summaryrefslogtreecommitdiff
path: root/tools/perf
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-04-27 17:45:09 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-04-27 17:45:09 -0700
commitc6536676c7fe3f572ba55842e59c3c71c01e7fb3 (patch)
tree47482eee74657c959161bf10efcaad1c8b53ebd3 /tools/perf
parente7c6e405e171fb33990a12ecfd14e6500d9e5cf2 (diff)
parent2c88d45edbb89029c1190bb3b136d2602f057c98 (diff)
Merge tag 'x86_core_for_v5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 updates from Borislav Petkov: - Turn the stack canary into a normal __percpu variable on 32-bit which gets rid of the LAZY_GS stuff and a lot of code. - Add an insn_decode() API which all users of the instruction decoder should preferrably use. Its goal is to keep the details of the instruction decoder away from its users and simplify and streamline how one decodes insns in the kernel. Convert its users to it. - kprobes improvements and fixes - Set the maximum DIE per package variable on Hygon - Rip out the dynamic NOP selection and simplify all the machinery around selecting NOPs. Use the simplified NOPs in objtool now too. - Add Xeon Sapphire Rapids to list of CPUs that support PPIN - Simplify the retpolines by folding the entire thing into an alternative now that objtool can handle alternatives with stack ops. Then, have objtool rewrite the call to the retpoline with the alternative which then will get patched at boot time. - Document Intel uarch per models in intel-family.h - Make Sub-NUMA Clustering topology the default and Cluster-on-Die the exception on Intel. * tag 'x86_core_for_v5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits) x86, sched: Treat Intel SNC topology as default, COD as exception x86/cpu: Comment Skylake server stepping too x86/cpu: Resort and comment Intel models objtool/x86: Rewrite retpoline thunk calls objtool: Skip magical retpoline .altinstr_replacement objtool: Cache instruction relocs objtool: Keep track of retpoline call sites objtool: Add elf_create_undef_symbol() objtool: Extract elf_symbol_add() objtool: Extract elf_strtab_concat() objtool: Create reloc sections implicitly objtool: Add elf_create_reloc() helper objtool: Rework the elf_rebuild_reloc_section() logic objtool: Fix static_call list generation objtool: Handle per arch retpoline naming objtool: Correctly handle retpoline thunk calls x86/retpoline: Simplify retpolines x86/alternatives: Optimize optimize_nops() x86: Add insn_decode_kernel() x86/kprobes: Move 'inline' to the beginning of the kprobe_is_ss() declaration ...
Diffstat (limited to 'tools/perf')
-rw-r--r--tools/perf/arch/x86/tests/insn-x86.c9
-rw-r--r--tools/perf/arch/x86/util/archinsn.c9
-rwxr-xr-xtools/perf/check-headers.sh15
-rw-r--r--tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c17
4 files changed, 30 insertions, 20 deletions
diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c
index 4f75ae990140..0262b0d8ccf5 100644
--- a/tools/perf/arch/x86/tests/insn-x86.c
+++ b/tools/perf/arch/x86/tests/insn-x86.c
@@ -96,13 +96,12 @@ static int get_branch(const char *branch_str)
static int test_data_item(struct test_data *dat, int x86_64)
{
struct intel_pt_insn intel_pt_insn;
+ int op, branch, ret;
struct insn insn;
- int op, branch;
- insn_init(&insn, dat->data, MAX_INSN_SIZE, x86_64);
- insn_get_length(&insn);
-
- if (!insn_complete(&insn)) {
+ ret = insn_decode(&insn, dat->data, MAX_INSN_SIZE,
+ x86_64 ? INSN_MODE_64 : INSN_MODE_32);
+ if (ret < 0) {
pr_debug("Failed to decode: %s\n", dat->asm_rep);
return -1;
}
diff --git a/tools/perf/arch/x86/util/archinsn.c b/tools/perf/arch/x86/util/archinsn.c
index 34d600c51044..546feda08428 100644
--- a/tools/perf/arch/x86/util/archinsn.c
+++ b/tools/perf/arch/x86/util/archinsn.c
@@ -11,7 +11,7 @@ void arch_fetch_insn(struct perf_sample *sample,
struct machine *machine)
{
struct insn insn;
- int len;
+ int len, ret;
bool is64bit = false;
if (!sample->ip)
@@ -19,8 +19,9 @@ void arch_fetch_insn(struct perf_sample *sample,
len = thread__memcpy(thread, machine, sample->insn, sample->ip, sizeof(sample->insn), &is64bit);
if (len <= 0)
return;
- insn_init(&insn, sample->insn, len, is64bit);
- insn_get_length(&insn);
- if (insn_complete(&insn) && insn.length <= len)
+
+ ret = insn_decode(&insn, sample->insn, len,
+ is64bit ? INSN_MODE_64 : INSN_MODE_32);
+ if (ret >= 0 && insn.length <= len)
sample->insn_len = insn.length;
}
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index dded93a2bc89..07857dfb4d91 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -75,6 +75,13 @@ include/uapi/asm-generic/mman-common.h
include/uapi/asm-generic/unistd.h
'
+SYNC_CHECK_FILES='
+arch/x86/include/asm/inat.h
+arch/x86/include/asm/insn.h
+arch/x86/lib/inat.c
+arch/x86/lib/insn.c
+'
+
# These copies are under tools/perf/trace/beauty/ as they are not used to in
# building object files only by scripts in tools/perf/trace/beauty/ to generate
# tables that then gets included in .c files for things like id->string syscall
@@ -129,6 +136,10 @@ for i in $FILES; do
check $i -B
done
+for i in $SYNC_CHECK_FILES; do
+ check $i '-I "^.*\/\*.*__ignore_sync_check__.*\*\/.*$"'
+done
+
# diff with extra ignore lines
check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memcpy_\(erms\|orig\))"'
check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"'
@@ -137,10 +148,6 @@ check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"'
check include/linux/build_bug.h '-I "^#\(ifndef\|endif\)\( \/\/\)* static_assert$"'
check include/linux/ctype.h '-I "isdigit("'
check lib/ctype.c '-I "^EXPORT_SYMBOL" -I "^#include <linux/export.h>" -B'
-check arch/x86/include/asm/inat.h '-I "^#include [\"<]\(asm/\)*inat_types.h[\">]"'
-check arch/x86/include/asm/insn.h '-I "^#include [\"<]\(asm/\)*inat.h[\">]"'
-check arch/x86/lib/inat.c '-I "^#include [\"<]\(../include/\)*asm/insn.h[\">]"'
-check arch/x86/lib/insn.c '-I "^#include [\"<]\(../include/\)*asm/in\(at\|sn\).h[\">]" -I "^#include [\"<]\(../include/\)*asm/emulate_prefix.h[\">]"'
# diff non-symmetric files
check_2 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
index 2f6cc7eea251..593f20e9774c 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
@@ -169,11 +169,13 @@ int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64,
struct intel_pt_insn *intel_pt_insn)
{
struct insn insn;
+ int ret;
- insn_init(&insn, buf, len, x86_64);
- insn_get_length(&insn);
- if (!insn_complete(&insn) || insn.length > len)
+ ret = insn_decode(&insn, buf, len,
+ x86_64 ? INSN_MODE_64 : INSN_MODE_32);
+ if (ret < 0 || insn.length > len)
return -1;
+
intel_pt_insn_decoder(&insn, intel_pt_insn);
if (insn.length < INTEL_PT_INSN_BUF_SZ)
memcpy(intel_pt_insn->buf, buf, insn.length);
@@ -194,12 +196,13 @@ const char *dump_insn(struct perf_insn *x, uint64_t ip __maybe_unused,
u8 *inbuf, int inlen, int *lenp)
{
struct insn insn;
- int n, i;
+ int n, i, ret;
int left;
- insn_init(&insn, inbuf, inlen, x->is64bit);
- insn_get_length(&insn);
- if (!insn_complete(&insn) || insn.length > inlen)
+ ret = insn_decode(&insn, inbuf, inlen,
+ x->is64bit ? INSN_MODE_64 : INSN_MODE_32);
+
+ if (ret < 0 || insn.length > inlen)
return "<bad>";
if (lenp)
*lenp = insn.length;