summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-01-30 22:15:14 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2018-01-30 22:15:14 +0300
commitd8b91dde38f4c43bd0bbbf17a90f735b16aaff2c (patch)
treebd72dabf6e4b23e060fce429c87e60504f69de54 /arch
parent5e7481a25e90b661d1dbbba18be3fd3dfe12ec6f (diff)
parente4c1091cb495d9cbec8956d642644a71a1689958 (diff)
downloadlinux-d8b91dde38f4c43bd0bbbf17a90f735b16aaff2c.tar.xz
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Ingo Molnar: "Kernel side changes: - Clean up the x86 instruction decoder (Masami Hiramatsu) - Add new uprobes optimization for PUSH instructions on x86 (Yonghong Song) - Add MSR_IA32_THERM_STATUS to the MSR events (Stephane Eranian) - Fix misc bugs, update documentation, plus various cleanups (Jiri Olsa) There's a large number of tooling side improvements: - Intel-PT/BTS improvements (Adrian Hunter) - Numerous 'perf trace' improvements (Arnaldo Carvalho de Melo) - Introduce an errno code to string facility (Hendrik Brueckner) - Various build system improvements (Jiri Olsa) - Add support for CoreSight trace decoding by making the perf tools use the external openCSD (Mathieu Poirier, Tor Jeremiassen) - Add ARM Statistical Profiling Extensions (SPE) support (Kim Phillips) - libtraceevent updates (Steven Rostedt) - Intel vendor event JSON updates (Andi Kleen) - Introduce 'perf report --mmaps' and 'perf report --tasks' to show info present in 'perf.data' (Jiri Olsa, Arnaldo Carvalho de Melo) - Add infrastructure to record first and last sample time to the perf.data file header, so that when processing all samples in a 'perf record' session, such as when doing build-id processing, or when specifically requesting that that info be recorded, use that in 'perf report --time', that also got support for percent slices in addition to absolute ones. I.e. now it is possible to ask for the samples in the 10%-20% time slice of a perf.data file (Jin Yao) - Allow system wide 'perf stat --per-thread', sorting the result (Jin Yao) E.g.: [root@jouet ~]# perf stat --per-thread --metrics IPC ^C Performance counter stats for 'system wide': make-22229 23,012,094,032 inst_retired.any # 0.8 IPC cc1-22419 692,027,497 inst_retired.any # 0.8 IPC gcc-22418 328,231,855 inst_retired.any # 0.9 IPC cc1-22509 220,853,647 inst_retired.any # 0.8 IPC gcc-22486 199,874,810 inst_retired.any # 1.0 IPC as-22466 177,896,365 inst_retired.any # 0.9 IPC cc1-22465 150,732,374 inst_retired.any # 0.8 IPC gcc-22508 112,555,593 inst_retired.any # 0.9 IPC cc1-22487 108,964,079 inst_retired.any # 0.7 IPC qemu-system-x86-2697 21,330,550 inst_retired.any # 0.3 IPC systemd-journal-551 20,642,951 inst_retired.any # 0.4 IPC docker-containe-17651 9,552,892 inst_retired.any # 0.5 IPC dockerd-current-9809 7,528,586 inst_retired.any # 0.5 IPC make-22153 12,504,194,380 inst_retired.any # 0.8 IPC python2-22429 12,081,290,954 inst_retired.any # 0.8 IPC <SNIP> python2-22429 15,026,328,103 cpu_clk_unhalted.thread cc1-22419 826,660,193 cpu_clk_unhalted.thread gcc-22418 365,321,295 cpu_clk_unhalted.thread cc1-22509 279,169,362 cpu_clk_unhalted.thread gcc-22486 210,156,950 cpu_clk_unhalted.thread <SNIP> 5.638075538 seconds time elapsed [root@jouet ~]# - Improve shell auto-completion of perf events (Jin Yao) - 'perf probe' improvements (Masami Hiramatsu) - Improve PMU infrastructure to support amp64's ThunderX2 implementation defined core events (Ganapatrao Kulkarni) - Various annotation related improvements and fixes (Thomas Richter) - Clarify usage of 'overwrite' and 'backward' in the evlist/mmap code, removing the 'overwrite' parameter from several functions as it was always used it as 'false' (Wang Nan) - Fix/improve 'perf record' reverse recording support (Wang Nan) - Improve command line options documentation (Sihyeon Jang) - Optimize sample parsing for ordering events, where we don't need to parse all the PERF_SAMPLE_ bits, just the ones leading to the timestamp needed to reorder events (Jiri Olsa) - Generalize the annotation code to support other source information besides objdump/DWARF obtained ones, starting with python scripts, that will is slated to be merged soon (Jiri Olsa) - ... and a lot more that I failed to list, see the shortlog and changelog for details" * 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (262 commits) perf trace beauty flock: Move to separate object file perf evlist: Remove fcntl.h from evlist.h perf trace beauty futex: Beautify FUTEX_BITSET_MATCH_ANY perf trace: Do not print from time delta for interrupted syscall lines perf trace: Add --print-sample perf bpf: Remove misplaced __maybe_unused attribute MAINTAINERS: Adding entry for CoreSight trace decoding perf tools: Add mechanic to synthesise CoreSight trace packets perf tools: Add full support for CoreSight trace decoding pert tools: Add queue management functionality perf tools: Add functionality to communicate with the openCSD decoder perf tools: Add support for decoding CoreSight trace data perf tools: Add decoder mechanic to support dumping trace data perf tools: Add processing of coresight metadata perf tools: Add initial entry point for decoder CoreSight traces perf tools: Integrating the CoreSight decoding library perf vendor events intel: Update IvyTown files to V20 perf vendor events intel: Update IvyBridge files to V20 perf vendor events intel: Update BroadwellDE events to V7 perf vendor events intel: Update SkylakeX events to V1.06 ...
Diffstat (limited to 'arch')
-rw-r--r--arch/x86/events/msr.c70
-rw-r--r--arch/x86/include/asm/uprobes.h4
-rw-r--r--arch/x86/kernel/uprobes.c107
-rw-r--r--arch/x86/tools/Makefile12
-rw-r--r--arch/x86/tools/insn_decoder_test.c (renamed from arch/x86/tools/test_get_len.c)43
-rw-r--r--arch/x86/tools/objdump_reformat.awk (renamed from arch/x86/tools/distill.awk)4
6 files changed, 183 insertions, 57 deletions
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 14efaa0e8684..18e2628e2d8f 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -10,7 +10,9 @@ enum perf_msr_id {
PERF_MSR_SMI = 4,
PERF_MSR_PTSC = 5,
PERF_MSR_IRPERF = 6,
-
+ PERF_MSR_THERM = 7,
+ PERF_MSR_THERM_SNAP = 8,
+ PERF_MSR_THERM_UNIT = 9,
PERF_MSR_EVENT_MAX,
};
@@ -29,6 +31,11 @@ static bool test_irperf(int idx)
return boot_cpu_has(X86_FEATURE_IRPERF);
}
+static bool test_therm_status(int idx)
+{
+ return boot_cpu_has(X86_FEATURE_DTHERM);
+}
+
static bool test_intel(int idx)
{
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
@@ -95,22 +102,28 @@ struct perf_msr {
bool (*test)(int idx);
};
-PMU_EVENT_ATTR_STRING(tsc, evattr_tsc, "event=0x00");
-PMU_EVENT_ATTR_STRING(aperf, evattr_aperf, "event=0x01");
-PMU_EVENT_ATTR_STRING(mperf, evattr_mperf, "event=0x02");
-PMU_EVENT_ATTR_STRING(pperf, evattr_pperf, "event=0x03");
-PMU_EVENT_ATTR_STRING(smi, evattr_smi, "event=0x04");
-PMU_EVENT_ATTR_STRING(ptsc, evattr_ptsc, "event=0x05");
-PMU_EVENT_ATTR_STRING(irperf, evattr_irperf, "event=0x06");
+PMU_EVENT_ATTR_STRING(tsc, evattr_tsc, "event=0x00" );
+PMU_EVENT_ATTR_STRING(aperf, evattr_aperf, "event=0x01" );
+PMU_EVENT_ATTR_STRING(mperf, evattr_mperf, "event=0x02" );
+PMU_EVENT_ATTR_STRING(pperf, evattr_pperf, "event=0x03" );
+PMU_EVENT_ATTR_STRING(smi, evattr_smi, "event=0x04" );
+PMU_EVENT_ATTR_STRING(ptsc, evattr_ptsc, "event=0x05" );
+PMU_EVENT_ATTR_STRING(irperf, evattr_irperf, "event=0x06" );
+PMU_EVENT_ATTR_STRING(cpu_thermal_margin, evattr_therm, "event=0x07" );
+PMU_EVENT_ATTR_STRING(cpu_thermal_margin.snapshot, evattr_therm_snap, "1" );
+PMU_EVENT_ATTR_STRING(cpu_thermal_margin.unit, evattr_therm_unit, "C" );
static struct perf_msr msr[] = {
- [PERF_MSR_TSC] = { 0, &evattr_tsc, NULL, },
- [PERF_MSR_APERF] = { MSR_IA32_APERF, &evattr_aperf, test_aperfmperf, },
- [PERF_MSR_MPERF] = { MSR_IA32_MPERF, &evattr_mperf, test_aperfmperf, },
- [PERF_MSR_PPERF] = { MSR_PPERF, &evattr_pperf, test_intel, },
- [PERF_MSR_SMI] = { MSR_SMI_COUNT, &evattr_smi, test_intel, },
- [PERF_MSR_PTSC] = { MSR_F15H_PTSC, &evattr_ptsc, test_ptsc, },
- [PERF_MSR_IRPERF] = { MSR_F17H_IRPERF, &evattr_irperf, test_irperf, },
+ [PERF_MSR_TSC] = { 0, &evattr_tsc, NULL, },
+ [PERF_MSR_APERF] = { MSR_IA32_APERF, &evattr_aperf, test_aperfmperf, },
+ [PERF_MSR_MPERF] = { MSR_IA32_MPERF, &evattr_mperf, test_aperfmperf, },
+ [PERF_MSR_PPERF] = { MSR_PPERF, &evattr_pperf, test_intel, },
+ [PERF_MSR_SMI] = { MSR_SMI_COUNT, &evattr_smi, test_intel, },
+ [PERF_MSR_PTSC] = { MSR_F15H_PTSC, &evattr_ptsc, test_ptsc, },
+ [PERF_MSR_IRPERF] = { MSR_F17H_IRPERF, &evattr_irperf, test_irperf, },
+ [PERF_MSR_THERM] = { MSR_IA32_THERM_STATUS, &evattr_therm, test_therm_status, },
+ [PERF_MSR_THERM_SNAP] = { MSR_IA32_THERM_STATUS, &evattr_therm_snap, test_therm_status, },
+ [PERF_MSR_THERM_UNIT] = { MSR_IA32_THERM_STATUS, &evattr_therm_unit, test_therm_status, },
};
static struct attribute *events_attrs[PERF_MSR_EVENT_MAX + 1] = {
@@ -161,9 +174,9 @@ static int msr_event_init(struct perf_event *event)
if (!msr[cfg].attr)
return -EINVAL;
- event->hw.idx = -1;
- event->hw.event_base = msr[cfg].msr;
- event->hw.config = cfg;
+ event->hw.idx = -1;
+ event->hw.event_base = msr[cfg].msr;
+ event->hw.config = cfg;
return 0;
}
@@ -184,7 +197,7 @@ static void msr_event_update(struct perf_event *event)
u64 prev, now;
s64 delta;
- /* Careful, an NMI might modify the previous event value. */
+ /* Careful, an NMI might modify the previous event value: */
again:
prev = local64_read(&event->hw.prev_count);
now = msr_read_counter(event);
@@ -193,17 +206,22 @@ again:
goto again;
delta = now - prev;
- if (unlikely(event->hw.event_base == MSR_SMI_COUNT))
+ if (unlikely(event->hw.event_base == MSR_SMI_COUNT)) {
delta = sign_extend64(delta, 31);
-
- local64_add(delta, &event->count);
+ local64_add(delta, &event->count);
+ } else if (unlikely(event->hw.event_base == MSR_IA32_THERM_STATUS)) {
+ /* If valid, extract digital readout, otherwise set to -1: */
+ now = now & (1ULL << 31) ? (now >> 16) & 0x3f : -1;
+ local64_set(&event->count, now);
+ } else {
+ local64_add(delta, &event->count);
+ }
}
static void msr_event_start(struct perf_event *event, int flags)
{
- u64 now;
+ u64 now = msr_read_counter(event);
- now = msr_read_counter(event);
local64_set(&event->hw.prev_count, now);
}
@@ -250,9 +268,7 @@ static int __init msr_init(void)
for (i = PERF_MSR_TSC + 1; i < PERF_MSR_EVENT_MAX; i++) {
u64 val;
- /*
- * Virt sucks arse; you cannot tell if a R/O MSR is present :/
- */
+ /* Virt sucks; you cannot tell if a R/O MSR is present :/ */
if (!msr[i].test(i) || rdmsrl_safe(msr[i].msr, &val))
msr[i].attr = NULL;
}
diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h
index 74f4c2ff6427..d8bfa98fca98 100644
--- a/arch/x86/include/asm/uprobes.h
+++ b/arch/x86/include/asm/uprobes.h
@@ -53,6 +53,10 @@ struct arch_uprobe {
u8 fixups;
u8 ilen;
} defparam;
+ struct {
+ u8 reg_offset; /* to the start of pt_regs */
+ u8 ilen;
+ } push;
};
};
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index a3755d293a48..85c7ef23d99f 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -528,11 +528,11 @@ static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
return 0;
}
-static int push_ret_address(struct pt_regs *regs, unsigned long ip)
+static int emulate_push_stack(struct pt_regs *regs, unsigned long val)
{
unsigned long new_sp = regs->sp - sizeof_long();
- if (copy_to_user((void __user *)new_sp, &ip, sizeof_long()))
+ if (copy_to_user((void __user *)new_sp, &val, sizeof_long()))
return -EFAULT;
regs->sp = new_sp;
@@ -566,7 +566,7 @@ static int default_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs
regs->ip += correction;
} else if (auprobe->defparam.fixups & UPROBE_FIX_CALL) {
regs->sp += sizeof_long(); /* Pop incorrect return address */
- if (push_ret_address(regs, utask->vaddr + auprobe->defparam.ilen))
+ if (emulate_push_stack(regs, utask->vaddr + auprobe->defparam.ilen))
return -ERESTART;
}
/* popf; tell the caller to not touch TF */
@@ -655,7 +655,7 @@ static bool branch_emulate_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
*
* But there is corner case, see the comment in ->post_xol().
*/
- if (push_ret_address(regs, new_ip))
+ if (emulate_push_stack(regs, new_ip))
return false;
} else if (!check_jmp_cond(auprobe, regs)) {
offs = 0;
@@ -665,6 +665,16 @@ static bool branch_emulate_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
return true;
}
+static bool push_emulate_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+ unsigned long *src_ptr = (void *)regs + auprobe->push.reg_offset;
+
+ if (emulate_push_stack(regs, *src_ptr))
+ return false;
+ regs->ip += auprobe->push.ilen;
+ return true;
+}
+
static int branch_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
{
BUG_ON(!branch_is_call(auprobe));
@@ -703,6 +713,10 @@ static const struct uprobe_xol_ops branch_xol_ops = {
.post_xol = branch_post_xol_op,
};
+static const struct uprobe_xol_ops push_xol_ops = {
+ .emulate = push_emulate_op,
+};
+
/* Returns -ENOSYS if branch_xol_ops doesn't handle this insn */
static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
{
@@ -750,6 +764,87 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
return 0;
}
+/* Returns -ENOSYS if push_xol_ops doesn't handle this insn */
+static int push_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
+{
+ u8 opc1 = OPCODE1(insn), reg_offset = 0;
+
+ if (opc1 < 0x50 || opc1 > 0x57)
+ return -ENOSYS;
+
+ if (insn->length > 2)
+ return -ENOSYS;
+ if (insn->length == 2) {
+ /* only support rex_prefix 0x41 (x64 only) */
+#ifdef CONFIG_X86_64
+ if (insn->rex_prefix.nbytes != 1 ||
+ insn->rex_prefix.bytes[0] != 0x41)
+ return -ENOSYS;
+
+ switch (opc1) {
+ case 0x50:
+ reg_offset = offsetof(struct pt_regs, r8);
+ break;
+ case 0x51:
+ reg_offset = offsetof(struct pt_regs, r9);
+ break;
+ case 0x52:
+ reg_offset = offsetof(struct pt_regs, r10);
+ break;
+ case 0x53:
+ reg_offset = offsetof(struct pt_regs, r11);
+ break;
+ case 0x54:
+ reg_offset = offsetof(struct pt_regs, r12);
+ break;
+ case 0x55:
+ reg_offset = offsetof(struct pt_regs, r13);
+ break;
+ case 0x56:
+ reg_offset = offsetof(struct pt_regs, r14);
+ break;
+ case 0x57:
+ reg_offset = offsetof(struct pt_regs, r15);
+ break;
+ }
+#else
+ return -ENOSYS;
+#endif
+ } else {
+ switch (opc1) {
+ case 0x50:
+ reg_offset = offsetof(struct pt_regs, ax);
+ break;
+ case 0x51:
+ reg_offset = offsetof(struct pt_regs, cx);
+ break;
+ case 0x52:
+ reg_offset = offsetof(struct pt_regs, dx);
+ break;
+ case 0x53:
+ reg_offset = offsetof(struct pt_regs, bx);
+ break;
+ case 0x54:
+ reg_offset = offsetof(struct pt_regs, sp);
+ break;
+ case 0x55:
+ reg_offset = offsetof(struct pt_regs, bp);
+ break;
+ case 0x56:
+ reg_offset = offsetof(struct pt_regs, si);
+ break;
+ case 0x57:
+ reg_offset = offsetof(struct pt_regs, di);
+ break;
+ }
+ }
+
+ auprobe->push.reg_offset = reg_offset;
+ auprobe->push.ilen = insn->length;
+ auprobe->ops = &push_xol_ops;
+ return 0;
+}
+
/**
* arch_uprobe_analyze_insn - instruction analysis including validity and fixups.
* @mm: the probed address space.
@@ -771,6 +866,10 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
if (ret != -ENOSYS)
return ret;
+ ret = push_setup_xol_ops(auprobe, &insn);
+ if (ret != -ENOSYS)
+ return ret;
+
/*
* Figure out which fixups default_post_xol_op() will need to perform,
* and annotate defparam->fixups accordingly.
diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile
index 972b8e8d939c..09af7ff53044 100644
--- a/arch/x86/tools/Makefile
+++ b/arch/x86/tools/Makefile
@@ -13,28 +13,28 @@ else
posttest_64bit = -n
endif
-distill_awk = $(srctree)/arch/x86/tools/distill.awk
+reformatter = $(srctree)/arch/x86/tools/objdump_reformat.awk
chkobjdump = $(srctree)/arch/x86/tools/chkobjdump.awk
quiet_cmd_posttest = TEST $@
- cmd_posttest = ($(OBJDUMP) -v | $(AWK) -f $(chkobjdump)) || $(OBJDUMP) -d -j .text $(objtree)/vmlinux | $(AWK) -f $(distill_awk) | $(obj)/test_get_len $(posttest_64bit) $(posttest_verbose)
+ cmd_posttest = ($(OBJDUMP) -v | $(AWK) -f $(chkobjdump)) || $(OBJDUMP) -d -j .text $(objtree)/vmlinux | $(AWK) -f $(reformatter) | $(obj)/insn_decoder_test $(posttest_64bit) $(posttest_verbose)
quiet_cmd_sanitytest = TEST $@
cmd_sanitytest = $(obj)/insn_sanity $(posttest_64bit) -m 1000000
-posttest: $(obj)/test_get_len vmlinux $(obj)/insn_sanity
+posttest: $(obj)/insn_decoder_test vmlinux $(obj)/insn_sanity
$(call cmd,posttest)
$(call cmd,sanitytest)
-hostprogs-y += test_get_len insn_sanity
+hostprogs-y += insn_decoder_test insn_sanity
# -I needed for generated C source and C source which in the kernel tree.
-HOSTCFLAGS_test_get_len.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/uapi/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/uapi/
+HOSTCFLAGS_insn_decoder_test.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/uapi/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/uapi/
HOSTCFLAGS_insn_sanity.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/
# Dependencies are also needed.
-$(obj)/test_get_len.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
+$(obj)/insn_decoder_test.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
$(obj)/insn_sanity.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
diff --git a/arch/x86/tools/test_get_len.c b/arch/x86/tools/insn_decoder_test.c
index ecf31e0358c8..a3b4fd954931 100644
--- a/arch/x86/tools/test_get_len.c
+++ b/arch/x86/tools/insn_decoder_test.c
@@ -9,10 +9,6 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
* Copyright (C) IBM Corporation, 2009
*/
@@ -21,6 +17,7 @@
#include <string.h>
#include <assert.h>
#include <unistd.h>
+#include <stdarg.h>
#define unlikely(cond) (cond)
@@ -33,7 +30,7 @@
* particular. See if insn_get_length() and the disassembler agree
* on the length of each instruction in an elf disassembly.
*
- * Usage: objdump -d a.out | awk -f distill.awk | ./test_get_len
+ * Usage: objdump -d a.out | awk -f objdump_reformat.awk | ./insn_decoder_test
*/
const char *prog;
@@ -42,8 +39,8 @@ static int x86_64;
static void usage(void)
{
- fprintf(stderr, "Usage: objdump -d a.out | awk -f distill.awk |"
- " %s [-y|-n] [-v]\n", prog);
+ fprintf(stderr, "Usage: objdump -d a.out | awk -f objdump_reformat.awk"
+ " | %s [-y|-n] [-v]\n", prog);
fprintf(stderr, "\t-y 64bit mode\n");
fprintf(stderr, "\t-n 32bit mode\n");
fprintf(stderr, "\t-v verbose mode\n");
@@ -52,10 +49,21 @@ static void usage(void)
static void malformed_line(const char *line, int line_nr)
{
- fprintf(stderr, "%s: malformed line %d:\n%s", prog, line_nr, line);
+ fprintf(stderr, "%s: error: malformed line %d:\n%s",
+ prog, line_nr, line);
exit(3);
}
+static void pr_warn(const char *fmt, ...)
+{
+ va_list ap;
+
+ fprintf(stderr, "%s: warning: ", prog);
+ va_start(ap, fmt);
+ vfprintf(stderr, fmt, ap);
+ va_end(ap);
+}
+
static void dump_field(FILE *fp, const char *name, const char *indent,
struct insn_field *field)
{
@@ -153,21 +161,20 @@ int main(int argc, char **argv)
insn_get_length(&insn);
if (insn.length != nb) {
warnings++;
- fprintf(stderr, "Warning: %s found difference at %s\n",
- prog, sym);
- fprintf(stderr, "Warning: %s", line);
- fprintf(stderr, "Warning: objdump says %d bytes, but "
- "insn_get_length() says %d\n", nb,
- insn.length);
+ pr_warn("Found an x86 instruction decoder bug, "
+ "please report this.\n", sym);
+ pr_warn("%s", line);
+ pr_warn("objdump says %d bytes, but insn_get_length() "
+ "says %d\n", nb, insn.length);
if (verbose)
dump_insn(stderr, &insn);
}
}
if (warnings)
- fprintf(stderr, "Warning: decoded and checked %d"
- " instructions with %d warnings\n", insns, warnings);
+ pr_warn("Decoded and checked %d instructions with %d "
+ "failures\n", insns, warnings);
else
- fprintf(stdout, "Success: decoded and checked %d"
- " instructions\n", insns);
+ fprintf(stdout, "%s: success: Decoded and checked %d"
+ " instructions\n", prog, insns);
return 0;
}
diff --git a/arch/x86/tools/distill.awk b/arch/x86/tools/objdump_reformat.awk
index e0edeccc1429..f418c91b71f0 100644
--- a/arch/x86/tools/distill.awk
+++ b/arch/x86/tools/objdump_reformat.awk
@@ -1,7 +1,7 @@
#!/bin/awk -f
# SPDX-License-Identifier: GPL-2.0
-# Usage: objdump -d a.out | awk -f distill.awk | ./test_get_len
-# Distills the disassembly as follows:
+# Usage: objdump -d a.out | awk -f objdump_reformat.awk | ./insn_decoder_test
+# Reformats the disassembly as follows:
# - Removes all lines except the disassembled instructions.
# - For instructions that exceed 1 line (7 bytes), crams all the hex bytes
# into a single line.