sched: make migrate_enable/migrate_disable inline

For 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() directly.

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

Link: https://lore.kernel.org/bpf/CAADnVQ+5sEDKHdsJY5ZsfGDO_1SEhhQWHrt2SMBG5SYyQ+jt7w@mail.gmail.com/ [1]
Signed-off-by: Menglong Dong <[email protected]>

Author: image-dragon

Kbuild

@@ -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

@@ -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

@@ -49,6 +49,9 @@
 #include <linux/tracepoint-defs.h>
 #include <linux/unwind_deferred_types.h>
 #include <asm/kmap_size.h>
+#ifndef COMPILE_OFFSETS
+#include <generated/rq-offsets.h>
+#endif
 
 /* task_struct member predeclarations (sorted alphabetically): */
 struct audit_context;
@@ -2307,4 +2310,78 @@ static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct allo
 #define alloc_tag_restore(_tag, _old)		do {} while (0)
 #endif
 
+#ifndef COMPILE_OFFSETS
+
+extern void __migrate_enable(void);
+
+struct rq;
+DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
+
+#ifdef CONFIG_SMP
+#define this_rq_raw() arch_raw_cpu_ptr(&runqueues)
+#else
+#define this_rq_raw() PERCPU_PTR(&runqueues)
+#endif
+
+static inline void migrate_enable(void)
+{
+	struct task_struct *p = current;
+
+#ifdef CONFIG_DEBUG_PREEMPT
+	/*
+	 * Check both overflow from migrate_disable() and superfluous
+	 * migrate_enable().
+	 */
+	if (WARN_ON_ONCE((s16)p->migration_disabled <= 0))
+		return;
+#endif
+
+	if (p->migration_disabled > 1) {
+		p->migration_disabled--;
+		return;
+	}
+
+	/*
+	 * Ensure stop_task runs either before or after this, and that
+	 * __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule().
+	 */
+	guard(preempt)();
+	if (unlikely(p->cpus_ptr != &p->cpus_mask))
+		__migrate_enable();
+	/*
+	 * Mustn't clear migration_disabled() until cpus_ptr points back at the
+	 * regular cpus_mask, otherwise things that race (eg.
+	 * select_fallback_rq) get confused.
+	 */
+	barrier();
+	p->migration_disabled = 0;
+	(*(unsigned int *)((void *)this_rq_raw() + RQ_nr_pinned))--;
+}
+
+static inline void migrate_disable(void)
+{
+	struct task_struct *p = current;
+
+	if (p->migration_disabled) {
+#ifdef CONFIG_DEBUG_PREEMPT
+		/*
+		 *Warn about overflow half-way through the range.
+		 */
+		WARN_ON_ONCE((s16)p->migration_disabled < 0);
+#endif
+		p->migration_disabled++;
+		return;
+	}
+
+	guard(preempt)();
+	(*(unsigned int *)((void *)this_rq_raw() + RQ_nr_pinned))++;
+	p->migration_disabled = 1;
+}
+#else
+static inline void migrate_disable(void) { }
+static inline void migrate_enable(void) { }
+#endif
+
+DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable())
+
 #endif

kernel/bpf/verifier.c

@@ -23870,8 +23870,7 @@ 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_disable)
-BTF_ID(func, migrate_enable)
+BTF_ID(func, __migrate_enable)
 #endif
 #if !defined CONFIG_PREEMPT_RCU && !defined CONFIG_TINY_RCU
 BTF_ID(func, rcu_read_unlock_strict)

kernel/sched/core.c

@@ -119,6 +119,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_compute_energy_tp);
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
+EXPORT_SYMBOL_GPL(runqueues);
 
 #ifdef CONFIG_SCHED_PROXY_EXEC
 DEFINE_STATIC_KEY_TRUE(__sched_proxy_exec);
@@ -2381,66 +2382,17 @@ static void migrate_disable_switch(struct rq *rq, struct task_struct *p)
 	__do_set_cpus_allowed(p, &ac);
 }
 
-void migrate_disable(void)
-{
-	struct task_struct *p = current;
-
-	if (p->migration_disabled) {
-#ifdef CONFIG_DEBUG_PREEMPT
-		/*
-		 *Warn about overflow half-way through the range.
-		 */
-		WARN_ON_ONCE((s16)p->migration_disabled < 0);
-#endif
-		p->migration_disabled++;
-		return;
-	}
-
-	guard(preempt)();
-	this_rq()->nr_pinned++;
-	p->migration_disabled = 1;
-}
-EXPORT_SYMBOL_GPL(migrate_disable);
-
-void migrate_enable(void)
+void __migrate_enable(void)
 {
 	struct task_struct *p = current;
 	struct affinity_context ac = {
 		.new_mask  = &p->cpus_mask,
 		.flags     = SCA_MIGRATE_ENABLE,
 	};
 
-#ifdef CONFIG_DEBUG_PREEMPT
-	/*
-	 * Check both overflow from migrate_disable() and superfluous
-	 * migrate_enable().
-	 */
-	if (WARN_ON_ONCE((s16)p->migration_disabled <= 0))
-		return;
-#endif
-
-	if (p->migration_disabled > 1) {
-		p->migration_disabled--;
-		return;
-	}
-
-	/*
-	 * Ensure stop_task runs either before or after this, and that
-	 * __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule().
-	 */
-	guard(preempt)();
-	if (p->cpus_ptr != &p->cpus_mask)
-		__set_cpus_allowed_ptr(p, &ac);
-	/*
-	 * Mustn't clear migration_disabled() until cpus_ptr points back at the
-	 * regular cpus_mask, otherwise things that race (eg.
-	 * select_fallback_rq) get confused.
-	 */
-	barrier();
-	p->migration_disabled = 0;
-	this_rq()->nr_pinned--;
+	__set_cpus_allowed_ptr(p, &ac);
 }
-EXPORT_SYMBOL_GPL(migrate_enable);
+EXPORT_SYMBOL_GPL(__migrate_enable);
 
 static inline bool rq_has_pinned_tasks(struct rq *rq)
 {

kernel/sched/rq-offsets.c

@@ -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;
+}