Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf tooling fixes from Thomas Gleixner:
"Core libraries:
- Fix max perf_event_attr.precise_ip detection.
- Fix parser error for uncore event alias
- Fixup ordering of kernel maps after obtaining the main kernel map
address.
Intel PT:
- Fix TSC slip where A TSC packet can slip past MTC packets so that
the timestamp appears to go backwards.
- Fixes for exported-sql-viewer GUI conversion to python3.
ARM coresight:
- Fix the build by adding a missing case value for enumeration value
introduced in newer library, that now is the required one.
tool headers:
- Syncronize kernel headers with the kernel, getting new io_uring and
pidfd_send_signal syscalls so that 'perf trace' can handle them"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf pmu: Fix parser error for uncore event alias
perf scripts python: exported-sql-viewer.py: Fix python3 support
perf scripts python: exported-sql-viewer.py: Fix never-ending loop
perf machine: Update kernel map address and re-order properly
tools headers uapi: Sync powerpc's asm/kvm.h copy with the kernel sources
tools headers: Update x86's syscall_64.tbl and uapi/asm-generic/unistd
tools headers uapi: Update drm/i915_drm.h
tools arch x86: Sync asm/cpufeatures.h with the kernel sources
tools headers uapi: Sync linux/fcntl.h to get the F_SEAL_FUTURE_WRITE addition
tools headers uapi: Sync asm-generic/mman-common.h and linux/mman.h
perf evsel: Fix max perf_event_attr.precise_ip detection
perf intel-pt: Fix TSC slip
perf cs-etm: Add missing case value
This commit is contained in:
Linus Torvalds
commit
590627f755
|
|
@ -27,8 +27,6 @@
|
|||
#define MAP_NONBLOCK 0x40000
|
||||
#define MAP_NORESERVE 0x10000
|
||||
#define MAP_POPULATE 0x20000
|
||||
#define MAP_PRIVATE 0x02
|
||||
#define MAP_SHARED 0x01
|
||||
#define MAP_STACK 0x80000
|
||||
#define PROT_EXEC 0x4
|
||||
#define PROT_GROWSDOWN 0x01000000
|
||||
|
|
|
|||
|
|
@ -28,8 +28,6 @@
|
|||
#define MAP_NONBLOCK 0x20000
|
||||
#define MAP_NORESERVE 0x0400
|
||||
#define MAP_POPULATE 0x10000
|
||||
#define MAP_PRIVATE 0x002
|
||||
#define MAP_SHARED 0x001
|
||||
#define MAP_STACK 0x40000
|
||||
#define PROT_EXEC 0x04
|
||||
#define PROT_GROWSDOWN 0x01000000
|
||||
|
|
|
|||
|
|
@ -27,8 +27,6 @@
|
|||
#define MAP_NONBLOCK 0x20000
|
||||
#define MAP_NORESERVE 0x4000
|
||||
#define MAP_POPULATE 0x10000
|
||||
#define MAP_PRIVATE 0x02
|
||||
#define MAP_SHARED 0x01
|
||||
#define MAP_STACK 0x40000
|
||||
#define PROT_EXEC 0x4
|
||||
#define PROT_GROWSDOWN 0x01000000
|
||||
|
|
|
|||
|
|
@ -463,10 +463,12 @@ struct kvm_ppc_cpu_char {
|
|||
#define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED (1ULL << 58)
|
||||
#define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF (1ULL << 57)
|
||||
#define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS (1ULL << 56)
|
||||
#define KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST (1ull << 54)
|
||||
|
||||
#define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY (1ULL << 63)
|
||||
#define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR (1ULL << 62)
|
||||
#define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ULL << 61)
|
||||
#define KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE (1ull << 58)
|
||||
|
||||
/* Per-vcpu XICS interrupt controller state */
|
||||
#define KVM_REG_PPC_ICP_STATE (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
|
||||
|
|
|
|||
|
|
@ -344,6 +344,7 @@
|
|||
/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
|
||||
#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */
|
||||
#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
|
||||
#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */
|
||||
#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */
|
||||
#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
|
||||
#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */
|
||||
|
|
|
|||
|
|
@ -27,8 +27,6 @@
|
|||
#define MAP_NONBLOCK 0x20000
|
||||
#define MAP_NORESERVE 0x0400
|
||||
#define MAP_POPULATE 0x10000
|
||||
#define MAP_PRIVATE 0x002
|
||||
#define MAP_SHARED 0x001
|
||||
#define MAP_STACK 0x40000
|
||||
#define PROT_EXEC 0x4
|
||||
#define PROT_GROWSDOWN 0x01000000
|
||||
|
|
|
|||
|
|
@ -4,9 +4,9 @@
|
|||
/*
|
||||
* Check OpenCSD library version is sufficient to provide required features
|
||||
*/
|
||||
#define OCSD_MIN_VER ((0 << 16) | (10 << 8) | (0))
|
||||
#define OCSD_MIN_VER ((0 << 16) | (11 << 8) | (0))
|
||||
#if !defined(OCSD_VER_NUM) || (OCSD_VER_NUM < OCSD_MIN_VER)
|
||||
#error "OpenCSD >= 0.10.0 is required"
|
||||
#error "OpenCSD >= 0.11.0 is required"
|
||||
#endif
|
||||
|
||||
int main(void)
|
||||
|
|
|
|||
|
|
@ -0,0 +1,23 @@
|
|||
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
|
||||
#ifndef __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
|
||||
#define __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
|
||||
|
||||
#include <asm-generic/mman-common.h>
|
||||
|
||||
/* We need this because we need to have tools/include/uapi/ included in the tools
|
||||
* header search path to get access to stuff that is not yet in the system's
|
||||
* copy of the files in that directory, but since this cset:
|
||||
*
|
||||
* 746c9398f5ac ("arch: move common mmap flags to linux/mman.h")
|
||||
*
|
||||
* We end up making sys/mman.h, that is in the system headers, to not find the
|
||||
* MAP_SHARED and MAP_PRIVATE defines because they are not anymore in our copy
|
||||
* of asm-generic/mman-common.h. So we define them here and include this header
|
||||
* from each of the per arch mman.h headers.
|
||||
*/
|
||||
#ifndef MAP_SHARED
|
||||
#define MAP_SHARED 0x01 /* Share changes */
|
||||
#define MAP_PRIVATE 0x02 /* Changes are private */
|
||||
#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */
|
||||
#endif
|
||||
#endif // __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
|
||||
|
|
@ -15,9 +15,7 @@
|
|||
#define PROT_GROWSDOWN 0x01000000 /* mprotect flag: extend change to start of growsdown vma */
|
||||
#define PROT_GROWSUP 0x02000000 /* mprotect flag: extend change to end of growsup vma */
|
||||
|
||||
#define MAP_SHARED 0x01 /* Share changes */
|
||||
#define MAP_PRIVATE 0x02 /* Changes are private */
|
||||
#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */
|
||||
/* 0x01 - 0x03 are defined in linux/mman.h */
|
||||
#define MAP_TYPE 0x0f /* Mask for type of mapping */
|
||||
#define MAP_FIXED 0x10 /* Interpret addr exactly */
|
||||
#define MAP_ANONYMOUS 0x20 /* don't use a file */
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
#ifndef __ASM_GENERIC_MMAN_H
|
||||
#define __ASM_GENERIC_MMAN_H
|
||||
|
||||
#include <asm-generic/mman-common.h>
|
||||
#include <asm-generic/mman-common-tools.h>
|
||||
|
||||
#define MAP_GROWSDOWN 0x0100 /* stack-like segment */
|
||||
#define MAP_DENYWRITE 0x0800 /* ETXTBSY */
|
||||
|
|
|
|||
|
|
@ -824,8 +824,17 @@ __SYSCALL(__NR_futex_time64, sys_futex)
|
|||
__SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval)
|
||||
#endif
|
||||
|
||||
#define __NR_pidfd_send_signal 424
|
||||
__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal)
|
||||
#define __NR_io_uring_setup 425
|
||||
__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup)
|
||||
#define __NR_io_uring_enter 426
|
||||
__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter)
|
||||
#define __NR_io_uring_register 427
|
||||
__SYSCALL(__NR_io_uring_register, sys_io_uring_register)
|
||||
|
||||
#undef __NR_syscalls
|
||||
#define __NR_syscalls 424
|
||||
#define __NR_syscalls 428
|
||||
|
||||
/*
|
||||
* 32 bit systems traditionally used different
|
||||
|
|
|
|||
|
|
@ -1486,9 +1486,73 @@ struct drm_i915_gem_context_param {
|
|||
#define I915_CONTEXT_MAX_USER_PRIORITY 1023 /* inclusive */
|
||||
#define I915_CONTEXT_DEFAULT_PRIORITY 0
|
||||
#define I915_CONTEXT_MIN_USER_PRIORITY -1023 /* inclusive */
|
||||
/*
|
||||
* When using the following param, value should be a pointer to
|
||||
* drm_i915_gem_context_param_sseu.
|
||||
*/
|
||||
#define I915_CONTEXT_PARAM_SSEU 0x7
|
||||
__u64 value;
|
||||
};
|
||||
|
||||
/**
|
||||
* Context SSEU programming
|
||||
*
|
||||
* It may be necessary for either functional or performance reason to configure
|
||||
* a context to run with a reduced number of SSEU (where SSEU stands for Slice/
|
||||
* Sub-slice/EU).
|
||||
*
|
||||
* This is done by configuring SSEU configuration using the below
|
||||
* @struct drm_i915_gem_context_param_sseu for every supported engine which
|
||||
* userspace intends to use.
|
||||
*
|
||||
* Not all GPUs or engines support this functionality in which case an error
|
||||
* code -ENODEV will be returned.
|
||||
*
|
||||
* Also, flexibility of possible SSEU configuration permutations varies between
|
||||
* GPU generations and software imposed limitations. Requesting such a
|
||||
* combination will return an error code of -EINVAL.
|
||||
*
|
||||
* NOTE: When perf/OA is active the context's SSEU configuration is ignored in
|
||||
* favour of a single global setting.
|
||||
*/
|
||||
struct drm_i915_gem_context_param_sseu {
|
||||
/*
|
||||
* Engine class & instance to be configured or queried.
|
||||
*/
|
||||
__u16 engine_class;
|
||||
__u16 engine_instance;
|
||||
|
||||
/*
|
||||
* Unused for now. Must be cleared to zero.
|
||||
*/
|
||||
__u32 flags;
|
||||
|
||||
/*
|
||||
* Mask of slices to enable for the context. Valid values are a subset
|
||||
* of the bitmask value returned for I915_PARAM_SLICE_MASK.
|
||||
*/
|
||||
__u64 slice_mask;
|
||||
|
||||
/*
|
||||
* Mask of subslices to enable for the context. Valid values are a
|
||||
* subset of the bitmask value return by I915_PARAM_SUBSLICE_MASK.
|
||||
*/
|
||||
__u64 subslice_mask;
|
||||
|
||||
/*
|
||||
* Minimum/Maximum number of EUs to enable per subslice for the
|
||||
* context. min_eus_per_subslice must be inferior or equal to
|
||||
* max_eus_per_subslice.
|
||||
*/
|
||||
__u16 min_eus_per_subslice;
|
||||
__u16 max_eus_per_subslice;
|
||||
|
||||
/*
|
||||
* Unused for now. Must be cleared to zero.
|
||||
*/
|
||||
__u32 rsvd;
|
||||
};
|
||||
|
||||
enum drm_i915_oa_format {
|
||||
I915_OA_FORMAT_A13 = 1, /* HSW only */
|
||||
I915_OA_FORMAT_A29, /* HSW only */
|
||||
|
|
|
|||
|
|
@ -41,6 +41,7 @@
|
|||
#define F_SEAL_SHRINK 0x0002 /* prevent file from shrinking */
|
||||
#define F_SEAL_GROW 0x0004 /* prevent file from growing */
|
||||
#define F_SEAL_WRITE 0x0008 /* prevent writes */
|
||||
#define F_SEAL_FUTURE_WRITE 0x0010 /* prevent future writes while mapped */
|
||||
/* (1U << 31) is reserved for signed error codes */
|
||||
|
||||
/*
|
||||
|
|
|
|||
|
|
@ -12,6 +12,10 @@
|
|||
#define OVERCOMMIT_ALWAYS 1
|
||||
#define OVERCOMMIT_NEVER 2
|
||||
|
||||
#define MAP_SHARED 0x01 /* Share changes */
|
||||
#define MAP_PRIVATE 0x02 /* Changes are private */
|
||||
#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */
|
||||
|
||||
/*
|
||||
* Huge page size encoding when MAP_HUGETLB is specified, and a huge page
|
||||
* size other than the default is desired. See hugetlb_encode.h.
|
||||
|
|
|
|||
|
|
@ -481,8 +481,8 @@ $(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_t
|
|||
mmap_flags_array := $(beauty_outdir)/mmap_flags_array.c
|
||||
mmap_flags_tbl := $(srctree)/tools/perf/trace/beauty/mmap_flags.sh
|
||||
|
||||
$(mmap_flags_array): $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl)
|
||||
$(Q)$(SHELL) '$(mmap_flags_tbl)' $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
|
||||
$(mmap_flags_array): $(linux_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl)
|
||||
$(Q)$(SHELL) '$(mmap_flags_tbl)' $(linux_uapi_dir) $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
|
||||
|
||||
mount_flags_array := $(beauty_outdir)/mount_flags_array.c
|
||||
mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh
|
||||
|
|
|
|||
|
|
@ -345,6 +345,10 @@
|
|||
334 common rseq __x64_sys_rseq
|
||||
# don't use numbers 387 through 423, add new calls after the last
|
||||
# 'common' entry
|
||||
424 common pidfd_send_signal __x64_sys_pidfd_send_signal
|
||||
425 common io_uring_setup __x64_sys_io_uring_setup
|
||||
426 common io_uring_enter __x64_sys_io_uring_enter
|
||||
427 common io_uring_register __x64_sys_io_uring_register
|
||||
|
||||
#
|
||||
# x32-specific system call numbers start at 512 to avoid cache impact
|
||||
|
|
|
|||
|
|
@ -103,7 +103,7 @@ done
|
|||
# diff with extra ignore lines
|
||||
check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
|
||||
check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
|
||||
check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common.h>"'
|
||||
check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"'
|
||||
check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"'
|
||||
|
||||
# diff non-symmetric files
|
||||
|
|
|
|||
|
|
@ -107,6 +107,7 @@ import os
|
|||
from PySide.QtCore import *
|
||||
from PySide.QtGui import *
|
||||
from PySide.QtSql import *
|
||||
pyside_version_1 = True
|
||||
from decimal import *
|
||||
from ctypes import *
|
||||
from multiprocessing import Process, Array, Value, Event
|
||||
|
|
@ -1526,6 +1527,19 @@ def BranchDataPrep(query):
|
|||
" (" + dsoname(query.value(15)) + ")")
|
||||
return data
|
||||
|
||||
def BranchDataPrepWA(query):
|
||||
data = []
|
||||
data.append(query.value(0))
|
||||
# Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string
|
||||
data.append("{:>19}".format(query.value(1)))
|
||||
for i in xrange(2, 8):
|
||||
data.append(query.value(i))
|
||||
data.append(tohex(query.value(8)).rjust(16) + " " + query.value(9) + offstr(query.value(10)) +
|
||||
" (" + dsoname(query.value(11)) + ")" + " -> " +
|
||||
tohex(query.value(12)) + " " + query.value(13) + offstr(query.value(14)) +
|
||||
" (" + dsoname(query.value(15)) + ")")
|
||||
return data
|
||||
|
||||
# Branch data model
|
||||
|
||||
class BranchModel(TreeModel):
|
||||
|
|
@ -1553,7 +1567,11 @@ class BranchModel(TreeModel):
|
|||
" AND evsel_id = " + str(self.event_id) +
|
||||
" ORDER BY samples.id"
|
||||
" LIMIT " + str(glb_chunk_sz))
|
||||
self.fetcher = SQLFetcher(glb, sql, BranchDataPrep, self.AddSample)
|
||||
if pyside_version_1 and sys.version_info[0] == 3:
|
||||
prep = BranchDataPrepWA
|
||||
else:
|
||||
prep = BranchDataPrep
|
||||
self.fetcher = SQLFetcher(glb, sql, prep, self.AddSample)
|
||||
self.fetcher.done.connect(self.Update)
|
||||
self.fetcher.Fetch(glb_chunk_sz)
|
||||
|
||||
|
|
@ -2079,14 +2097,6 @@ def IsSelectable(db, table, sql = ""):
|
|||
return False
|
||||
return True
|
||||
|
||||
# SQL data preparation
|
||||
|
||||
def SQLTableDataPrep(query, count):
|
||||
data = []
|
||||
for i in xrange(count):
|
||||
data.append(query.value(i))
|
||||
return data
|
||||
|
||||
# SQL table data model item
|
||||
|
||||
class SQLTableItem():
|
||||
|
|
@ -2110,7 +2120,7 @@ class SQLTableModel(TableModel):
|
|||
self.more = True
|
||||
self.populated = 0
|
||||
self.column_headers = column_headers
|
||||
self.fetcher = SQLFetcher(glb, sql, lambda x, y=len(column_headers): SQLTableDataPrep(x, y), self.AddSample)
|
||||
self.fetcher = SQLFetcher(glb, sql, lambda x, y=len(column_headers): self.SQLTableDataPrep(x, y), self.AddSample)
|
||||
self.fetcher.done.connect(self.Update)
|
||||
self.fetcher.Fetch(glb_chunk_sz)
|
||||
|
||||
|
|
@ -2154,6 +2164,12 @@ class SQLTableModel(TableModel):
|
|||
def columnHeader(self, column):
|
||||
return self.column_headers[column]
|
||||
|
||||
def SQLTableDataPrep(self, query, count):
|
||||
data = []
|
||||
for i in xrange(count):
|
||||
data.append(query.value(i))
|
||||
return data
|
||||
|
||||
# SQL automatic table data model
|
||||
|
||||
class SQLAutoTableModel(SQLTableModel):
|
||||
|
|
@ -2182,8 +2198,32 @@ class SQLAutoTableModel(SQLTableModel):
|
|||
QueryExec(query, "SELECT column_name FROM information_schema.columns WHERE table_schema = '" + schema + "' and table_name = '" + select_table_name + "'")
|
||||
while query.next():
|
||||
column_headers.append(query.value(0))
|
||||
if pyside_version_1 and sys.version_info[0] == 3:
|
||||
if table_name == "samples_view":
|
||||
self.SQLTableDataPrep = self.samples_view_DataPrep
|
||||
if table_name == "samples":
|
||||
self.SQLTableDataPrep = self.samples_DataPrep
|
||||
super(SQLAutoTableModel, self).__init__(glb, sql, column_headers, parent)
|
||||
|
||||
def samples_view_DataPrep(self, query, count):
|
||||
data = []
|
||||
data.append(query.value(0))
|
||||
# Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string
|
||||
data.append("{:>19}".format(query.value(1)))
|
||||
for i in xrange(2, count):
|
||||
data.append(query.value(i))
|
||||
return data
|
||||
|
||||
def samples_DataPrep(self, query, count):
|
||||
data = []
|
||||
for i in xrange(9):
|
||||
data.append(query.value(i))
|
||||
# Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string
|
||||
data.append("{:>19}".format(query.value(9)))
|
||||
for i in xrange(10, count):
|
||||
data.append(query.value(i))
|
||||
return data
|
||||
|
||||
# Base class for custom ResizeColumnsToContents
|
||||
|
||||
class ResizeColumnsToContentsBase(QObject):
|
||||
|
|
@ -2868,9 +2908,13 @@ class LibXED():
|
|||
ok = self.xed_format_context(2, inst.xedp, inst.bufferp, sizeof(inst.buffer), ip, 0, 0)
|
||||
if not ok:
|
||||
return 0, ""
|
||||
if sys.version_info[0] == 2:
|
||||
result = inst.buffer.value
|
||||
else:
|
||||
result = inst.buffer.value.decode()
|
||||
# Return instruction length and the disassembled instruction text
|
||||
# For now, assume the length is in byte 166
|
||||
return inst.xedd[166], inst.buffer.value
|
||||
return inst.xedd[166], result
|
||||
|
||||
def TryOpen(file_name):
|
||||
try:
|
||||
|
|
@ -2886,9 +2930,14 @@ def Is64Bit(f):
|
|||
header = f.read(7)
|
||||
f.seek(pos)
|
||||
magic = header[0:4]
|
||||
eclass = ord(header[4])
|
||||
encoding = ord(header[5])
|
||||
version = ord(header[6])
|
||||
if sys.version_info[0] == 2:
|
||||
eclass = ord(header[4])
|
||||
encoding = ord(header[5])
|
||||
version = ord(header[6])
|
||||
else:
|
||||
eclass = header[4]
|
||||
encoding = header[5]
|
||||
version = header[6]
|
||||
if magic == chr(127) + "ELF" and eclass > 0 and eclass < 3 and encoding > 0 and encoding < 3 and version == 1:
|
||||
result = True if eclass == 2 else False
|
||||
return result
|
||||
|
|
|
|||
|
|
@ -1,15 +1,18 @@
|
|||
#!/bin/sh
|
||||
# SPDX-License-Identifier: LGPL-2.1
|
||||
|
||||
if [ $# -ne 2 ] ; then
|
||||
if [ $# -ne 3 ] ; then
|
||||
[ $# -eq 1 ] && hostarch=$1 || hostarch=`uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/`
|
||||
linux_header_dir=tools/include/uapi/linux
|
||||
header_dir=tools/include/uapi/asm-generic
|
||||
arch_header_dir=tools/arch/${hostarch}/include/uapi/asm
|
||||
else
|
||||
header_dir=$1
|
||||
arch_header_dir=$2
|
||||
linux_header_dir=$1
|
||||
header_dir=$2
|
||||
arch_header_dir=$3
|
||||
fi
|
||||
|
||||
linux_mman=${linux_header_dir}/mman.h
|
||||
arch_mman=${arch_header_dir}/mman.h
|
||||
|
||||
# those in egrep -vw are flags, we want just the bits
|
||||
|
|
@ -20,6 +23,11 @@ egrep -q $regex ${arch_mman} && \
|
|||
(egrep $regex ${arch_mman} | \
|
||||
sed -r "s/$regex/\2 \1/g" | \
|
||||
xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
|
||||
egrep -q $regex ${linux_mman} && \
|
||||
(egrep $regex ${linux_mman} | \
|
||||
egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \
|
||||
sed -r "s/$regex/\2 \1/g" | \
|
||||
xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
|
||||
([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.*' ${arch_mman}) &&
|
||||
(egrep $regex ${header_dir}/mman-common.h | \
|
||||
egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \
|
||||
|
|
|
|||
|
|
@ -387,6 +387,7 @@ cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder,
|
|||
break;
|
||||
case OCSD_INSTR_ISB:
|
||||
case OCSD_INSTR_DSB_DMB:
|
||||
case OCSD_INSTR_WFI_WFE:
|
||||
case OCSD_INSTR_OTHER:
|
||||
default:
|
||||
packet->last_instr_taken_branch = false;
|
||||
|
|
|
|||
|
|
@ -231,35 +231,6 @@ void perf_evlist__set_leader(struct perf_evlist *evlist)
|
|||
}
|
||||
}
|
||||
|
||||
void perf_event_attr__set_max_precise_ip(struct perf_event_attr *pattr)
|
||||
{
|
||||
struct perf_event_attr attr = {
|
||||
.type = PERF_TYPE_HARDWARE,
|
||||
.config = PERF_COUNT_HW_CPU_CYCLES,
|
||||
.exclude_kernel = 1,
|
||||
.precise_ip = 3,
|
||||
};
|
||||
|
||||
event_attr_init(&attr);
|
||||
|
||||
/*
|
||||
* Unnamed union member, not supported as struct member named
|
||||
* initializer in older compilers such as gcc 4.4.7
|
||||
*/
|
||||
attr.sample_period = 1;
|
||||
|
||||
while (attr.precise_ip != 0) {
|
||||
int fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
|
||||
if (fd != -1) {
|
||||
close(fd);
|
||||
break;
|
||||
}
|
||||
--attr.precise_ip;
|
||||
}
|
||||
|
||||
pattr->precise_ip = attr.precise_ip;
|
||||
}
|
||||
|
||||
int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise)
|
||||
{
|
||||
struct perf_evsel *evsel = perf_evsel__new_cycles(precise);
|
||||
|
|
|
|||
|
|
@ -315,8 +315,6 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
|
|||
void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
|
||||
struct perf_evsel *tracking_evsel);
|
||||
|
||||
void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr);
|
||||
|
||||
struct perf_evsel *
|
||||
perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
|
||||
|
||||
|
|
|
|||
|
|
@ -295,7 +295,6 @@ struct perf_evsel *perf_evsel__new_cycles(bool precise)
|
|||
if (!precise)
|
||||
goto new_event;
|
||||
|
||||
perf_event_attr__set_max_precise_ip(&attr);
|
||||
/*
|
||||
* Now let the usual logic to set up the perf_event_attr defaults
|
||||
* to kick in when we return and before perf_evsel__open() is called.
|
||||
|
|
@ -305,6 +304,8 @@ new_event:
|
|||
if (evsel == NULL)
|
||||
goto out;
|
||||
|
||||
evsel->precise_max = true;
|
||||
|
||||
/* use asprintf() because free(evsel) assumes name is allocated */
|
||||
if (asprintf(&evsel->name, "cycles%s%s%.*s",
|
||||
(attr.precise_ip || attr.exclude_kernel) ? ":" : "",
|
||||
|
|
@ -1083,7 +1084,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
|
|||
}
|
||||
|
||||
if (evsel->precise_max)
|
||||
perf_event_attr__set_max_precise_ip(attr);
|
||||
attr->precise_ip = 3;
|
||||
|
||||
if (opts->all_user) {
|
||||
attr->exclude_kernel = 1;
|
||||
|
|
@ -1749,6 +1750,59 @@ static bool ignore_missing_thread(struct perf_evsel *evsel,
|
|||
return true;
|
||||
}
|
||||
|
||||
static void display_attr(struct perf_event_attr *attr)
|
||||
{
|
||||
if (verbose >= 2) {
|
||||
fprintf(stderr, "%.60s\n", graph_dotted_line);
|
||||
fprintf(stderr, "perf_event_attr:\n");
|
||||
perf_event_attr__fprintf(stderr, attr, __open_attr__fprintf, NULL);
|
||||
fprintf(stderr, "%.60s\n", graph_dotted_line);
|
||||
}
|
||||
}
|
||||
|
||||
static int perf_event_open(struct perf_evsel *evsel,
|
||||
pid_t pid, int cpu, int group_fd,
|
||||
unsigned long flags)
|
||||
{
|
||||
int precise_ip = evsel->attr.precise_ip;
|
||||
int fd;
|
||||
|
||||
while (1) {
|
||||
pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx",
|
||||
pid, cpu, group_fd, flags);
|
||||
|
||||
fd = sys_perf_event_open(&evsel->attr, pid, cpu, group_fd, flags);
|
||||
if (fd >= 0)
|
||||
break;
|
||||
|
||||
/*
|
||||
* Do quick precise_ip fallback if:
|
||||
* - there is precise_ip set in perf_event_attr
|
||||
* - maximum precise is requested
|
||||
* - sys_perf_event_open failed with ENOTSUP error,
|
||||
* which is associated with wrong precise_ip
|
||||
*/
|
||||
if (!precise_ip || !evsel->precise_max || (errno != ENOTSUP))
|
||||
break;
|
||||
|
||||
/*
|
||||
* We tried all the precise_ip values, and it's
|
||||
* still failing, so leave it to standard fallback.
|
||||
*/
|
||||
if (!evsel->attr.precise_ip) {
|
||||
evsel->attr.precise_ip = precise_ip;
|
||||
break;
|
||||
}
|
||||
|
||||
pr_debug2("\nsys_perf_event_open failed, error %d\n", -ENOTSUP);
|
||||
evsel->attr.precise_ip--;
|
||||
pr_debug2("decreasing precise_ip by one (%d)\n", evsel->attr.precise_ip);
|
||||
display_attr(&evsel->attr);
|
||||
}
|
||||
|
||||
return fd;
|
||||
}
|
||||
|
||||
int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
|
||||
struct thread_map *threads)
|
||||
{
|
||||
|
|
@ -1824,12 +1878,7 @@ retry_sample_id:
|
|||
if (perf_missing_features.sample_id_all)
|
||||
evsel->attr.sample_id_all = 0;
|
||||
|
||||
if (verbose >= 2) {
|
||||
fprintf(stderr, "%.60s\n", graph_dotted_line);
|
||||
fprintf(stderr, "perf_event_attr:\n");
|
||||
perf_event_attr__fprintf(stderr, &evsel->attr, __open_attr__fprintf, NULL);
|
||||
fprintf(stderr, "%.60s\n", graph_dotted_line);
|
||||
}
|
||||
display_attr(&evsel->attr);
|
||||
|
||||
for (cpu = 0; cpu < cpus->nr; cpu++) {
|
||||
|
||||
|
|
@ -1841,13 +1890,10 @@ retry_sample_id:
|
|||
|
||||
group_fd = get_group_fd(evsel, cpu, thread);
|
||||
retry_open:
|
||||
pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx",
|
||||
pid, cpus->map[cpu], group_fd, flags);
|
||||
|
||||
test_attr__ready();
|
||||
|
||||
fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu],
|
||||
group_fd, flags);
|
||||
fd = perf_event_open(evsel, pid, cpus->map[cpu],
|
||||
group_fd, flags);
|
||||
|
||||
FD(evsel, cpu, thread) = fd;
|
||||
|
||||
|
|
|
|||
|
|
@ -251,19 +251,15 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
|
|||
if (!(decoder->tsc_ctc_ratio_n % decoder->tsc_ctc_ratio_d))
|
||||
decoder->tsc_ctc_mult = decoder->tsc_ctc_ratio_n /
|
||||
decoder->tsc_ctc_ratio_d;
|
||||
|
||||
/*
|
||||
* Allow for timestamps appearing to backwards because a TSC
|
||||
* packet has slipped past a MTC packet, so allow 2 MTC ticks
|
||||
* or ...
|
||||
*/
|
||||
decoder->tsc_slip = multdiv(2 << decoder->mtc_shift,
|
||||
decoder->tsc_ctc_ratio_n,
|
||||
decoder->tsc_ctc_ratio_d);
|
||||
}
|
||||
/* ... or 0x100 paranoia */
|
||||
if (decoder->tsc_slip < 0x100)
|
||||
decoder->tsc_slip = 0x100;
|
||||
|
||||
/*
|
||||
* A TSC packet can slip past MTC packets so that the timestamp appears
|
||||
* to go backwards. One estimate is that can be up to about 40 CPU
|
||||
* cycles, which is certainly less than 0x1000 TSC ticks, but accept
|
||||
* slippage an order of magnitude more to be on the safe side.
|
||||
*/
|
||||
decoder->tsc_slip = 0x10000;
|
||||
|
||||
intel_pt_log("timestamp: mtc_shift %u\n", decoder->mtc_shift);
|
||||
intel_pt_log("timestamp: tsc_ctc_ratio_n %u\n", decoder->tsc_ctc_ratio_n);
|
||||
|
|
|
|||
|
|
@ -1421,6 +1421,20 @@ static void machine__set_kernel_mmap(struct machine *machine,
|
|||
machine->vmlinux_map->end = ~0ULL;
|
||||
}
|
||||
|
||||
static void machine__update_kernel_mmap(struct machine *machine,
|
||||
u64 start, u64 end)
|
||||
{
|
||||
struct map *map = machine__kernel_map(machine);
|
||||
|
||||
map__get(map);
|
||||
map_groups__remove(&machine->kmaps, map);
|
||||
|
||||
machine__set_kernel_mmap(machine, start, end);
|
||||
|
||||
map_groups__insert(&machine->kmaps, map);
|
||||
map__put(map);
|
||||
}
|
||||
|
||||
int machine__create_kernel_maps(struct machine *machine)
|
||||
{
|
||||
struct dso *kernel = machine__get_kernel(machine);
|
||||
|
|
@ -1453,17 +1467,11 @@ int machine__create_kernel_maps(struct machine *machine)
|
|||
goto out_put;
|
||||
}
|
||||
|
||||
/* we have a real start address now, so re-order the kmaps */
|
||||
map = machine__kernel_map(machine);
|
||||
|
||||
map__get(map);
|
||||
map_groups__remove(&machine->kmaps, map);
|
||||
|
||||
/* assume it's the last in the kmaps */
|
||||
machine__set_kernel_mmap(machine, addr, ~0ULL);
|
||||
|
||||
map_groups__insert(&machine->kmaps, map);
|
||||
map__put(map);
|
||||
/*
|
||||
* we have a real start address now, so re-order the kmaps
|
||||
* assume it's the last in the kmaps
|
||||
*/
|
||||
machine__update_kernel_mmap(machine, addr, ~0ULL);
|
||||
}
|
||||
|
||||
if (machine__create_extra_kernel_maps(machine, kernel))
|
||||
|
|
@ -1599,7 +1607,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
|
|||
if (strstr(kernel->long_name, "vmlinux"))
|
||||
dso__set_short_name(kernel, "[kernel.vmlinux]", false);
|
||||
|
||||
machine__set_kernel_mmap(machine, event->mmap.start,
|
||||
machine__update_kernel_mmap(machine, event->mmap.start,
|
||||
event->mmap.start + event->mmap.len);
|
||||
|
||||
/*
|
||||
|
|
|
|||
|
|
@ -732,10 +732,20 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
|
|||
|
||||
if (!is_arm_pmu_core(name)) {
|
||||
pname = pe->pmu ? pe->pmu : "cpu";
|
||||
|
||||
/*
|
||||
* uncore alias may be from different PMU
|
||||
* with common prefix
|
||||
*/
|
||||
if (pmu_is_uncore(name) &&
|
||||
!strncmp(pname, name, strlen(pname)))
|
||||
goto new_alias;
|
||||
|
||||
if (strcmp(pname, name))
|
||||
continue;
|
||||
}
|
||||
|
||||
new_alias:
|
||||
/* need type casts to override 'const' */
|
||||
__perf_pmu__new_alias(head, NULL, (char *)pe->name,
|
||||
(char *)pe->desc, (char *)pe->event,
|
||||
|
|
|
|||
Loading…
Reference in New Issue