @@ -8458,11 +9142,13 @@ static void disas_thumb_insn(CPUState *e if (insn & (1 << 8)) { if (insn & (1 << 11)) { /* pop pc */ + instr_count_inc(ARM_THUMB_INSTRUCTION_POP); tmp = gen_ld32(addr, IS_USER(s)); /* don't set the pc until the rest of the instruction has completed */ } else { /* push lr */ + instr_count_inc(ARM_THUMB_INSTRUCTION_PUSH); tmp = load_reg(s, 14); gen_st32(tmp, addr, IS_USER(s)); } @@ -8506,6 +9192,7 @@ static void disas_thumb_insn(CPUState *e break; case 0xe: /* bkpt */ + instr_count_inc(ARM_THUMB_INSTRUCTION_BKPT); gen_set_condexec(s); gen_set_pc_im(s->pc - 2); gen_exception(EXCP_BKPT); @@ -8518,15 +9205,25 @@ static void disas_thumb_insn(CPUState *e rd = insn & 0x7; tmp = load_reg(s, rn); switch ((insn >> 6) & 3) { - case 0: tcg_gen_bswap_i32(tmp, tmp); break; - case 1: gen_rev16(tmp); break; - case 3: gen_revsh(tmp); break; + case 0: + instr_count_inc(ARM_THUMB_INSTRUCTION_REV); + tcg_gen_bswap_i32(tmp, tmp); + break; + case 1: + instr_count_inc(ARM_THUMB_INSTRUCTION_REV16); + gen_rev16(tmp); + break; + case 3: + instr_count_inc(ARM_THUMB_INSTRUCTION_REVSH); + gen_revsh(tmp); + break; default: goto illegal_op; } store_reg(s, rd, tmp); break; case 6: /* cps */ + instr_count_inc(ARM_THUMB_INSTRUCTION_CPS); ARCH(6); if (IS_USER(s)) break; @@ -8568,10 +9265,12 @@ static void disas_thumb_insn(CPUState *e if (insn & (1 << i)) { if (insn & (1 << 11)) { /* load */ + instr_count_inc(ARM_THUMB_INSTRUCTION_LDMIA); tmp = gen_ld32(addr, IS_USER(s)); store_reg(s, i, tmp); } else { /* store */ + instr_count_inc(ARM_THUMB_INSTRUCTION_STMIA); tmp = load_reg(s, i); gen_st32(tmp, addr, IS_USER(s)); } @@ -8595,6 +9294,7 @@ static void disas_thumb_insn(CPUState *e if (cond == 0xf) { /* swi */ + instr_count_inc(ARM_THUMB_INSTRUCTION_SWI); gen_set_condexec(s); gen_set_pc_im(s->pc); s->is_jmp = DISAS_SWI; @@ -8607,6 +9307,7 @@ static void disas_thumb_insn(CPUState *e gen_movl_T1_reg(s, 15); /* jump to the offset */ + instr_count_inc(ARM_THUMB_INSTRUCTION_B1); val = (uint32_t)s->pc + 2; offset = ((int32_t)insn << 24) >> 24; val += offset << 1; @@ -8615,11 +9316,14 @@ static void disas_thumb_insn(CPUState *e case 14: if (insn & (1 << 11)) { + printf("BLX1\n"); + instr_count_inc(ARM_THUMB_INSTRUCTION_BLX1); if (disas_thumb2_insn(env, s, insn)) goto undef32; break; } /* unconditional branch */ + instr_count_inc(ARM_THUMB_INSTRUCTION_B2); val = (uint32_t)s->pc; offset = ((int32_t)insn << 21) >> 21; val += (offset << 1) + 2; @@ -8627,6 +9331,11 @@ static void disas_thumb_insn(CPUState *e break; case 15: + if (insn & (1 << 11)) { + instr_count_inc(ARM_THUMB_INSTRUCTION_BL); + } else { + instr_count_inc(ARM_THUMB_INSTRUCTION_BL_BLX_HIGH_PART); + } if (disas_thumb2_insn(env, s, insn)) goto undef32; break; ^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2009-06-29 8:43 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2009-06-12 10:56 [Qemu-devel] [PATCH] Instruction counting instrumentation for ARM, 2nd version Sami Kiminki
2009-06-12 15:41 ` Jamie Lokier
2009-06-15 8:12 ` Sami Kiminki
2009-06-15 13:26 ` Laurent Desnogues
2009-06-29 8:42 ` [Qemu-devel] [PATCH] Instruction counting instrumentation for ARM v3 Sami Kiminki
[not found] ` <761ea48b0906150531j6cf88fa2v5652322efcc7469c@mail.gmail.com>
2009-06-15 13:31 ` [Qemu-devel] [PATCH] Instruction counting instrumentation for ARM, 2nd version & 2nd try Sami Kiminki
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).