mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2026-08-30 18:03:10 -04:00
f4806cc63c
Compare the cost of allocating and freeing variable-sized regions using a bitmap, IDA and a Maple Tree. All implementations process the same randomly generated sequence of regions containing up to 32 entries, until the configured capacity is exhausted. The benchmark exercises monotonic allocation into an initially empty pool, followed by reverse-order freeing. It does not model fragmentation or interleaved allocation and freeing, nor does it isolate locking or RCU overhead. Allocation time includes the terminal failed request that detects exhaustion. Run the benchmark at several capacities to show how the approaches scale. Report allocation and free times separately because bitmap, IDA and Maple Tree removal have substantially different costs. On x86/kvm, the output example is: Start testing bitmap vs IDA vs Maple Tree region allocation memory: bitmap is exact; IDA and Maple Tree are lower bounds Type alloc (ns) free (ns) regions capacity memory (B) Bitmap 93457345 176151 60644 1000000 125000 Maple 11758660 12870146 60644 1000000 1552656 IDA 31066416 20870824 60644 1000000 134864 Bitmap 919119 17679 6032 100000 12504 Maple 1158193 1187140 6032 100000 154640 IDA 2759670 2116004 6032 100000 14288 Bitmap 17120 2043 613 10000 1256 Maple 116350 117537 613 10000 15888 IDA 243396 202654 613 10000 1872 Bitmap 1220 262 55 1000 128 Maple 12076 10106 55 1000 1552 IDA 25730 20875 55 1000 144 Bitmap 593 124 18 100 16 Maple 3599 4782 18 100 528 IDA 3266 1960 18 100 144 Bitmap 414 129 10 10 8 Maple 2143 1385 10 10 272 IDA 892 648 10 10 16 Region allocation benchmark complete Reported IDA and Maple Tree memory figures exclude slab overhead and transient allocations. The Maple Tree figure is additionally a lower-bound estimate that assumes fully occupied leaf nodes and excludes internal nodes. IDA has no region-allocation API, so each region is implemented as a sequence of single-ID allocations. The IDs remain contiguous because this benchmark fills an initially empty IDA monotonically. The benchmark is motivated by the discussion linked below about choosing the best data structure for the channel ID pool with the capacity of 2048 IDs for the nova GPU driver. Specifically for 2048 IDs the result is: Bitmap 5112 615 121 2048 256 Maple 78526 59592 121 2048 3344 IDA 165274 117761 121 2048 848 The benchmark accepts a list of up to 64 nonzero capacities to test. For example: insmod region_alloc_benchmark.ko capacities=1024,2048,4096,65536 The list may contain duplicate capacities. Each occurrence generates a new region-size sequence, which is useful for collecting statistical characteristics of the benchmark results. Link: https://lore.kernel.org/all/20260710-chid-maple-v1-1-4ee869055268@nvidia.com/ Tested-by: Eliot Courtney <ecourtney@nvidia.com> Reviewed-by: Eliot Courtney <ecourtney@nvidia.com> Signed-off-by: Yury Norov <ynorov@nvidia.com>
338 lines
11 KiB
Makefile
338 lines
11 KiB
Makefile
# SPDX-License-Identifier: GPL-2.0
|
|
#
|
|
# Makefile for some libs needed in the kernel.
|
|
#
|
|
|
|
ccflags-remove-$(CONFIG_FUNCTION_TRACER) += $(CC_FLAGS_FTRACE)
|
|
|
|
# Branch profiling isn't noinstr-safe
|
|
ifdef CONFIG_TRACE_BRANCH_PROFILING
|
|
CFLAGS_smp_processor_id.o += -DDISABLE_BRANCH_PROFILING
|
|
endif
|
|
|
|
# These files are disabled because they produce lots of non-interesting and/or
|
|
# flaky coverage that is not a function of syscall inputs. For example,
|
|
# rbtree can be global and individual rotations don't correlate with inputs.
|
|
KCOV_INSTRUMENT_string.o := n
|
|
KCOV_INSTRUMENT_rbtree.o := n
|
|
KCOV_INSTRUMENT_list_debug.o := n
|
|
KCOV_INSTRUMENT_debugobjects.o := n
|
|
KCOV_INSTRUMENT_dynamic_debug.o := n
|
|
KCOV_INSTRUMENT_fault-inject.o := n
|
|
KCOV_INSTRUMENT_find_bit.o := n
|
|
|
|
# string.o implements standard library functions like memset/memcpy etc.
|
|
# Use -ffreestanding to ensure that the compiler does not try to "optimize"
|
|
# them into calls to themselves.
|
|
CFLAGS_string.o := -ffreestanding
|
|
|
|
# Early boot use of cmdline, don't instrument it
|
|
ifdef CONFIG_AMD_MEM_ENCRYPT
|
|
KASAN_SANITIZE_string.o := n
|
|
|
|
CFLAGS_string.o += -fno-stack-protector
|
|
endif
|
|
|
|
lib-y := ctype.o string.o vsprintf.o cmdline.o \
|
|
rbtree.o radix-tree.o timerqueue.o xarray.o \
|
|
maple_tree.o idr.o extable.o irq_regs.o argv_split.o \
|
|
flex_proportions.o ratelimit.o \
|
|
is_single_threaded.o plist.o decompress.o kobject_uevent.o \
|
|
earlycpio.o seq_buf.o siphash.o dec_and_lock.o \
|
|
nmi_backtrace.o win_minmax.o memcat_p.o \
|
|
buildid.o objpool.o iomem_copy.o sys_info.o
|
|
|
|
lib-$(CONFIG_UNION_FIND) += union_find.o
|
|
lib-$(CONFIG_PRINTK) += dump_stack.o
|
|
lib-$(CONFIG_SMP) += cpumask.o
|
|
lib-$(CONFIG_MIN_HEAP) += min_heap.o
|
|
|
|
lib-y += kobject.o klist.o
|
|
obj-y += lockref.o
|
|
|
|
CONTEXT_ANALYSIS_rhashtable.o := y
|
|
|
|
obj-y += bcd.o sort.o parser.o debug_locks.o random32.o \
|
|
bust_spinlocks.o kasprintf.o bitmap.o scatterlist.o \
|
|
list_sort.o uuid.o iov_iter.o clz_ctz.o \
|
|
bsearch.o find_bit.o llist.o lwq.o memweight.o kfifo.o \
|
|
percpu-refcount.o rhashtable.o base64.o \
|
|
once.o refcount.o rcuref.o usercopy.o errseq.o bucket_locks.o \
|
|
generic-radix-tree.o bitmap-str.o
|
|
obj-y += string_helpers.o
|
|
obj-y += hexdump.o
|
|
obj-$(CONFIG_TEST_HEXDUMP) += test_hexdump.o
|
|
obj-y += kstrtox.o
|
|
obj-$(CONFIG_FIND_BIT_BENCHMARK) += find_bit_benchmark.o
|
|
obj-$(CONFIG_REGION_ALLOC_BENCHMARK) += region_alloc_benchmark.o
|
|
obj-$(CONFIG_FIND_BIT_BENCHMARK_RUST) += find_bit_benchmark_rust.o
|
|
obj-$(CONFIG_TEST_BPF) += test_bpf.o
|
|
test_dhry-objs := dhry_1.o dhry_2.o dhry_run.o
|
|
obj-$(CONFIG_TEST_DHRY) += test_dhry.o
|
|
obj-$(CONFIG_TEST_FIRMWARE) += test_firmware.o
|
|
obj-$(CONFIG_TEST_BITOPS) += test_bitops.o
|
|
CFLAGS_test_bitops.o += -Werror
|
|
obj-$(CONFIG_TEST_SYSCTL) += test_sysctl.o
|
|
obj-$(CONFIG_TEST_IDA) += test_ida.o
|
|
obj-$(CONFIG_TEST_UBSAN) += test_ubsan.o
|
|
CFLAGS_test_ubsan.o += $(call cc-disable-warning, unused-but-set-variable)
|
|
UBSAN_SANITIZE_test_ubsan.o := y
|
|
obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
|
|
obj-$(CONFIG_TEST_LKM) += test_module.o
|
|
obj-$(CONFIG_TEST_VMALLOC) += test_vmalloc.o
|
|
obj-$(CONFIG_TEST_WORKQUEUE) += test_workqueue.o
|
|
obj-$(CONFIG_TEST_RHASHTABLE) += test_rhashtable.o
|
|
obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_keys.o
|
|
obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_key_base.o
|
|
obj-$(CONFIG_TEST_DYNAMIC_DEBUG) += test_dynamic_debug.o
|
|
|
|
obj-$(CONFIG_TEST_BITMAP) += test_bitmap.o
|
|
ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_KASAN),yy)
|
|
# FIXME: Clang breaks test_bitmap_const_eval when KASAN and GCOV are enabled
|
|
GCOV_PROFILE_test_bitmap.o := n
|
|
endif
|
|
|
|
obj-$(CONFIG_TEST_XARRAY) += test_xarray.o
|
|
obj-$(CONFIG_TEST_MAPLE_TREE) += test_maple_tree.o
|
|
obj-$(CONFIG_TEST_PARMAN) += test_parman.o
|
|
obj-$(CONFIG_TEST_KMOD) += test_kmod.o
|
|
obj-$(CONFIG_TEST_DEBUG_VIRTUAL) += test_debug_virtual.o
|
|
obj-$(CONFIG_TEST_MEMCAT_P) += test_memcat_p.o
|
|
obj-$(CONFIG_TEST_OBJAGG) += test_objagg.o
|
|
obj-$(CONFIG_TEST_MEMINIT) += test_meminit.o
|
|
obj-$(CONFIG_TEST_LOCKUP) += test_lockup.o
|
|
obj-$(CONFIG_TEST_HMM) += test_hmm.o
|
|
obj-$(CONFIG_TEST_FREE_PAGES) += test_free_pages.o
|
|
obj-$(CONFIG_TEST_REF_TRACKER) += test_ref_tracker.o
|
|
obj-$(CONFIG_TEST_OBJPOOL) += test_objpool.o
|
|
obj-$(CONFIG_TEST_KEXEC_HANDOVER) += test_kho.o
|
|
|
|
obj-$(CONFIG_TEST_FPU) += test_fpu.o
|
|
test_fpu-y := test_fpu_glue.o test_fpu_impl.o
|
|
CFLAGS_test_fpu_impl.o += $(CC_FLAGS_FPU)
|
|
CFLAGS_REMOVE_test_fpu_impl.o += $(CC_FLAGS_NO_FPU)
|
|
|
|
obj-y += kunit/
|
|
|
|
ifeq ($(CONFIG_DEBUG_KOBJECT),y)
|
|
CFLAGS_kobject.o += -DDEBUG
|
|
CFLAGS_kobject_uevent.o += -DDEBUG
|
|
endif
|
|
|
|
obj-$(CONFIG_DEBUG_INFO_REDUCED) += debug_info.o
|
|
CFLAGS_debug_info.o += $(call cc-option, -femit-struct-debug-detailed=any)
|
|
|
|
obj-y += math/ crc/ crypto/ tests/ vdso/ raid/
|
|
|
|
obj-$(CONFIG_GENERIC_IOMAP) += iomap.o
|
|
obj-$(CONFIG_HAS_IOMEM) += iomap_copy.o devres.o
|
|
obj-$(CONFIG_CHECK_SIGNATURE) += check_signature.o
|
|
obj-$(CONFIG_DEBUG_LOCKING_API_SELFTESTS) += locking-selftest.o
|
|
|
|
obj-$(CONFIG_GENERIC_CPU_CACHE_MAINTENANCE) += cache_maint.o
|
|
|
|
lib-y += logic_pio.o
|
|
|
|
lib-$(CONFIG_INDIRECT_IOMEM) += logic_iomem.o
|
|
|
|
obj-$(CONFIG_TRACE_MMIO_ACCESS) += trace_readwrite.o
|
|
|
|
obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
|
|
|
|
obj-$(CONFIG_BTREE) += btree.o
|
|
obj-$(CONFIG_INTERVAL_TREE) += interval_tree.o
|
|
obj-$(CONFIG_ASSOCIATIVE_ARRAY) += assoc_array.o
|
|
obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o
|
|
obj-$(CONFIG_LIST_HARDENED) += list_debug.o
|
|
obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o
|
|
|
|
obj-$(CONFIG_GENERIC_BITREVERSE) += bitrev.o
|
|
obj-$(CONFIG_LINEAR_RANGES) += linear_ranges.o
|
|
obj-$(CONFIG_PACKING) += packing.o
|
|
obj-$(CONFIG_PACKING_KUNIT_TEST) += packing_test.o
|
|
obj-$(CONFIG_XXHASH) += xxhash.o
|
|
obj-$(CONFIG_GENERIC_ALLOCATOR) += genalloc.o
|
|
|
|
obj-$(CONFIG_842_COMPRESS) += 842/
|
|
obj-$(CONFIG_842_DECOMPRESS) += 842/
|
|
obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/
|
|
obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/
|
|
obj-$(CONFIG_ZLIB_DFLTCC) += zlib_dfltcc/
|
|
obj-$(CONFIG_REED_SOLOMON) += reed_solomon/
|
|
obj-$(CONFIG_BCH) += bch.o
|
|
obj-$(CONFIG_LZO_COMPRESS) += lzo/
|
|
obj-$(CONFIG_LZO_DECOMPRESS) += lzo/
|
|
obj-$(CONFIG_LZ4_COMPRESS) += lz4/
|
|
obj-$(CONFIG_LZ4HC_COMPRESS) += lz4/
|
|
obj-$(CONFIG_LZ4_DECOMPRESS) += lz4/
|
|
obj-$(CONFIG_ZSTD_COMPRESS) += zstd/
|
|
obj-$(CONFIG_ZSTD_DECOMPRESS) += zstd/
|
|
obj-$(CONFIG_XZ_DEC) += xz/
|
|
|
|
lib-$(CONFIG_DECOMPRESS_GZIP) += decompress_inflate.o
|
|
lib-$(CONFIG_DECOMPRESS_BZIP2) += decompress_bunzip2.o
|
|
lib-$(CONFIG_DECOMPRESS_LZMA) += decompress_unlzma.o
|
|
lib-$(CONFIG_DECOMPRESS_XZ) += decompress_unxz.o
|
|
lib-$(CONFIG_DECOMPRESS_LZO) += decompress_unlzo.o
|
|
lib-$(CONFIG_DECOMPRESS_LZ4) += decompress_unlz4.o
|
|
lib-$(CONFIG_DECOMPRESS_ZSTD) += decompress_unzstd.o
|
|
|
|
obj-$(CONFIG_TEXTSEARCH) += textsearch.o
|
|
obj-$(CONFIG_TEXTSEARCH_KMP) += ts_kmp.o
|
|
obj-$(CONFIG_TEXTSEARCH_BM) += ts_bm.o
|
|
obj-$(CONFIG_TEXTSEARCH_FSM) += ts_fsm.o
|
|
obj-$(CONFIG_SMP) += percpu_counter.o
|
|
obj-$(CONFIG_AUDIT_GENERIC) += audit.o
|
|
obj-$(CONFIG_AUDIT_COMPAT_GENERIC) += compat_audit.o
|
|
|
|
obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o
|
|
obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
|
|
obj-$(CONFIG_FAULT_INJECTION_USERCOPY) += fault-inject-usercopy.o
|
|
obj-$(CONFIG_NOTIFIER_ERROR_INJECTION) += notifier-error-inject.o
|
|
obj-$(CONFIG_PM_NOTIFIER_ERROR_INJECT) += pm-notifier-error-inject.o
|
|
obj-$(CONFIG_NETDEV_NOTIFIER_ERROR_INJECT) += netdev-notifier-error-inject.o
|
|
obj-$(CONFIG_MEMORY_NOTIFIER_ERROR_INJECT) += memory-notifier-error-inject.o
|
|
obj-$(CONFIG_OF_RECONFIG_NOTIFIER_ERROR_INJECT) += \
|
|
of-reconfig-notifier-error-inject.o
|
|
obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
|
|
|
|
obj-$(CONFIG_CODE_TAGGING) += codetag.o
|
|
obj-$(CONFIG_MEM_ALLOC_PROFILING) += alloc_tag.o
|
|
|
|
lib-$(CONFIG_GENERIC_BUG) += bug.o
|
|
|
|
obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o
|
|
obj-$(CONFIG_ARCH_NEED_CMPXCHG_1_EMU) += cmpxchg-emu.o
|
|
|
|
obj-$(CONFIG_DYNAMIC_DEBUG_CORE) += dynamic_debug.o
|
|
#ensure exported functions have prototypes
|
|
CFLAGS_dynamic_debug.o := -DDYNAMIC_DEBUG_MODULE
|
|
|
|
obj-$(CONFIG_SYMBOLIC_ERRNAME) += errname.o
|
|
|
|
obj-$(CONFIG_NLATTR) += nlattr.o
|
|
|
|
obj-$(CONFIG_LRU_CACHE) += lru_cache.o
|
|
|
|
obj-$(CONFIG_GENERIC_CSUM) += checksum.o
|
|
|
|
obj-$(CONFIG_GENERIC_ATOMIC64) += atomic64.o
|
|
|
|
obj-$(CONFIG_ATOMIC64_SELFTEST) += atomic64_test.o
|
|
|
|
obj-$(CONFIG_CPU_RMAP) += cpu_rmap.o
|
|
|
|
obj-$(CONFIG_CLOSURES) += closure.o
|
|
|
|
obj-$(CONFIG_DQL) += dynamic_queue_limits.o
|
|
|
|
obj-$(CONFIG_GLOB) += glob.o
|
|
|
|
obj-$(CONFIG_DIMLIB) += dim/
|
|
obj-$(CONFIG_SIGNATURE) += digsig.o
|
|
|
|
lib-$(CONFIG_CLZ_TAB) += clz_tab.o
|
|
|
|
obj-$(CONFIG_GENERIC_STRNCPY_FROM_USER) += strncpy_from_user.o
|
|
obj-$(CONFIG_GENERIC_STRNLEN_USER) += strnlen_user.o
|
|
|
|
obj-$(CONFIG_GENERIC_NET_UTILS) += net_utils.o
|
|
|
|
obj-$(CONFIG_SG_SPLIT) += sg_split.o
|
|
obj-$(CONFIG_SG_POOL) += sg_pool.o
|
|
obj-$(CONFIG_MEMREGION) += memregion.o
|
|
obj-$(CONFIG_STMP_DEVICE) += stmp_device.o
|
|
obj-$(CONFIG_IRQ_POLL) += irq_poll.o
|
|
|
|
# stackdepot.c should not be instrumented or call instrumented functions.
|
|
# Prevent the compiler from calling builtins like memcmp() or bcmp() from this
|
|
# file.
|
|
CFLAGS_stackdepot.o += -fno-builtin
|
|
CONTEXT_ANALYSIS_stackdepot.o := y
|
|
obj-$(CONFIG_STACKDEPOT) += stackdepot.o
|
|
KASAN_SANITIZE_stackdepot.o := n
|
|
# In particular, instrumenting stackdepot.c with KMSAN will result in infinite
|
|
# recursion.
|
|
KMSAN_SANITIZE_stackdepot.o := n
|
|
KCOV_INSTRUMENT_stackdepot.o := n
|
|
|
|
obj-$(CONFIG_REF_TRACKER) += ref_tracker.o
|
|
|
|
libfdt_files = fdt.o fdt_ro.o fdt_wip.o fdt_rw.o fdt_sw.o fdt_strerror.o \
|
|
fdt_empty_tree.o fdt_addresses.o
|
|
$(foreach file, $(libfdt_files), \
|
|
$(eval CFLAGS_$(file) = -I $(srctree)/scripts/dtc/libfdt))
|
|
lib-$(CONFIG_LIBFDT) += $(libfdt_files)
|
|
|
|
obj-$(CONFIG_BOOT_CONFIG) += bootconfig.o
|
|
obj-$(CONFIG_BOOT_CONFIG_EMBED) += bootconfig-data.o
|
|
|
|
$(obj)/bootconfig-data.o: $(obj)/default.bconf
|
|
|
|
targets += default.bconf
|
|
filechk_defbconf = cat $(or $(real-prereqs), /dev/null)
|
|
$(obj)/default.bconf: $(CONFIG_BOOT_CONFIG_EMBED_FILE) FORCE
|
|
$(call filechk,defbconf)
|
|
|
|
obj-$(CONFIG_RBTREE_TEST) += rbtree_test.o
|
|
obj-$(CONFIG_INTERVAL_TREE_TEST) += interval_tree_test.o
|
|
|
|
obj-$(CONFIG_PERCPU_TEST) += percpu_test.o
|
|
|
|
obj-$(CONFIG_ASN1) += asn1_decoder.o
|
|
obj-$(CONFIG_ASN1_ENCODER) += asn1_encoder.o
|
|
|
|
obj-$(CONFIG_FONT_SUPPORT) += fonts/
|
|
|
|
#
|
|
# Build a fast OID lookip registry from include/linux/oid_registry.h
|
|
#
|
|
obj-$(CONFIG_OID_REGISTRY) += oid_registry.o
|
|
|
|
$(obj)/oid_registry.o: $(obj)/oid_registry_data.c
|
|
|
|
$(obj)/oid_registry_data.c: $(srctree)/include/linux/oid_registry.h \
|
|
$(src)/build_OID_registry
|
|
$(call cmd,build_OID_registry)
|
|
|
|
quiet_cmd_build_OID_registry = GEN $@
|
|
cmd_build_OID_registry = perl $(src)/build_OID_registry $< $@
|
|
|
|
clean-files += oid_registry_data.c
|
|
|
|
obj-$(CONFIG_UCS2_STRING) += ucs2_string.o
|
|
obj-$(CONFIG_UBSAN) += ubsan.o
|
|
|
|
UBSAN_SANITIZE_ubsan.o := n
|
|
KASAN_SANITIZE_ubsan.o := n
|
|
KCSAN_SANITIZE_ubsan.o := n
|
|
KMSAN_SANITIZE_ubsan.o := n
|
|
CFLAGS_ubsan.o := -fno-stack-protector $(DISABLE_KSTACK_ERASE)
|
|
|
|
obj-$(CONFIG_SBITMAP) += sbitmap.o
|
|
|
|
obj-$(CONFIG_PARMAN) += parman.o
|
|
|
|
obj-y += group_cpus.o
|
|
|
|
# GCC library routines
|
|
obj-$(CONFIG_GENERIC_LIB_ASHLDI3) += ashldi3.o
|
|
obj-$(CONFIG_GENERIC_LIB_ASHRDI3) += ashrdi3.o
|
|
obj-$(CONFIG_GENERIC_LIB_LSHRDI3) += lshrdi3.o
|
|
obj-$(CONFIG_GENERIC_LIB_MULDI3) += muldi3.o
|
|
obj-$(CONFIG_GENERIC_LIB_CMPDI2) += cmpdi2.o
|
|
obj-$(CONFIG_GENERIC_LIB_UCMPDI2) += ucmpdi2.o
|
|
obj-$(CONFIG_OBJAGG) += objagg.o
|
|
|
|
# pldmfw library
|
|
obj-$(CONFIG_PLDMFW) += pldmfw/
|
|
|
|
obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o
|
|
|
|
obj-$(CONFIG_FIRMWARE_TABLE) += fw_table.o
|
|
|
|
CONTEXT_ANALYSIS_test_context-analysis.o := y
|
|
obj-$(CONFIG_CONTEXT_ANALYSIS_TEST) += test_context-analysis.o
|
|
|
|
subdir-$(CONFIG_FORTIFY_SOURCE) += test_fortify
|