sched: make migrate_enable/migrate_disable inline
Subsystems (23)
v4 cover sched: make migrate_enable/migrate_disable inline
In this series, we make migrate_enable/migrate_disable inline to obtain better performance in some case.
In the first patch, we add the macro "COMPILE_OFFSETS" to all the asm-offset.c to avoid circular dependency in the 2nd patch.
In the 2nd patch, we generate the offset of nr_pinned in "struct rq" with rq-offsets.c, as the "struct rq" is defined internally and we need to access the "nr_pinned" field in migrate_enable and migrate_disable. Then, we move the definition of migrate_enable/migrate_disable from kernel/sched/core.c to include/linux/sched.h.
In the 3rd patch, we fix some typos in include/linux/preempt.h.
One of the beneficiaries of this series is BPF trampoline. Without this series, the migrate_enable/migrate_disable is hot when we run the benchmark for FENTRY, FEXIT, MODIFY_RETURN, etc:
54.63% bpf_prog_2dcccf652aac1793_bench_trigger_fentry [k]
bpf_prog_2dcccf652aac1793_bench_trigger_fentry
10.43% [kernel] [k] migrate_enable
10.07% bpf_trampoline_6442517037 [k] bpf_trampoline_6442517037 8.06% [kernel] [k] __bpf_prog_exit_recur
4.11% libc.so.6 [.] syscall
2.15% [kernel] [k] entry_SYSCALL_64
1.48% [kernel] [k] memchr_inv
1.32% [kernel] [k] fput
1.16% [kernel] [k] _copy_to_user
0.73% [kernel] [k] bpf_prog_test_run_raw_tp
Before this patch, the performance of BPF FENTRY is:
fentry : 113.030 ± 0.149M/s fentry : 112.501 ± 0.187M/s fentry : 112.828 ± 0.267M/s fentry : 115.287 ± 0.241M/s
After this patch, the performance of BPF FENTRY increases to:
fentry : 143.644 ± 0.670M/s fentry : 149.764 ± 0.362M/s fentry : 149.642 ± 0.156M/s fentry : 145.263 ± 0.221M/s
Changes since V3:
* some modification on the 2nd patch, as Alexei advised:
- rename CREATE_MIGRATE_DISABLE to INSTANTIATE_EXPORTED_MIGRATE_DISABLE
- add document for INSTANTIATE_EXPORTED_MIGRATE_DISABLE
Changes since V2:
* some modification on the 2nd patch, as Peter advised:
- don't export runqueues, define migrate_enable and migrate_disable in kernel/sched/core.c and use them for kernel modules instead
- define the macro this_rq_pinned()
- add some comment for this_rq_raw()
Changes since V1:
* use PERCPU_PTR() for this_rq_raw() if !CONFIG_SMP in the 2nd patch
Menglong Dong (3):
arch: add the macro COMPILE_OFFSETS to all the asm-offsets.c
sched: make migrate_enable/migrate_disable inline
sched: fix some typos in include/linux/preempt.h
Kbuild | 13 ++- arch/alpha/kernel/asm-offsets.c | 1 + arch/arc/kernel/asm-offsets.c | 1 + arch/arm/kernel/asm-offsets.c | 2 + arch/arm64/kernel/asm-offsets.c | 1 + arch/csky/kernel/asm-offsets.c | 1 + arch/hexagon/kernel/asm-offsets.c | 1 + arch/loongarch/kernel/asm-offsets.c | 2 + arch/m68k/kernel/asm-offsets.c | 1 + arch/microblaze/kernel/asm-offsets.c | 1 + arch/mips/kernel/asm-offsets.c | 2 + arch/nios2/kernel/asm-offsets.c | 1 + arch/openrisc/kernel/asm-offsets.c | 1 + arch/parisc/kernel/asm-offsets.c | 1 + arch/powerpc/kernel/asm-offsets.c | 1 + arch/riscv/kernel/asm-offsets.c | 1 + arch/s390/kernel/asm-offsets.c | 1 + arch/sh/kernel/asm-offsets.c | 1 + arch/sparc/kernel/asm-offsets.c | 1 + arch/um/kernel/asm-offsets.c | 2 + arch/xtensa/kernel/asm-offsets.c | 1 + include/linux/preempt.h | 11 +-- include/linux/sched.h | 113 +++++++++++++++++++++++++++ kernel/bpf/verifier.c | 1 + kernel/sched/core.c | 63 ++++----------- kernel/sched/rq-offsets.c | 12 +++ 26 files changed, 180 insertions(+), 57 deletions(-) create mode 100644 kernel/sched/rq-offsets.c
Signature · 1 line
2.51.0
PATCH v4 1/3 arch: add the macro COMPILE_OFFSETS to all the asm-offsets.c
The include/generated/asm-offsets.h is generated in Kbuild during compiling from arch/SRCARCH/kernel/asm-offsets.c. When we want to generate another similar offset header file, circular dependency can happen.
For example, we want to generate a offset file include/generated/test.h, which is included in include/sched/sched.h. If we generate asm-offsets.h first, it will fail, as include/sched/sched.h is included in asm-offsets.c and include/generated/test.h doesn't exist; If we generate test.h first, it can't success neither, as include/generated/asm-offsets.h is included by it.
In x86_64, the macro COMPILE_OFFSETS is used to avoid such circular dependency. We can generate asm-offsets.h first, and if the COMPILE_OFFSETS is defined, we don't include the "generated/test.h".
And we define the macro COMPILE_OFFSETS for all the asm-offsets.c for this purpose.
--- arch/alpha/kernel/asm-offsets.c | 1 + arch/arc/kernel/asm-offsets.c | 1 + arch/arm/kernel/asm-offsets.c | 2 ++ arch/arm64/kernel/asm-offsets.c | 1 + arch/csky/kernel/asm-offsets.c | 1 + arch/hexagon/kernel/asm-offsets.c | 1 + arch/loongarch/kernel/asm-offsets.c | 2 ++ arch/m68k/kernel/asm-offsets.c | 1 + arch/microblaze/kernel/asm-offsets.c | 1 + arch/mips/kernel/asm-offsets.c | 2 ++ arch/nios2/kernel/asm-offsets.c | 1 + arch/openrisc/kernel/asm-offsets.c | 1 + arch/parisc/kernel/asm-offsets.c | 1 + arch/powerpc/kernel/asm-offsets.c | 1 + arch/riscv/kernel/asm-offsets.c | 1 + arch/s390/kernel/asm-offsets.c | 1 + arch/sh/kernel/asm-offsets.c | 1 + arch/sparc/kernel/asm-offsets.c | 1 + arch/um/kernel/asm-offsets.c | 2 ++ arch/xtensa/kernel/asm-offsets.c | 1 + 20 files changed, 24 insertions(+)
arch/alpha/kernel/asm-offsets.c +1 -0
@@ -4,6 +4,7 @@* This code generates raw asm output which is post-processed to extract * and format the required data. */ +#define COMPILE_OFFSETS #include <linux/types.h> #include <linux/stddef.h>
arch/arc/kernel/asm-offsets.c +1 -0
@@ -2,6 +2,7 @@/* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) */ +#define COMPILE_OFFSETS #include <linux/sched.h> #include <linux/mm.h>
arch/arm/kernel/asm-offsets.c +2 -0
@@ -7,6 +7,8 @@* This code generates raw asm output which is post-processed to extract * and format the required data. */ +#define COMPILE_OFFSETS +#include <linux/compiler.h> #include <linux/sched.h> #include <linux/mm.h>
arch/arm64/kernel/asm-offsets.c +1 -0
@@ -6,6 +6,7 @@* 2001-2002 Keith Owens * Copyright (C) 2012 ARM Ltd. */ +#define COMPILE_OFFSETS #include <linux/arm_sdei.h> #include <linux/sched.h>
arch/csky/kernel/asm-offsets.c +1 -0
@@ -1,5 +1,6 @@// SPDX-License-Identifier: GPL-2.0 // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. +#define COMPILE_OFFSETS #include <linux/sched.h> #include <linux/kernel_stat.h>
arch/hexagon/kernel/asm-offsets.c +1 -0
@@ -8,6 +8,7 @@* * Copyright (c) 2010-2012, The Linux Foundation. All rights reserved. */ +#define COMPILE_OFFSETS #include <linux/compat.h> #include <linux/types.h>
arch/loongarch/kernel/asm-offsets.c +2 -0
@@ -4,6 +4,8 @@* * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ +#define COMPILE_OFFSETS +#include <linux/types.h> #include <linux/sched.h> #include <linux/mm.h>
arch/m68k/kernel/asm-offsets.c +1 -0
@@ -9,6 +9,7 @@* #defines from the assembly-language output. */ +#define COMPILE_OFFSETS #define ASM_OFFSETS_C #include <linux/stddef.h>
arch/microblaze/kernel/asm-offsets.c +1 -0
@@ -7,6 +7,7 @@* License. See the file "COPYING" in the main directory of this archive * for more details. */ +#define COMPILE_OFFSETS #include <linux/init.h> #include <linux/stddef.h>
arch/mips/kernel/asm-offsets.c +2 -0
@@ -9,6 +9,8 @@* Kevin Kissell, [email protected] and Carsten Langgaard, [email protected] * Copyright (C) 2000 MIPS Technologies, Inc. */ +#define COMPILE_OFFSETS +#include <linux/compat.h> #include <linux/types.h> #include <linux/sched.h>
arch/nios2/kernel/asm-offsets.c +1 -0
@@ -2,6 +2,7 @@/* * Copyright (C) 2011 Tobias Klauser <[email protected]> */ +#define COMPILE_OFFSETS #include <linux/stddef.h> #include <linux/sched.h>
arch/openrisc/kernel/asm-offsets.c +1 -0
@@ -18,6 +18,7 @@* compile this file to assembler, and then extract the * #defines from the assembly-language output. */ +#define COMPILE_OFFSETS #include <linux/signal.h> #include <linux/sched.h>
arch/parisc/kernel/asm-offsets.c +1 -0
@@ -13,6 +13,7 @@* Copyright (C) 2002 Randolph Chung <tausq with parisc-linux.org> * Copyright (C) 2003 James Bottomley <jejb at parisc-linux.org> */ +#define COMPILE_OFFSETS #include <linux/types.h> #include <linux/sched.h>
arch/powerpc/kernel/asm-offsets.c +1 -0
@@ -8,6 +8,7 @@* compile this file to assembler, and then extract the * #defines from the assembly-language output. */ +#define COMPILE_OFFSETS #include <linux/compat.h> #include <linux/signal.h>
arch/riscv/kernel/asm-offsets.c +1 -0
@@ -3,6 +3,7 @@* Copyright (C) 2012 Regents of the University of California * Copyright (C) 2017 SiFive */ +#define COMPILE_OFFSETS #include <linux/kbuild.h> #include <linux/mm.h>
arch/s390/kernel/asm-offsets.c +1 -0
@@ -4,6 +4,7 @@* This code generates raw asm output which is post-processed to extract * and format the required data. */ +#define COMPILE_OFFSETS #include <linux/kbuild.h> #include <linux/sched.h>
arch/sh/kernel/asm-offsets.c +1 -0
@@ -8,6 +8,7 @@* compile this file to assembler, and then extract the * #defines from the assembly-language output. */ +#define COMPILE_OFFSETS #include <linux/stddef.h> #include <linux/types.h>
arch/sparc/kernel/asm-offsets.c +1 -0
@@ -10,6 +10,7 @@* * On sparc, thread_info data is static and TI_XXX offsets are computed by hand. */ +#define COMPILE_OFFSETS #include <linux/sched.h> #include <linux/mm_types.h>
arch/um/kernel/asm-offsets.c +2 -0
@@ -1 +1,3 @@ +#define COMPILE_OFFSETS +#include <sysdep/kernel-offsets.h>
arch/xtensa/kernel/asm-offsets.c +1 -0
@@ -11,6 +11,7 @@* * Chris Zankel <[email protected]> */ +#define COMPILE_OFFSETS #include <asm/processor.h> #include <asm/coprocessor.h>
Signature · 1 line
2.51.0
PATCH v4 2/3 sched: make migrate_enable/migrate_disable inline
In reply to Menglong DongFor now, migrate_enable and migrate_disable are global, which makes them become hotspots in some case. Take BPF for example, the function calling to migrate_enable and migrate_disable in BPF trampoline can introduce significant overhead, and following is the 'perf top' of FENTRY's benchmark (./tools/testing/selftests/bpf/bench trig-fentry):
54.63% bpf_prog_2dcccf652aac1793_bench_trigger_fentry [k]
bpf_prog_2dcccf652aac1793_bench_trigger_fentry
10.43% [kernel] [k] migrate_enable
10.07% bpf_trampoline_6442517037 [k] bpf_trampoline_6442517037 8.06% [kernel] [k] __bpf_prog_exit_recur
4.11% libc.so.6 [.] syscall
2.15% [kernel] [k] entry_SYSCALL_64
1.48% [kernel] [k] memchr_inv
1.32% [kernel] [k] fput
1.16% [kernel] [k] _copy_to_user
0.73% [kernel] [k] bpf_prog_test_run_raw_tp
So in this commit, we make migrate_enable/migrate_disable inline to obtain better performance. The struct rq is defined internally in kernel/sched/sched.h, and the field "nr_pinned" is accessed in migrate_enable/migrate_disable, which makes it hard to make them inline.
Alexei Starovoitov suggests to generate the offset of "nr_pinned" in [1], so we can define the migrate_enable/migrate_disable in include/linux/sched.h and access "this_rq()->nr_pinned" with "(void *)this_rq() + RQ_nr_pinned".
The offset of "nr_pinned" is generated in include/generated/rq-offsets.h by kernel/sched/rq-offsets.c.
Generally speaking, we move the definition of migrate_enable and migrate_disable to include/linux/sched.h from kernel/sched/core.c. The calling to __set_cpus_allowed_ptr() is leaved in ___migrate_enable().
The "struct rq" is not available in include/linux/sched.h, so we can't access the "runqueues" with this_cpu_ptr(), as the compilation will fail in this_cpu_ptr() -> raw_cpu_ptr() -> __verify_pcpu_ptr():
typeof((ptr) + 0)
So we introduce the this_rq_raw() and access the runqueues with arch_raw_cpu_ptr/PERCPU_PTR directly.
The variable "runqueues" is not visible in the kernel modules, and export it is not a good idea. As Peter Zijlstra advised in [2], we define and export migrate_enable/migrate_disable in kernel/sched/core.c too, and use them for the modules.
Before this patch, the performance of BPF FENTRY is:
fentry : 113.030 ± 0.149M/s fentry : 112.501 ± 0.187M/s fentry : 112.828 ± 0.267M/s fentry : 115.287 ± 0.241M/s
After this patch, the performance of BPF FENTRY increases to:
fentry : 143.644 ± 0.670M/s fentry : 149.764 ± 0.362M/s fentry : 149.642 ± 0.156M/s fentry : 145.263 ± 0.221M/s
---
v4:
- rename CREATE_MIGRATE_DISABLE to INSTANTIATE_EXPORTED_MIGRATE_DISABLE
- add document for INSTANTIATE_EXPORTED_MIGRATE_DISABLE
v3:
- don't export runqueues, define migrate_enable and migrate_disable in kernel/sched/core.c and use them for kernel modules instead
- define the macro this_rq_pinned()
- add some comment for this_rq_raw()
v2:
- use PERCPU_PTR() for this_rq_raw() if !CONFIG_SMP
--- Kbuild | 13 ++++- include/linux/preempt.h | 3 - include/linux/sched.h | 113 ++++++++++++++++++++++++++++++++++++++ kernel/bpf/verifier.c | 1 + kernel/sched/core.c | 63 +++++---------------- kernel/sched/rq-offsets.c | 12 ++++ 6 files changed, 152 insertions(+), 53 deletions(-) create mode 100644 kernel/sched/rq-offsets.c
Kbuild +12 -1
@@ -34,13 +34,24 @@ 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__) +# Generate rq-offsets.h + +rq-offsets-file := include/generated/rq-offsets.h + +targets += kernel/sched/rq-offsets.s + +kernel/sched/rq-offsets.s: $(offsets-file) + +$(rq-offsets-file): kernel/sched/rq-offsets.s FORCE + $(call filechk,offsets,__RQ_OFFSETS_H__) + # Check for missing system calls quiet_cmd_syscalls = CALL $< cmd_syscalls = $(CONFIG_SHELL) $< $(CC) $(c_flags) $(missing_syscalls_flags) PHONY += missing-syscalls -missing-syscalls: scripts/checksyscalls.sh $(offsets-file) +missing-syscalls: scripts/checksyscalls.sh $(rq-offsets-file) $(call cmd,syscalls) # Check the manual modification of atomic headers
include/linux/preempt.h +0 -3
@@ -424,8 +424,6 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier,* work-conserving schedulers. * */ -extern void migrate_disable (void ); -extern void migrate_enable (void );/** * preempt_disable_nested - Disable preemption inside a normally preempt disabled section
@@ -471,7 +469,6 @@ static __always_inline void preempt_enable_nested(void) DEFINE_LOCK_GUARD_0(preempt, preempt_disable(), preempt_enable()) DEFINE_LOCK_GUARD_0(preempt_notrace, preempt_disable_notrace(), preempt_enable_notrace()) -DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable())#ifdef CONFIG_PREEMPT_DYNAMIC
include/linux/sched.h +113 -0
123 lines not on this page · raw message
kernel/bpf/verifier.c +1 -0
@@ -23855,6 +23855,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,BTF_SET_START (btf_id_deny) BTF_ID_UNUSED#ifdef CONFIG_SMP +BTF_ID(func, ___migrate_enable) BTF_ID(func, migrate_disable) BTF_ID(func, migrate_enable)#endif
kernel/sched/core.c +14 -49
83 lines not on this page · raw message
kernel/sched/rq-offsets.c new file +12 -0
@@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 +#define COMPILE_OFFSETS +#include <linux/kbuild.h> +#include <linux/types.h> +#include "sched.h" + +int main (void ) +{ +DEFINE (RQ_nr_pinned, offsetof(struct rq , nr_pinned)); + +return 0 ; +}
Signature · 1 line
2.51.0
PATCH v4 3/3 sched: fix some typos in include/linux/preempt.h
In reply to Menglong DongThere are some typos in the comments of migrate in include/linux/preempt.h:
elegible -> eligible
it's -> its
migirate_disable -> migrate_disable
abritrary -> arbitrary
Just fix them.
--- include/linux/preempt.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
include/linux/preempt.h +4 -4
@@ -372,7 +372,7 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier,/* * Migrate-Disable and why it is undesired. * -* When a preempted task becomes elegible to run under the ideal model (IOW it +* When a preempted task becomes eligible to run under the ideal model (IOW it * becomes one of the M highest priority tasks), it might still have to wait * for the preemptee's migrate_disable() section to complete. Thereby suffering * a reduction in bandwidth in the exact duration of the migrate_disable()
@@ -387,7 +387,7 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier,* - a lower priority tasks; which under preempt_disable() could've instantly * migrated away when another CPU becomes available, is now constrained * by the ability to push the higher priority task away, which might itself be -* in a migrate_disable() section, reducing it's available bandwidth. +* in a migrate_disable() section, reducing its available bandwidth. * * IOW it trades latency / moves the interference term, but it stays in the * system, and as long as it remains unbounded, the system is not fully
@@ -399,7 +399,7 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier,* PREEMPT_RT breaks a number of assumptions traditionally held. By forcing a * number of primitives into becoming preemptible, they would also allow * migration. This turns out to break a bunch of per-cpu usage. To this end, -* all these primitives employ migirate_disable() to restore this implicit +* all these primitives employ migrate_disable() to restore this implicit * assumption. * * This is a 'temporary' work-around at best. The correct solution is getting
@@ -407,7 +407,7 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier,* per-cpu locking or short preempt-disable regions. * * The end goal must be to get rid of migrate_disable(), alternatively we need -* a schedulability theory that does not depend on abritrary migration. +* a schedulability theory that does not depend on arbitrary migration. * * * Notes on the implementation.
Signature · 1 line
2.51.0
syzbot ci has tested the following series
syzbot ci has tested the following series
[v4] sched: make migrate_enable/migrate_disable inline
https://lore.kernel.org/all/[email protected]
* [PATCH v4 1/3] arch: add the macro COMPILE_OFFSETS to all the asm-offsets.c
* [PATCH v4 2/3] sched: make migrate_enable/migrate_disable inline
* [PATCH v4 3/3] sched: fix some typos in include/linux/preempt.h
and found the following issue:
kernel build error
Full report is available here:
https://ci.syzbot.org/series/aac2d563-711a-4b4b-89c3-7365b1c03190
***
kernel build error
tree: bpf-next URL: https://kernel.googlesource.com/pub/scm/linux/kernel/git/bpf/bpf-next.git base: d3abefe897408718799ae3bd06295b89b870a38e arch: amd64 compiler: Debian clang version 20.1.7 (++20250616065708+6146a88f6049-1~exp1~20250616065826.132), Debian LLD 20.1.7 config: https://ci.syzbot.org/builds/bb1748d9-0b48-4894-b30e-ea91020f1c78/config
./include/linux/rcupdate.h:968:3: error: call to undeclared function 'migrate_disable'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration] ./include/linux/rcupdate.h:976:3: error: call to undeclared function 'migrate_enable'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration] ./include/linux/sched.h:2402:20: error: static declaration of 'migrate_disable' follows non-static declaration./include/linux/sched.h:2407:20: error: static declaration of 'migrate_enable' follows non-static declaration
***
If these findings have caused you to resend the series or submit a separate fix, please add the following tag to your commit message:
---
This report is generated by a bot. It may contain errors. syzbot ci engineers can be reached at [email protected].
On 2025/8/28 14:03 Menglong Dong <[email protected]> write:
Quoted 6 lines
In this series, we make migrate_enable/migrate_disable inline to obtain better performance in some case.
In the first patch, we add the macro "
COMPILE_OFFSETS" to all theasm-offset.cto avoid circular dependency in the 2nd patch.
Quoted 7 lines
In the 2nd patch, we generate the offset of
nr_pinnedin "struct rq" withrq-offsets.c, as the "struct rq" is defined internally and we need to access the "nr_pinned" field inmigrate_enableandmigrate_disable. Then, we move the definition of migrate_enable/migrate_disable fromkernel/sched/core.ctoinclude/linux/sched.h.In the 3rd patch, we fix some typos in
include/linux/preempt.h.
Hi, everyone. Do we have any thoughts on this series?
Thanks!
Menglong Dong
Quoted 84 lines
One of the beneficiaries of this series is BPF trampoline. Without this series, the migrate_enable/migrate_disable is hot when we run the benchmark for FENTRY, FEXIT,
MODIFY_RETURN, etc:54.63%
bpf_prog_2dcccf652aac1793_bench_trigger_fentry[k]bpf_prog_2dcccf652aac1793_bench_trigger_fentry10.43% [kernel] [k]
migrate_enable
10.07%bpf_trampoline_6442517037[k]bpf_trampoline_64425170378.06% [kernel] [k]__bpf_prog_exit_recur
4.11% libc.so.6 [.] syscall
2.15% [kernel] [k]entry_SYSCALL_64
1.48% [kernel] [k]memchr_inv
1.32% [kernel] [k] fput
1.16% [kernel] [k]_copy_to_user
0.73% [kernel] [k]bpf_prog_test_run_raw_tpBefore this patch, the performance of BPF FENTRY is:
fentry : 113.030 ± 0.149M/s fentry : 112.501 ± 0.187M/s fentry : 112.828 ± 0.267M/s fentry : 115.287 ± 0.241M/sAfter this patch, the performance of BPF FENTRY increases to:
fentry : 143.644 ± 0.670M/s fentry : 149.764 ± 0.362M/s fentry : 149.642 ± 0.156M/s fentry : 145.263 ± 0.221M/sChanges since V3:
* some modification on the 2nd patch, as Alexei advised:
- renameCREATE_MIGRATE_DISABLEtoINSTANTIATE_EXPORTED_MIGRATE_DISABLE
- add document forINSTANTIATE_EXPORTED_MIGRATE_DISABLEChanges since V2:
* some modification on the 2nd patch, as Peter advised:
- don't export runqueues, definemigrate_enableandmigrate_disableinkernel/sched/core.cand use them for kernel modules instead
- define the macrothis_rq_pinned()
- add some comment forthis_rq_raw()Changes since V1:
* usePERCPU_PTR()forthis_rq_raw()if !CONFIG_SMP in the 2nd patchMenglong Dong (3):
arch: add the macroCOMPILE_OFFSETSto all theasm-offsets.c
sched: make migrate_enable/migrate_disable inline
sched: fix some typos ininclude/linux/preempt.hKbuild | 13 ++- arch/alpha/kernel/asm-offsets.c | 1 + arch/arc/kernel/asm-offsets.c | 1 + arch/arm/kernel/asm-offsets.c | 2 + arch/arm64/kernel/asm-offsets.c | 1 + arch/csky/kernel/asm-offsets.c | 1 + arch/hexagon/kernel/asm-offsets.c | 1 + arch/loongarch/kernel/asm-offsets.c | 2 + arch/m68k/kernel/asm-offsets.c | 1 + arch/microblaze/kernel/asm-offsets.c | 1 + arch/mips/kernel/asm-offsets.c | 2 + arch/nios2/kernel/asm-offsets.c | 1 + arch/openrisc/kernel/asm-offsets.c | 1 + arch/parisc/kernel/asm-offsets.c | 1 + arch/powerpc/kernel/asm-offsets.c | 1 + arch/riscv/kernel/asm-offsets.c | 1 + arch/s390/kernel/asm-offsets.c | 1 + arch/sh/kernel/asm-offsets.c | 1 + arch/sparc/kernel/asm-offsets.c | 1 + arch/um/kernel/asm-offsets.c | 2 + arch/xtensa/kernel/asm-offsets.c | 1 + include/linux/preempt.h | 11 +-- include/linux/sched.h | 113 +++++++++++++++++++++++++++ kernel/bpf/verifier.c | 1 + kernel/sched/core.c | 63 ++++----------- kernel/sched/rq-offsets.c | 12 +++ 26 files changed, 180 insertions(+), 57 deletions(-) create mode 100644 kernel/sched/rq-offsets.cSignature · 1 line
2.51.0
Quoted 14 lines · Menglong Dong
On 2025/8/28 14:03 Menglong Dong <[email protected]> write:
Quoted 12 lines
In this series, we make migrate_enable/migrate_disable inline to obtain better performance in some case.
In the first patch, we add the macro "
COMPILE_OFFSETS" to all theasm-offset.cto avoid circular dependency in the 2nd patch.In the 2nd patch, we generate the offset of
nr_pinnedin "struct rq" withrq-offsets.c, as the "struct rq" is defined internally and we need to access the "nr_pinned" field inmigrate_enableandmigrate_disable. Then, we move the definition of migrate_enable/migrate_disable fromkernel/sched/core.ctoinclude/linux/sched.h.
Quoted 3 lines
Quoted 1 line
In the 3rd patch, we fix some typos in
include/linux/preempt.h.Hi, everyone. Do we have any thoughts on this series?
Pls fix build errors and repost.
Peter Zijlstra
maintainerQuoted 7 lines · Menglong Dong
+/* The "struct rq" is not available here, so we can't access the
+ * "runqueues" withthis_cpu_ptr(), as the compilation will fail in
+ *this_cpu_ptr()->raw_cpu_ptr()->__verify_pcpu_ptr():
+ * typeof((ptr) + 0)
+ *
+ * So use arch_raw_cpu_ptr()/PERCPU_PTR() directly here.
+ */
Please fix broken comment style while you fix that compile error.
Quoted 11 lines · Peter Zijlstra
Quoted 7 lines · Menglong Dong
+/* The "struct rq" is not available here, so we can't access the
+ * "runqueues" withthis_cpu_ptr(), as the compilation will fail in
+ *this_cpu_ptr()->raw_cpu_ptr()->__verify_pcpu_ptr():
+ * typeof((ptr) + 0)
+ *
+ * So use arch_raw_cpu_ptr()/PERCPU_PTR() directly here.
+ */
Quoted 1 line
Please fix broken comment style while you fix that compile error.
+1
We switched to normal kernel comment style in bpf land quite some time ago, but old habits die hard and I have to keep reminding people to use normal comments in all new code.
On 2025/9/16 19:07 Peter Zijlstra <[email protected]> write:
Quoted 11 lines · Menglong Dong
Quoted 8 lines
+/* The "struct rq" is not available here, so we can't access the
+ * "runqueues" withthis_cpu_ptr(), as the compilation will fail in
+ *this_cpu_ptr()->raw_cpu_ptr()->__verify_pcpu_ptr():
+ * typeof((ptr) + 0)
+ *
+ * So use arch_raw_cpu_ptr()/PERCPU_PTR() directly here.
+ */Please fix broken comment style while you fix that compile error.
It's a little embarrassing. The compile error is caused by the commit 1b93c03fb319 ("rcu: add rcu_read_lock_dont_migrate()") in bpf-next tree, which uses migrate_enable/migrate_disable in include/linux/rcupdate.h but include the <linux/preempt.h>.
I can fix it by replace the linux/preempt.h with linux/sched.h, but should I fix it in this series? I mean, the commit 1b93c03fb319 doesn't exist in the tip for now :/
Thanks!
Menglong Dong
Quoted 2 lines
Quoted 14 lines · Menglong Dong
On 2025/9/16 19:07 Peter Zijlstra <[email protected]> write:
Quoted 11 lines · Menglong Dong
Quoted 8 lines
+/* The "struct rq" is not available here, so we can't access the
+ * "runqueues" withthis_cpu_ptr(), as the compilation will fail in
+ *this_cpu_ptr()->raw_cpu_ptr()->__verify_pcpu_ptr():
+ * typeof((ptr) + 0)
+ *
+ * So use arch_raw_cpu_ptr()/PERCPU_PTR() directly here.
+ */Please fix broken comment style while you fix that compile error.
Quoted 8 lines
It's a little embarrassing. The compile error is caused by the commit
1b93c03fb319("rcu: addrcu_read_lock_dont_migrate()") in bpf-next tree, which uses migrate_enable/migrate_disable ininclude/linux/rcupdate.hbut include the <linux/preempt.h>.I can fix it by replace the
linux/preempt.hwithlinux/sched.h, but should I fix it in this series? I mean, the commit1b93c03fb319doesn't exist in the tip for now :/
If it's just a different include then go for it.
Make sure there are no nasty build issues during the merge window.
On 2025/9/17 09:29 Alexei Starovoitov <[email protected]> write:
Quoted 20 lines · Menglong Dong
Quoted 19 lines
On 2025/9/16 19:07 Peter Zijlstra <[email protected]> write:
Quoted 11 lines · Menglong Dong
Quoted 8 lines
+/* The "struct rq" is not available here, so we can't access the
+ * "runqueues" withthis_cpu_ptr(), as the compilation will fail in
+ *this_cpu_ptr()->raw_cpu_ptr()->__verify_pcpu_ptr():
+ * typeof((ptr) + 0)
+ *
+ * So use arch_raw_cpu_ptr()/PERCPU_PTR() directly here.
+ */Please fix broken comment style while you fix that compile error.
It's a little embarrassing. The compile error is caused by the commit
1b93c03fb319("rcu: addrcu_read_lock_dont_migrate()") in bpf-next tree, which uses migrate_enable/migrate_disable ininclude/linux/rcupdate.hbut include the <linux/preempt.h>.
Quoted 6 lines
Quoted 3 lines
I can fix it by replace the
linux/preempt.hwithlinux/sched.h, but should I fix it in this series? I mean, the commit1b93c03fb319doesn't exist in the tip for now :/If it's just a different include then go for it.
Make sure there are no nasty build issues during the merge window.
OK!