mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-25 05:34:00 +08:00
3a36281a17
- Support instruction latency in 'perf report', with both memory latency (weight) and instruction latency information, users can locate expensive load instructions and understand time spent in different stages. - Extend 'perf c2c' to display the number of loads which were blocked by data or address conflict. - Add 'perf stat' support for L2 topdown events in systems such as Intel's Sapphire rapids server. - Add support for PERF_SAMPLE_CODE_PAGE_SIZE in various tools, as a sort key, for instance: perf report --stdio --sort=comm,symbol,code_page_size - New 'perf daemon' command to run long running sessions while providing a way to control the enablement of events without restarting a traditional 'perf record' session. - Enable counting events for BPF programs in 'perf stat' just like for other targets (tid, cgroup, cpu, etc), e.g.: # perf stat -e ref-cycles,cycles -b 254 -I 1000 1.487903822 115,200 ref-cycles 1.487903822 86,012 cycles 2.489147029 80,560 ref-cycles 2.489147029 73,784 cycles ^C# The example above counts 'cycles' and 'ref-cycles' of BPF program of id 254. It is similar to bpftool-prog-profile command, but more flexible. - Support the new layout for PERF_RECORD_MMAP2 to carry the DSO build-id using infrastructure generalised from the eBPF subsystem, removing the need for traversing the perf.data file to collect build-ids at the end of 'perf record' sessions and helping with long running sessions where binaries can get replaced in updates, leading to possible mis-resolution of symbols. - Support filtering by hex address in 'perf script'. - Support DSO filter in 'perf script', like in other perf tools. - Add namespaces support to 'perf inject' - Add support for SDT (Dtrace Style Markers) events on ARM64. perf record: - Fix handling of eventfd() when draining a buffer in 'perf record'. - Improvements to the generation of metadata events for pre-existing threads (mmaps, comm, etc), speeding up the work done at the start of system wide or per CPU 'perf record' sessions. Hardware tracing: - Initial support for tracing KVM with Intel PT. - Intel PT fixes for IPC - Support Intel PT PSB (synchronization packets) events. - Automatically group aux-output events to overcome --filter syntax. - Enable PERF_SAMPLE_DATA_SRC on ARMs SPE. - Update ARM's CoreSight hardware tracing OpenCSD library to v1.0.0. perf annotate TUI: - Fix handling of 'k' ("show line number") hotkey - Fix jump parsing for C++ code. perf probe: - Add protection to avoid endless loop. cgroups: - Avoid reading cgroup mountpoint multiple times, caching it. - Fix handling of cgroup v1/v2 in mixed hierarchy. Symbol resolving: - Add OCaml symbol demangling. - Further fixes for handling PE executables when using perf with Wine and .exe/.dll files. - Fix 'perf unwind' DSO handling. - Resolve symbols against debug file first, to deal with artifacts related to LTO. - Fix gap between kernel end and module start on powerpc. Reporting tools: - The DSO filter shouldn't show samples in unresolved maps. - Improve debuginfod support in various tools. build ids: - Fix 16-byte build ids in 'perf buildid-cache', add a 'perf test' entry for that case. perf test: - Support for PERF_SAMPLE_WEIGHT_STRUCT. - Add test case for PERF_SAMPLE_CODE_PAGE_SIZE. - Shell based tests for 'perf daemon's commands ('start', 'stop, 'reconfig', 'list', etc). - ARM cs-etm 'perf test' fixes. - Add parse-metric memory bandwidth testcase. Compiler related: - Fix 'perf probe' kretprobe issue caused by gcc 11 bug when used with -fpatchable-function-entry. - Fix ARM64 build with gcc 11's -Wformat-overflow. - Fix unaligned access in sample parsing test. - Fix printf conversion specifier for IP addresses on arm64, s390 and powerpc. Arch specific: - Support exposing Performance Monitor Counter SPRs as part of extended regs on powerpc. - Add JSON 'perf stat' metrics for ARM64's imx8mp, imx8mq and imx8mn DDR, fix imx8mm ones. - Fix common and uarch events for ARM64's A76 and Ampere eMag Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> -----BEGIN PGP SIGNATURE----- iHUEABYIAB0WIQR2GiIUctdOfX2qHhGyPKLppCJ+JwUCYDANTQAKCRCyPKLppCJ+ J4veAQCISY1BPHscUTRYhq9cwU/Zs0ImtX7zDT4jxaP39JkduAD/eSqYavAJrtQh HDyEiTgZ7CQSp5eCbXkzrnet4n3G9QE= =H/Jk -----END PGP SIGNATURE----- Merge tag 'perf-tools-for-v5.12-2020-02-19' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux Pull perf tool updates from Arnaldo Carvalho de Melo: "New features: - Support instruction latency in 'perf report', with both memory latency (weight) and instruction latency information, users can locate expensive load instructions and understand time spent in different stages. - Extend 'perf c2c' to display the number of loads which were blocked by data or address conflict. - Add 'perf stat' support for L2 topdown events in systems such as Intel's Sapphire rapids server. - Add support for PERF_SAMPLE_CODE_PAGE_SIZE in various tools, as a sort key, for instance: perf report --stdio --sort=comm,symbol,code_page_size - New 'perf daemon' command to run long running sessions while providing a way to control the enablement of events without restarting a traditional 'perf record' session. - Enable counting events for BPF programs in 'perf stat' just like for other targets (tid, cgroup, cpu, etc), e.g.: # perf stat -e ref-cycles,cycles -b 254 -I 1000 1.487903822 115,200 ref-cycles 1.487903822 86,012 cycles 2.489147029 80,560 ref-cycles 2.489147029 73,784 cycles ^C The example above counts 'cycles' and 'ref-cycles' of BPF program of id 254. It is similar to bpftool-prog-profile command, but more flexible. - Support the new layout for PERF_RECORD_MMAP2 to carry the DSO build-id using infrastructure generalised from the eBPF subsystem, removing the need for traversing the perf.data file to collect build-ids at the end of 'perf record' sessions and helping with long running sessions where binaries can get replaced in updates, leading to possible mis-resolution of symbols. - Support filtering by hex address in 'perf script'. - Support DSO filter in 'perf script', like in other perf tools. - Add namespaces support to 'perf inject' - Add support for SDT (Dtrace Style Markers) events on ARM64. perf record: - Fix handling of eventfd() when draining a buffer in 'perf record'. - Improvements to the generation of metadata events for pre-existing threads (mmaps, comm, etc), speeding up the work done at the start of system wide or per CPU 'perf record' sessions. Hardware tracing: - Initial support for tracing KVM with Intel PT. - Intel PT fixes for IPC - Support Intel PT PSB (synchronization packets) events. - Automatically group aux-output events to overcome --filter syntax. - Enable PERF_SAMPLE_DATA_SRC on ARMs SPE. - Update ARM's CoreSight hardware tracing OpenCSD library to v1.0.0. perf annotate TUI: - Fix handling of 'k' ("show line number") hotkey - Fix jump parsing for C++ code. perf probe: - Add protection to avoid endless loop. cgroups: - Avoid reading cgroup mountpoint multiple times, caching it. - Fix handling of cgroup v1/v2 in mixed hierarchy. Symbol resolving: - Add OCaml symbol demangling. - Further fixes for handling PE executables when using perf with Wine and .exe/.dll files. - Fix 'perf unwind' DSO handling. - Resolve symbols against debug file first, to deal with artifacts related to LTO. - Fix gap between kernel end and module start on powerpc. Reporting tools: - The DSO filter shouldn't show samples in unresolved maps. - Improve debuginfod support in various tools. build ids: - Fix 16-byte build ids in 'perf buildid-cache', add a 'perf test' entry for that case. perf test: - Support for PERF_SAMPLE_WEIGHT_STRUCT. - Add test case for PERF_SAMPLE_CODE_PAGE_SIZE. - Shell based tests for 'perf daemon's commands ('start', 'stop, 'reconfig', 'list', etc). - ARM cs-etm 'perf test' fixes. - Add parse-metric memory bandwidth testcase. Compiler related: - Fix 'perf probe' kretprobe issue caused by gcc 11 bug when used with -fpatchable-function-entry. - Fix ARM64 build with gcc 11's -Wformat-overflow. - Fix unaligned access in sample parsing test. - Fix printf conversion specifier for IP addresses on arm64, s390 and powerpc. Arch specific: - Support exposing Performance Monitor Counter SPRs as part of extended regs on powerpc. - Add JSON 'perf stat' metrics for ARM64's imx8mp, imx8mq and imx8mn DDR, fix imx8mm ones. - Fix common and uarch events for ARM64's A76 and Ampere eMag" * tag 'perf-tools-for-v5.12-2020-02-19' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (148 commits) perf buildid-cache: Don't skip 16-byte build-ids perf buildid-cache: Add test for 16-byte build-id perf symbol: Remove redundant libbfd checks perf test: Output the sub testing result in cs-etm perf test: Suppress logs in cs-etm testing perf tools: Fix arm64 build error with gcc-11 perf intel-pt: Add documentation for tracing virtual machines perf intel-pt: Split VM-Entry and VM-Exit branches perf intel-pt: Adjust sample flags for VM-Exit perf intel-pt: Allow for a guest kernel address filter perf intel-pt: Support decoding of guest kernel perf machine: Factor out machine__idle_thread() perf machine: Factor out machines__find_guest() perf intel-pt: Amend decoder to track the NR flag perf intel-pt: Retain the last PIP packet payload as is perf intel_pt: Add vmlaunch and vmresume as branches perf script: Add branch types for VM-Entry and VM-Exit perf auxtrace: Automatically group aux-output events perf test: Fix unaligned access in sample parsing test perf tools: Support arch specific PERF_SAMPLE_WEIGHT_STRUCT processing ...
151 lines
4.5 KiB
Makefile
151 lines
4.5 KiB
Makefile
# SPDX-License-Identifier: GPL-2.0
|
|
ifneq ($(O),)
|
|
ifeq ($(origin O), command line)
|
|
dummy := $(if $(shell cd $(PWD); test -d $(O) || echo $(O)),$(error O=$(O) does not exist),)
|
|
ABSOLUTE_O := $(shell cd $(PWD); cd $(O) ; pwd)
|
|
OUTPUT := $(ABSOLUTE_O)/$(if $(subdir),$(subdir)/)
|
|
COMMAND_O := O=$(ABSOLUTE_O)
|
|
ifeq ($(objtree),)
|
|
objtree := $(O)
|
|
endif
|
|
endif
|
|
endif
|
|
|
|
# check that the output directory actually exists
|
|
ifneq ($(OUTPUT),)
|
|
OUTDIR := $(shell cd $(OUTPUT) && pwd)
|
|
$(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
|
|
endif
|
|
|
|
#
|
|
# Include saner warnings here, which can catch bugs:
|
|
#
|
|
EXTRA_WARNINGS := -Wbad-function-cast
|
|
EXTRA_WARNINGS += -Wdeclaration-after-statement
|
|
EXTRA_WARNINGS += -Wformat-security
|
|
EXTRA_WARNINGS += -Wformat-y2k
|
|
EXTRA_WARNINGS += -Winit-self
|
|
EXTRA_WARNINGS += -Wmissing-declarations
|
|
EXTRA_WARNINGS += -Wmissing-prototypes
|
|
EXTRA_WARNINGS += -Wnested-externs
|
|
EXTRA_WARNINGS += -Wno-system-headers
|
|
EXTRA_WARNINGS += -Wold-style-definition
|
|
EXTRA_WARNINGS += -Wpacked
|
|
EXTRA_WARNINGS += -Wredundant-decls
|
|
EXTRA_WARNINGS += -Wstrict-prototypes
|
|
EXTRA_WARNINGS += -Wswitch-default
|
|
EXTRA_WARNINGS += -Wswitch-enum
|
|
EXTRA_WARNINGS += -Wundef
|
|
EXTRA_WARNINGS += -Wwrite-strings
|
|
EXTRA_WARNINGS += -Wformat
|
|
|
|
CC_NO_CLANG := $(shell $(CC) -dM -E -x c /dev/null | grep -Fq "__clang__"; echo $$?)
|
|
|
|
# Makefiles suck: This macro sets a default value of $(2) for the
|
|
# variable named by $(1), unless the variable has been set by
|
|
# environment or command line. This is necessary for CC and AR
|
|
# because make sets default values, so the simpler ?= approach
|
|
# won't work as expected.
|
|
define allow-override
|
|
$(if $(or $(findstring environment,$(origin $(1))),\
|
|
$(findstring command line,$(origin $(1)))),,\
|
|
$(eval $(1) = $(2)))
|
|
endef
|
|
|
|
# Allow setting various cross-compile vars or setting CROSS_COMPILE as a prefix.
|
|
$(call allow-override,CC,$(CROSS_COMPILE)gcc)
|
|
$(call allow-override,AR,$(CROSS_COMPILE)ar)
|
|
$(call allow-override,LD,$(CROSS_COMPILE)ld)
|
|
$(call allow-override,CXX,$(CROSS_COMPILE)g++)
|
|
$(call allow-override,STRIP,$(CROSS_COMPILE)strip)
|
|
|
|
ifneq ($(LLVM),)
|
|
HOSTAR ?= llvm-ar
|
|
HOSTCC ?= clang
|
|
HOSTLD ?= ld.lld
|
|
else
|
|
HOSTAR ?= ar
|
|
HOSTCC ?= gcc
|
|
HOSTLD ?= ld
|
|
endif
|
|
|
|
# Some tools require Clang, LLC and/or LLVM utils
|
|
CLANG ?= clang
|
|
LLC ?= llc
|
|
LLVM_CONFIG ?= llvm-config
|
|
LLVM_OBJCOPY ?= llvm-objcopy
|
|
LLVM_STRIP ?= llvm-strip
|
|
|
|
ifeq ($(CC_NO_CLANG), 1)
|
|
EXTRA_WARNINGS += -Wstrict-aliasing=3
|
|
endif
|
|
|
|
# Hack to avoid type-punned warnings on old systems such as RHEL5:
|
|
# We should be changing CFLAGS and checking gcc version, but this
|
|
# will do for now and keep the above -Wstrict-aliasing=3 in place
|
|
# in newer systems.
|
|
# Needed for the __raw_cmpxchg in tools/arch/x86/include/asm/cmpxchg.h
|
|
#
|
|
# See https://lkml.org/lkml/2006/11/28/253 and https://gcc.gnu.org/gcc-4.8/changes.html,
|
|
# that takes into account Linus's comments (search for Wshadow) for the reasoning about
|
|
# -Wshadow not being interesting before gcc 4.8.
|
|
|
|
ifneq ($(filter 3.%,$(MAKE_VERSION)),) # make-3
|
|
EXTRA_WARNINGS += -fno-strict-aliasing
|
|
EXTRA_WARNINGS += -Wno-shadow
|
|
else
|
|
EXTRA_WARNINGS += -Wshadow
|
|
endif
|
|
|
|
ifneq ($(findstring $(MAKEFLAGS), w),w)
|
|
PRINT_DIR = --no-print-directory
|
|
else
|
|
NO_SUBDIR = :
|
|
endif
|
|
|
|
ifneq ($(findstring s,$(filter-out --%,$(MAKEFLAGS))),)
|
|
silent=1
|
|
endif
|
|
|
|
#
|
|
# Define a callable command for descending to a new directory
|
|
#
|
|
# Call by doing: $(call descend,directory[,target])
|
|
#
|
|
descend = \
|
|
+mkdir -p $(OUTPUT)$(1) && \
|
|
$(MAKE) $(COMMAND_O) subdir=$(if $(subdir),$(subdir)/$(1),$(1)) $(PRINT_DIR) -C $(1) $(2)
|
|
|
|
QUIET_SUBDIR0 = +$(MAKE) $(COMMAND_O) -C # space to separate -C and subdir
|
|
QUIET_SUBDIR1 =
|
|
|
|
ifneq ($(silent),1)
|
|
ifneq ($(V),1)
|
|
QUIET_CC = @echo ' CC '$@;
|
|
QUIET_CC_FPIC = @echo ' CC FPIC '$@;
|
|
QUIET_CLANG = @echo ' CLANG '$@;
|
|
QUIET_AR = @echo ' AR '$@;
|
|
QUIET_LINK = @echo ' LINK '$@;
|
|
QUIET_MKDIR = @echo ' MKDIR '$@;
|
|
QUIET_GEN = @echo ' GEN '$@;
|
|
QUIET_SUBDIR0 = +@subdir=
|
|
QUIET_SUBDIR1 = ;$(NO_SUBDIR) \
|
|
echo ' SUBDIR '$$subdir; \
|
|
$(MAKE) $(PRINT_DIR) -C $$subdir
|
|
QUIET_FLEX = @echo ' FLEX '$@;
|
|
QUIET_BISON = @echo ' BISON '$@;
|
|
QUIET_GENSKEL = @echo ' GEN-SKEL '$@;
|
|
|
|
descend = \
|
|
+@echo ' DESCEND '$(1); \
|
|
mkdir -p $(OUTPUT)$(1) && \
|
|
$(MAKE) $(COMMAND_O) subdir=$(if $(subdir),$(subdir)/$(1),$(1)) $(PRINT_DIR) -C $(1) $(2)
|
|
|
|
QUIET_CLEAN = @printf ' CLEAN %s\n' $1;
|
|
QUIET_INSTALL = @printf ' INSTALL %s\n' $1;
|
|
QUIET_UNINST = @printf ' UNINST %s\n' $1;
|
|
endif
|
|
endif
|
|
|
|
pound := \#
|