mirror of
git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2025-09-04 20:19:47 +08:00
4fa118e5b7
- Allow RTLA to collect data via BPF The current implementation of rtla uses libtracefs and libtraceevent to pull sample events generated by the timerlat tracer from the trace buffer. rtla then processes the sample by updating the histogram and summary (current, maximum, minimum, and sum values) as well as checks if tracing has been stopped due to threshold overflow. In use cases where a large number of samples is being generated, that is, with measurements running on many CPUs and with a low interval, this sample processing design causes a significant CPU load on the rtla side. Furthermore, with >100 CPUs and 100us interval, rtla was reported as not being able to keep up with the samples and dropping most of them, leading to it being unusable. Change the way the timerlat trace processes samples by attaching a BPF program to the trace event using the BPF skeleton feature of bpftool. Unlike the current implementation, the BPF implementation does not check whether tracing is stopped (in BPF mode, tracing is always off to improve performance), but waits for a write to a BPF ringbuffer instead. This allows rtla to exit immediately when a threshold is violated, without waiting for the next iteration of the while loop. If the requirements for the BPF implementation are not met, either at build time or at run time, the current implementation is used as fallback. Which implementation is being used can be seen when running rtla timerlat with "-D" option. rtla can be forced to run in non-BPF mode by setting the RTLA_NO_BPF option to 1, for debugging purposes. - Fix LD_FLAGS from being dropped in build - Refactor code to remove duplication of save_trace_to_file - Always set options and do not rely on default settings Do not rely on the default kernel settings of the tracers when starting. They could have been changed by the user which gives inconsistent results. Always set the options that rtla expects. - Add creation of ctags and TAGS for traversing code -----BEGIN PGP SIGNATURE----- iIoEABYIADIWIQRRSw7ePDh/lE+zeZMp5XQQmuv6qgUCZ+WBgRQccm9zdGVkdEBn b29kbWlzLm9yZwAKCRAp5XQQmuv6qg54AQDCOChaSSBiUkD0VoPKIeDMlPfvO5Qz Xvrst5gtopfKFgEA12/9Lll/sh1eoc4saeGBooNY48HBUMjmX3KNFB14PQg= =aHFu -----END PGP SIGNATURE----- Merge tag 'trace-tools-v6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing tooling updates from Steven Rostedt: - Allow RTLA to collect data via BPF The current implementation of rtla uses libtracefs and libtraceevent to pull sample events generated by the timerlat tracer from the trace buffer. rtla then processes the sample by updating the histogram and summary (current, maximum, minimum, and sum values) as well as checks if tracing has been stopped due to threshold overflow. In use cases where a large number of samples is being generated, that is, with measurements running on many CPUs and with a low interval, this sample processing design causes a significant CPU load on the rtla side. Furthermore, with >100 CPUs and 100us interval, rtla was reported as not being able to keep up with the samples and dropping most of them, leading to it being unusable. Change the way the timerlat trace processes samples by attaching a BPF program to the trace event using the BPF skeleton feature of bpftool. Unlike the current implementation, the BPF implementation does not check whether tracing is stopped (in BPF mode, tracing is always off to improve performance), but waits for a write to a BPF ringbuffer instead. This allows rtla to exit immediately when a threshold is violated, without waiting for the next iteration of the while loop. If the requirements for the BPF implementation are not met, either at build time or at run time, the current implementation is used as fallback. Which implementation is being used can be seen when running rtla timerlat with "-D" option. rtla can be forced to run in non-BPF mode by setting the RTLA_NO_BPF option to 1, for debugging purposes. - Fix LD_FLAGS from being dropped in build - Refactor code to remove duplication of save_trace_to_file - Always set options and do not rely on default settings Do not rely on the default kernel settings of the tracers when starting. They could have been changed by the user which gives inconsistent results. Always set the options that rtla expects. - Add creation of ctags and TAGS for traversing code * tag 'trace-tools-v6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: rtla: Add the ability to create ctags and etags rtla/tests: Test setting default options rtla/tests: Reset osnoise options before check rtla: Always set all tracer options rtla/osnoise: Set OSNOISE_WORKLOAD to true rtla: Unify apply_config between top and hist rtla/osnoise: Unify params struct rtla: Fix segfault in save_trace_to_file call tools/build: Use SYSTEM_BPFTOOL for system bpftool rtla: Refactor save_trace_to_file tools/rv: Keep user LDFLAGS in build rtla/timerlat: Test BPF mode rtla/timerlat_top: Use BPF to collect samples rtla/timerlat_top: Move divisor to update rtla/timerlat_hist: Use BPF to collect samples rtla/timerlat: Add BPF skeleton to collect samples rtla: Add optional dependency on BPF tooling tools/build: Add bpftool-skeletons feature test rtla/timerlat: Unify params struct
225 lines
6.9 KiB
Makefile
225 lines
6.9 KiB
Makefile
# SPDX-License-Identifier: GPL-2.0
|
|
ifneq ($(O),)
|
|
ifeq ($(origin O), command line)
|
|
$(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
|
|
EXTRA_WARNINGS += -Wno-type-limits
|
|
|
|
# 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) = $(2)))
|
|
endef
|
|
|
|
ifneq ($(LLVM),)
|
|
ifneq ($(filter %/,$(LLVM)),)
|
|
LLVM_PREFIX := $(LLVM)
|
|
else ifneq ($(filter -%,$(LLVM)),)
|
|
LLVM_SUFFIX := $(LLVM)
|
|
endif
|
|
|
|
$(call allow-override,CC,$(LLVM_PREFIX)clang$(LLVM_SUFFIX))
|
|
$(call allow-override,AR,$(LLVM_PREFIX)llvm-ar$(LLVM_SUFFIX))
|
|
$(call allow-override,LD,$(LLVM_PREFIX)ld.lld$(LLVM_SUFFIX))
|
|
$(call allow-override,CXX,$(LLVM_PREFIX)clang++$(LLVM_SUFFIX))
|
|
$(call allow-override,STRIP,$(LLVM_PREFIX)llvm-strip$(LLVM_SUFFIX))
|
|
else
|
|
# 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)
|
|
endif
|
|
|
|
CC_NO_CLANG := $(shell $(CC) -dM -E -x c /dev/null | grep -Fq "__clang__"; echo $$?)
|
|
|
|
ifneq ($(LLVM),)
|
|
HOSTAR ?= $(LLVM_PREFIX)llvm-ar$(LLVM_SUFFIX)
|
|
HOSTCC ?= $(LLVM_PREFIX)clang$(LLVM_SUFFIX)
|
|
HOSTLD ?= $(LLVM_PREFIX)ld.lld$(LLVM_SUFFIX)
|
|
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
|
|
|
|
# Some tools require bpftool
|
|
SYSTEM_BPFTOOL ?= bpftool
|
|
|
|
ifeq ($(CC_NO_CLANG), 1)
|
|
EXTRA_WARNINGS += -Wstrict-aliasing=3
|
|
|
|
else ifneq ($(CROSS_COMPILE),)
|
|
# Allow userspace to override CLANG_CROSS_FLAGS to specify their own
|
|
# sysroots and flags or to avoid the GCC call in pure Clang builds.
|
|
ifeq ($(CLANG_CROSS_FLAGS),)
|
|
CLANG_CROSS_FLAGS := --target=$(notdir $(CROSS_COMPILE:%-=%))
|
|
GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)gcc 2>/dev/null))
|
|
ifneq ($(GCC_TOOLCHAIN_DIR),)
|
|
CLANG_CROSS_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE))
|
|
CLANG_CROSS_FLAGS += --sysroot=$(shell $(CROSS_COMPILE)gcc -print-sysroot)
|
|
CLANG_CROSS_FLAGS += --gcc-toolchain=$(realpath $(GCC_TOOLCHAIN_DIR)/..)
|
|
endif # GCC_TOOLCHAIN_DIR
|
|
endif # CLANG_CROSS_FLAGS
|
|
CFLAGS += $(CLANG_CROSS_FLAGS)
|
|
AFLAGS += $(CLANG_CROSS_FLAGS)
|
|
else
|
|
CLANG_CROSS_FLAGS :=
|
|
endif # CROSS_COMPILE
|
|
|
|
# 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://lore.kernel.org/lkml/9a8748490611281710g78402fbeh8ff7fcc162dbcbca@mail.gmail.com/
|
|
# 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
|
|
|
|
# Beautify output
|
|
# ---------------------------------------------------------------------------
|
|
#
|
|
# Most of build commands in Kbuild start with "cmd_". You can optionally define
|
|
# "quiet_cmd_*". If defined, the short log is printed. Otherwise, no log from
|
|
# that command is printed by default.
|
|
#
|
|
# e.g.)
|
|
# quiet_cmd_depmod = DEPMOD $(MODLIB)
|
|
# cmd_depmod = $(srctree)/scripts/depmod.sh $(DEPMOD) $(KERNELRELEASE)
|
|
#
|
|
# A simple variant is to prefix commands with $(Q) - that's useful
|
|
# for commands that shall be hidden in non-verbose mode.
|
|
#
|
|
# $(Q)$(MAKE) $(build)=scripts/basic
|
|
#
|
|
# To put more focus on warnings, be less verbose as default
|
|
# Use 'make V=1' to see the full commands
|
|
|
|
ifeq ($(V),1)
|
|
quiet =
|
|
Q =
|
|
else
|
|
quiet = quiet_
|
|
Q = @
|
|
endif
|
|
|
|
# If the user is running make -s (silent mode), suppress echoing of commands
|
|
# make-4.0 (and later) keep single letter options in the 1st word of MAKEFLAGS.
|
|
ifeq ($(filter 3.%,$(MAKE_VERSION)),)
|
|
short-opts := $(firstword -$(MAKEFLAGS))
|
|
else
|
|
short-opts := $(filter-out --%,$(MAKEFLAGS))
|
|
endif
|
|
|
|
ifneq ($(findstring s,$(short-opts)),)
|
|
silent=1
|
|
quiet=silent_
|
|
endif
|
|
|
|
export quiet Q
|
|
|
|
#
|
|
# 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 ' GENSKEL '$@;
|
|
|
|
descend = \
|
|
+@echo ' DESCEND '$(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 := \#
|