Revision e03a5125ec7bd1d4e8b062816a8813436876dc7c authored by Nicholas Piggin on 12 July 2019, 03:59:12 UTC, committed by Linus Torvalds on 12 July 2019, 18:05:46 UTC
CONFIG_NUMA on 64-bit CPUs currently enables hashdist unconditionally even when booting on single node machines. This causes the large system hashes to be allocated with vmalloc, and mapped with small pages. This change clears hashdist if only one node has come up with memory. This results in the important large inode and dentry hashes using memblock allocations. All others are within 4MB size up to about 128GB of RAM, which allows them to be allocated from the linear map on most non-NUMA images. Other big hashes like futex and TCP should eventually be moved over to the same style of allocation as those vfs caches that use HASH_EARLY if !hashdist, so they don't exceed MAX_ORDER on very large non-NUMA images. This brings dTLB misses for linux kernel tree `git diff` from ~45,000 to ~8,000 on a Kaby Lake KVM guest with 8MB dentry hash and mitigations=off (performance is in the noise, under 1% difference, page tables are likely to be well cached for this workload). Link: http://lkml.kernel.org/r/20190605144814.29319-2-npiggin@gmail.com Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent ec11408
Kbuild
# SPDX-License-Identifier: GPL-2.0
#
# Kbuild for top-level directory of the kernel
#####
# Generate bounds.h
bounds-file := include/generated/bounds.h
always := $(bounds-file)
targets := kernel/bounds.s
$(bounds-file): kernel/bounds.s FORCE
$(call filechk,offsets,__LINUX_BOUNDS_H__)
#####
# Generate timeconst.h
timeconst-file := include/generated/timeconst.h
targets += $(timeconst-file)
filechk_gentimeconst = echo $(CONFIG_HZ) | bc -q $<
$(timeconst-file): kernel/time/timeconst.bc FORCE
$(call filechk,gentimeconst)
#####
# Generate asm-offsets.h
offsets-file := include/generated/asm-offsets.h
always += $(offsets-file)
targets += arch/$(SRCARCH)/kernel/asm-offsets.s
arch/$(SRCARCH)/kernel/asm-offsets.s: $(timeconst-file) $(bounds-file)
$(offsets-file): arch/$(SRCARCH)/kernel/asm-offsets.s FORCE
$(call filechk,offsets,__ASM_OFFSETS_H__)
#####
# Check for missing system calls
always += missing-syscalls
targets += missing-syscalls
quiet_cmd_syscalls = CALL $<
cmd_syscalls = $(CONFIG_SHELL) $< $(CC) $(c_flags) $(missing_syscalls_flags)
missing-syscalls: scripts/checksyscalls.sh $(offsets-file) FORCE
$(call cmd,syscalls)
#####
# Check atomic headers are up-to-date
always += old-atomics
targets += old-atomics
quiet_cmd_atomics = CALL $<
cmd_atomics = $(CONFIG_SHELL) $<
old-atomics: scripts/atomic/check-atomics.sh FORCE
$(call cmd,atomics)
# Keep these three files during make clean
no-clean-files := $(bounds-file) $(offsets-file) $(timeconst-file)
Computing file changes ...
