mirror of
https://git.proxmox.com/git/mirror_ubuntu-kernels.git
synced 2025-12-07 18:28:26 +00:00
Patch series "Speed up mremap on large regions", v4.
mremap time can be optimized by moving entries at the PMD/PUD level if the
source and destination addresses are PMD/PUD-aligned and PMD/PUD-sized.
Enable moving at the PMD and PUD levels on arm64 and x86. Other
architectures where this type of move is supported and known to be safe
can also opt-in to these optimizations by enabling HAVE_MOVE_PMD and
HAVE_MOVE_PUD.
Observed Performance Improvements for remapping a PUD-aligned 1GB-sized
region on x86 and arm64:
- HAVE_MOVE_PMD is already enabled on x86 : N/A
- Enabling HAVE_MOVE_PUD on x86 : ~13x speed up
- Enabling HAVE_MOVE_PMD on arm64 : ~ 8x speed up
- Enabling HAVE_MOVE_PUD on arm64 : ~19x speed up
Altogether, HAVE_MOVE_PMD and HAVE_MOVE_PUD
give a total of ~150x speed up on arm64.
This patch (of 4):
Test mremap on regions of various sizes and alignments and validate data
after remapping. Also provide total time for remapping the region which
is useful for performance comparison of the mremap optimizations that move
pages at the PMD/PUD levels if HAVE_MOVE_PMD and/or HAVE_MOVE_PUD are
enabled.
Link: https://lkml.kernel.org/r/20201014005320.2233162-1-kaleshsingh@google.com
Link: https://lkml.kernel.org/r/20201014005320.2233162-2-kaleshsingh@google.com
Signed-off-by: Kalesh Singh <kaleshsingh@google.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Minchan Kim <minchan@google.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Sami Tolvanen <samitolvanen@google.com>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Krzysztof Kozlowski <krzk@kernel.org>
Cc: Frederic Weisbecker <frederic@kernel.org>
Cc: Hassan Naveed <hnaveed@wavecomp.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Gavin Shan <gshan@redhat.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Steven Price <steven.price@arm.com>
Cc: Jia He <justin.he@arm.com>
Cc: Ram Pai <linuxram@us.ibm.com>
Cc: Sandipan Das <sandipan@linux.ibm.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: SeongJae Park <sjpark@amazon.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
158 lines
4.6 KiB
Makefile
158 lines
4.6 KiB
Makefile
# SPDX-License-Identifier: GPL-2.0
|
|
# Makefile for vm selftests
|
|
|
|
include local_config.mk
|
|
|
|
uname_M := $(shell uname -m 2>/dev/null || echo not)
|
|
MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/')
|
|
|
|
# Without this, failed build products remain, with up-to-date timestamps,
|
|
# thus tricking Make (and you!) into believing that All Is Well, in subsequent
|
|
# make invocations:
|
|
.DELETE_ON_ERROR:
|
|
|
|
# Avoid accidental wrong builds, due to built-in rules working just a little
|
|
# bit too well--but not quite as well as required for our situation here.
|
|
#
|
|
# In other words, "make userfaultfd" is supposed to fail to build at all,
|
|
# because this Makefile only supports either "make" (all), or "make /full/path".
|
|
# However, the built-in rules, if not suppressed, will pick up CFLAGS and the
|
|
# initial LDLIBS (but not the target-specific LDLIBS, because those are only
|
|
# set for the full path target!). This causes it to get pretty far into building
|
|
# things despite using incorrect values such as an *occasionally* incomplete
|
|
# LDLIBS.
|
|
MAKEFLAGS += --no-builtin-rules
|
|
|
|
CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS)
|
|
LDLIBS = -lrt -lpthread
|
|
TEST_GEN_FILES = compaction_test
|
|
TEST_GEN_FILES += gup_test
|
|
TEST_GEN_FILES += hmm-tests
|
|
TEST_GEN_FILES += hugepage-mmap
|
|
TEST_GEN_FILES += hugepage-shm
|
|
TEST_GEN_FILES += khugepaged
|
|
TEST_GEN_FILES += map_fixed_noreplace
|
|
TEST_GEN_FILES += map_hugetlb
|
|
TEST_GEN_FILES += map_populate
|
|
TEST_GEN_FILES += mlock-random-test
|
|
TEST_GEN_FILES += mlock2-tests
|
|
TEST_GEN_FILES += mremap_dontunmap
|
|
TEST_GEN_FILES += mremap_test
|
|
TEST_GEN_FILES += on-fault-limit
|
|
TEST_GEN_FILES += thuge-gen
|
|
TEST_GEN_FILES += transhuge-stress
|
|
TEST_GEN_FILES += userfaultfd
|
|
|
|
ifeq ($(ARCH),x86_64)
|
|
CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32)
|
|
CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_64bit_program.c)
|
|
CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_program.c -no-pie)
|
|
|
|
TARGETS := protection_keys
|
|
BINARIES_32 := $(TARGETS:%=%_32)
|
|
BINARIES_64 := $(TARGETS:%=%_64)
|
|
|
|
ifeq ($(CAN_BUILD_WITH_NOPIE),1)
|
|
CFLAGS += -no-pie
|
|
endif
|
|
|
|
ifeq ($(CAN_BUILD_I386),1)
|
|
TEST_GEN_FILES += $(BINARIES_32)
|
|
endif
|
|
|
|
ifeq ($(CAN_BUILD_X86_64),1)
|
|
TEST_GEN_FILES += $(BINARIES_64)
|
|
endif
|
|
else
|
|
|
|
ifneq (,$(findstring $(ARCH),powerpc))
|
|
TEST_GEN_FILES += protection_keys
|
|
endif
|
|
|
|
endif
|
|
|
|
ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64))
|
|
TEST_GEN_FILES += va_128TBswitch
|
|
TEST_GEN_FILES += virtual_address_range
|
|
TEST_GEN_FILES += write_to_hugetlbfs
|
|
endif
|
|
|
|
TEST_PROGS := run_vmtests.sh
|
|
|
|
TEST_FILES := test_vmalloc.sh
|
|
|
|
KSFT_KHDR_INSTALL := 1
|
|
include ../lib.mk
|
|
|
|
ifeq ($(ARCH),x86_64)
|
|
BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32))
|
|
BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64))
|
|
|
|
define gen-target-rule-32
|
|
$(1) $(1)_32: $(OUTPUT)/$(1)_32
|
|
.PHONY: $(1) $(1)_32
|
|
endef
|
|
|
|
define gen-target-rule-64
|
|
$(1) $(1)_64: $(OUTPUT)/$(1)_64
|
|
.PHONY: $(1) $(1)_64
|
|
endef
|
|
|
|
ifeq ($(CAN_BUILD_I386),1)
|
|
$(BINARIES_32): CFLAGS += -m32
|
|
$(BINARIES_32): LDLIBS += -lrt -ldl -lm
|
|
$(BINARIES_32): %_32: %.c
|
|
$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@
|
|
$(foreach t,$(TARGETS),$(eval $(call gen-target-rule-32,$(t))))
|
|
endif
|
|
|
|
ifeq ($(CAN_BUILD_X86_64),1)
|
|
$(BINARIES_64): CFLAGS += -m64
|
|
$(BINARIES_64): LDLIBS += -lrt -ldl
|
|
$(BINARIES_64): %_64: %.c
|
|
$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@
|
|
$(foreach t,$(TARGETS),$(eval $(call gen-target-rule-64,$(t))))
|
|
endif
|
|
|
|
# x86_64 users should be encouraged to install 32-bit libraries
|
|
ifeq ($(CAN_BUILD_I386)$(CAN_BUILD_X86_64),01)
|
|
all: warn_32bit_failure
|
|
|
|
warn_32bit_failure:
|
|
@echo "Warning: you seem to have a broken 32-bit build" 2>&1; \
|
|
echo "environment. This will reduce test coverage of 64-bit" 2>&1; \
|
|
echo "kernels. If you are using a Debian-like distribution," 2>&1; \
|
|
echo "try:"; 2>&1; \
|
|
echo ""; \
|
|
echo " apt-get install gcc-multilib libc6-i386 libc6-dev-i386"; \
|
|
echo ""; \
|
|
echo "If you are using a Fedora-like distribution, try:"; \
|
|
echo ""; \
|
|
echo " yum install glibc-devel.*i686"; \
|
|
exit 0;
|
|
endif
|
|
endif
|
|
|
|
$(OUTPUT)/mlock-random-test: LDLIBS += -lcap
|
|
|
|
$(OUTPUT)/gup_test: ../../../../mm/gup_test.h
|
|
|
|
$(OUTPUT)/hmm-tests: local_config.h
|
|
|
|
# HMM_EXTRA_LIBS may get set in local_config.mk, or it may be left empty.
|
|
$(OUTPUT)/hmm-tests: LDLIBS += $(HMM_EXTRA_LIBS)
|
|
|
|
local_config.mk local_config.h: check_config.sh
|
|
/bin/sh ./check_config.sh $(CC)
|
|
|
|
EXTRA_CLEAN += local_config.mk local_config.h
|
|
|
|
ifeq ($(HMM_EXTRA_LIBS),)
|
|
all: warn_missing_hugelibs
|
|
|
|
warn_missing_hugelibs:
|
|
@echo ; \
|
|
echo "Warning: missing libhugetlbfs support. Some HMM tests will be skipped." ; \
|
|
echo
|
|
endif
|