Message-Id: <1344006145-26115-2-git-send-email-fweisbec@gmail.com>
Date:	Fri,  3 Aug 2012 17:02:21 +0200
From:	Frederic Weisbecker <fweisbec@...il.com>
To:	LKML <linux-kernel@...r.kernel.org>
Cc:	Frederic Weisbecker <fweisbec@...il.com>,
	Alessio Igor Bogani <abogani@...nel.org>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Avi Kivity <avi@...hat.com>,
	Chris Metcalf <cmetcalf@...era.com>,
	Christoph Lameter <cl@...ux.com>,
	Geoff Levand <geoff@...radead.org>,
	Gilad Ben Yossef <gilad@...yossef.com>,
	Hakan Akkan <hakanakkan@...il.com>,
	"H. Peter Anvin" <hpa@...or.com>, Ingo Molnar <mingo@...nel.org>,
	Kevin Hilman <khilman@...com>,
	Max Krasnyansky <maxk@...lcomm.com>,
	"Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>,
	Peter Zijlstra <peterz@...radead.org>,
	Stephen Hemminger <shemminger@...tta.com>,
	Steven Rostedt <rostedt@...dmis.org>,
	Sven-Thorsten Dietrich <thebigcorporation@...il.com>,
	Thomas Gleixner <tglx@...utronix.de>
Subject: [PATCH 1/5] code_domain: New code domain tracking susbsystem

Create a new subsystem that handles the probing on kernel
boundaries to keep track of the transitions between code domains
with two basic initial domains: user or kernel.

This is an abstraction of some RCU code that use it to implement
its userspace extended quiescent state.

We need to pull this up from RCU into this new level of indirection
because this probing is also going to be used to implement an "on
demand" generic virtual cputime accounting. A necessary step to
shutdown the tick while still accounting the cputime.

Signed-off-by: Frederic Weisbecker <fweisbec@...il.com>
Cc: Alessio Igor Bogani <abogani@...nel.org>
Cc: Andrew Morton <akpm@...ux-foundation.org>
Cc: Avi Kivity <avi@...hat.com>
Cc: Chris Metcalf <cmetcalf@...era.com>
Cc: Christoph Lameter <cl@...ux.com>
Cc: Geoff Levand <geoff@...radead.org>
Cc: Gilad Ben Yossef <gilad@...yossef.com>
Cc: Hakan Akkan <hakanakkan@...il.com>
Cc: H. Peter Anvin <hpa@...or.com>
Cc: Ingo Molnar <mingo@...nel.org>
Cc: Kevin Hilman <khilman@...com>
Cc: Max Krasnyansky <maxk@...lcomm.com>
Cc: Paul E. McKenney <paulmck@...ux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Stephen Hemminger <shemminger@...tta.com>
Cc: Steven Rostedt <rostedt@...dmis.org>
Cc: Sven-Thorsten Dietrich <thebigcorporation@...il.com>
Cc: Thomas Gleixner <tglx@...utronix.de>
---
 arch/Kconfig                                  |   12 +++---
 arch/x86/Kconfig                              |    2 +-
 arch/x86/include/asm/{rcu.h => code_domain.h} |   12 +++---
 arch/x86/kernel/ptrace.c                      |    6 +-
 arch/x86/kernel/signal.c                      |    5 +-
 arch/x86/kernel/traps.c                       |    2 +-
 arch/x86/mm/fault.c                           |    2 +-
 include/linux/code_domain.h                   |   18 ++++++++
 include/linux/rcupdate.h                      |    2 -
 include/linux/sched.h                         |    8 ---
 init/Kconfig                                  |   24 ++++++----
 kernel/Makefile                               |    1 +
 kernel/code_domain_tracking.c                 |   59 +++++++++++++++++++++++++
 kernel/rcutree.c                              |   42 +-----------------
 kernel/sched/core.c                           |    9 ++--
 15 files changed, 121 insertions(+), 83 deletions(-)
 rename arch/x86/include/asm/{rcu.h => code_domain.h} (53%)
 create mode 100644 include/linux/code_domain.h
 create mode 100644 kernel/code_domain_tracking.c

diff --git a/arch/Kconfig b/arch/Kconfig
index d891c62..2ce2a2f 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -277,14 +277,14 @@ config SECCOMP_FILTER
 config HAVE_VIRT_CPU_ACCOUNTING
 	bool
 
-config HAVE_RCU_USER_QS
+config HAVE_CODE_DOMAIN_TRACKING
 	bool
 	help
-	  Provide kernel entry/exit hooks necessary for userspace
+	  Provide kernel boundaries probing necessary for userspace
 	  RCU extended quiescent state. Syscalls need to be wrapped inside
-	  rcu_user_exit()-rcu_user_enter() through the slow path using
-	  TIF_NOHZ flag. Exceptions handlers must be wrapped as well. Irqs
-	  are already protected inside rcu_irq_enter/rcu_irq_exit() but
-	  preemption or signal handling on irq exit still need to be protected.
+	  user_exit()-user_enter() through the slow path using TIF_NOHZ flag.
+	  Exceptions handlers must be wrapped as well. Irqs are already
+	  protected inside rcu_irq_enter/rcu_irq_exit() but preemption or
+	  signal handling on irq exit still need to be protected.
 
 source "kernel/gcov/Kconfig"
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 38dfcc2..cc9bf3e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -95,7 +95,7 @@ config X86
 	select KTIME_SCALAR if X86_32
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
-	select HAVE_RCU_USER_QS if X86_64
+	select HAVE_CODE_DOMAIN_TRACKING if X86_64
 
 config INSTRUCTION_DECODER
 	def_bool (KPROBES || PERF_EVENTS || UPROBES)
diff --git a/arch/x86/include/asm/rcu.h b/arch/x86/include/asm/code_domain.h
similarity index 53%
rename from arch/x86/include/asm/rcu.h
rename to arch/x86/include/asm/code_domain.h
index 439815b..e245152 100644
--- a/arch/x86/include/asm/rcu.h
+++ b/arch/x86/include/asm/code_domain.h
@@ -1,19 +1,19 @@
-#ifndef _ASM_X86_RCU_H
-#define _ASM_X86_RCU_H
+#ifndef _ASM_X86_CODE_DOMAIN_H
+#define _ASM_X86_CODE_DOMAIN_H
 
-#include <linux/rcupdate.h>
+#include <linux/code_domain.h>
 #include <asm/ptrace.h>
 
 static inline void exception_enter(struct pt_regs *regs)
 {
-	rcu_user_exit();
+	user_exit();
 }
 
 static inline void exception_exit(struct pt_regs *regs)
 {
-#ifdef CONFIG_RCU_USER_QS
+#ifdef CONFIG_CODE_DOMAIN_TRACKING
 	if (user_mode(regs))
-		rcu_user_enter();
+		user_enter();
 #endif
 }
 
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 9f94f8e..5bc2e50 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -21,7 +21,7 @@
 #include <linux/signal.h>
 #include <linux/perf_event.h>
 #include <linux/hw_breakpoint.h>
-#include <linux/rcupdate.h>
+#include <linux/code_domain.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -1464,7 +1464,7 @@ long syscall_trace_enter(struct pt_regs *regs)
 {
 	long ret = 0;
 
-	rcu_user_exit();
+	user_exit();
 
 	/*
 	 * If we stepped into a sysenter/syscall insn, it trapped in
@@ -1530,5 +1530,5 @@ void syscall_trace_leave(struct pt_regs *regs)
 	if (step || test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, step);
 
-	rcu_user_enter();
+	user_enter();
 }
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 5cc2579..fc3e12c 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -19,6 +19,7 @@
 #include <linux/uaccess.h>
 #include <linux/user-return-notifier.h>
 #include <linux/uprobes.h>
+#include <linux/code_domain.h>
 
 #include <asm/processor.h>
 #include <asm/ucontext.h>
@@ -776,7 +777,7 @@ static void do_signal(struct pt_regs *regs)
 void
 do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 {
-	rcu_user_exit();
+	user_exit();
 
 #ifdef CONFIG_X86_MCE
 	/* notify userspace of pending MCEs */
@@ -804,7 +805,7 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 	clear_thread_flag(TIF_IRET);
 #endif /* CONFIG_X86_32 */
 
-	rcu_user_enter();
+	user_enter();
 }
 
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 9b8195b..2d1fe02 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -52,7 +52,7 @@
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
 #include <asm/mce.h>
-#include <asm/rcu.h>
+#include <asm/code_domain.h>
 
 #include <asm/mach_traps.h>
 
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 7dde46d..be026ea 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -18,7 +18,7 @@
 #include <asm/pgalloc.h>		/* pgd_*(), ...			*/
 #include <asm/kmemcheck.h>		/* kmemcheck_*(), ...		*/
 #include <asm/fixmap.h>			/* VSYSCALL_START		*/
-#include <asm/rcu.h>			/* exception_enter(), ...	*/
+#include <asm/code_domain.h>		/* exception_enter(), ...	*/
 
 /*
  * Page fault error code bits:
diff --git a/include/linux/code_domain.h b/include/linux/code_domain.h
new file mode 100644
index 0000000..5d4513d
--- /dev/null
+++ b/include/linux/code_domain.h
@@ -0,0 +1,18 @@
+#ifndef _LINUX_CODE_DOMAIN_TRACKING_H
+#define _LINUX_CODE_DOMAIN_TRACKING_H
+
+#ifdef CONFIG_CODE_DOMAIN_TRACKING
+#include <linux/sched.h>
+
+extern void user_enter(void);
+extern void user_exit(void);
+extern void code_domain_task_switch(struct task_struct *prev,
+				    struct task_struct *next);
+#else
+static inline void user_enter(void) { }
+static inline void user_exit(void) { }
+static inline void code_domain_task_switch(struct task_struct *prev,
+					   struct task_struct *next) { }
+#endif /* !CONFIG_CODE_DOMAIN_TRACKING */
+
+#endif
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 1fc0a0e..e411117 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -197,8 +197,6 @@ extern void rcu_user_enter(void);
 extern void rcu_user_exit(void);
 extern void rcu_user_enter_irq(void);
 extern void rcu_user_exit_irq(void);
-extern void rcu_user_hooks_switch(struct task_struct *prev,
-				  struct task_struct *next);
 #else
 static inline void rcu_user_enter(void) { }
 static inline void rcu_user_exit(void) { }
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 30105f4..7b7a438 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1899,14 +1899,6 @@ static inline void rcu_copy_process(struct task_struct *p)
 
 #endif
 
-static inline void rcu_switch(struct task_struct *prev,
-			      struct task_struct *next)
-{
-#ifdef CONFIG_RCU_USER_QS
-	rcu_user_hooks_switch(prev, next);
-#endif
-}
-
 #ifdef CONFIG_SMP
 extern void do_set_cpus_allowed(struct task_struct *p,
 			       const struct cpumask *new_mask);
diff --git a/init/Kconfig b/init/Kconfig
index cc1d581..e2854a0 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -404,6 +404,19 @@ config AUDIT_LOGINUID_IMMUTABLE
 source "kernel/irq/Kconfig"
 source "kernel/time/Kconfig"
 
+config CODE_DOMAIN_TRACKING
+       bool
+
+config CODE_DOMAIN_TRACKING_FORCE
+	bool "Force kernel boundaries probing"
+	depends on CODE_DOMAIN_TRACKING
+	help
+	  Set the probes in user/kernel boundaries by default in order to
+	  test the features that rely on it such as userspace RCU extended
+	  quiescent states.
+	  This test is there for debugging until we have a real user like a
+	  full adaptive nohz option.
+
 menu "RCU Subsystem"
 
 choice
@@ -456,7 +469,8 @@ config PREEMPT_RCU
 
 config RCU_USER_QS
 	bool "Consider userspace as in RCU extended quiescent state"
-	depends on HAVE_RCU_USER_QS && SMP
+	depends on HAVE_CODE_DOMAIN_TRACKING && SMP
+	select CODE_DOMAIN_TRACKING
 	help
 	  This option sets hooks on kernel / userspace boundaries and
 	  puts RCU in extended quiescent state when the CPU runs in
@@ -464,14 +478,6 @@ config RCU_USER_QS
 	  excluded from the global RCU state machine and thus doesn't
 	  to keep the timer tick on for RCU.
 
-config RCU_USER_QS_FORCE
-	bool "Force userspace extended QS by default"
-	depends on RCU_USER_QS
-	help
-	  Set the hooks in user/kernel boundaries by default in order to
-	  test this feature that treats userspace as an extended quiescent
-	  state until we have a real user like a full adaptive nohz option.
-
 config RCU_FANOUT
 	int "Tree-based hierarchical RCU fanout value"
 	range 2 64 if 64BIT
diff --git a/kernel/Makefile b/kernel/Makefile
index c0cc67a..86bc293 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -110,6 +110,7 @@ obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o
 obj-$(CONFIG_PADATA) += padata.o
 obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
 obj-$(CONFIG_JUMP_LABEL) += jump_label.o
+obj-$(CONFIG_CODE_DOMAIN_TRACKING) += code_domain_tracking.o
 
 $(obj)/configs.o: $(obj)/config_data.h
 
diff --git a/kernel/code_domain_tracking.c b/kernel/code_domain_tracking.c
new file mode 100644
index 0000000..8332c76
--- /dev/null
+++ b/kernel/code_domain_tracking.c
@@ -0,0 +1,59 @@
+#include <linux/code_domain.h>
+#include <linux/rcupdate.h>
+#include <linux/sched.h>
+#include <linux/percpu.h>
+
+struct code_domain_tracking {
+	/*
+	 * When tracking_active is false, hooks are not
+	 * set to minimize overhead: TIF flags are cleared
+	 * and calls to user_enter/exit are ignored. This
+	 * may be further optimized using static keys.
+	 */
+	bool tracking_active;
+	enum {
+		IN_KERNEL = 0,
+		IN_USER,
+	} state;
+};
+
+DEFINE_PER_CPU(struct code_domain_tracking, code_domain) = {
+#ifdef CONFIG_CODE_DOMAIN_TRACKING_FORCE
+	.tracking_active = true,
+#endif
+};
+
+void user_enter(void)
+{
+	unsigned long flags;
+
+	WARN_ON_ONCE(!current->mm);
+	local_irq_save(flags);
+	if (__this_cpu_read(code_domain.tracking_active) &&
+	    __this_cpu_read(code_domain.state) != IN_USER) {
+		__this_cpu_write(code_domain.state, IN_USER);
+		rcu_user_enter();
+	}
+	local_irq_restore(flags);
+}
+
+void user_exit(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	if (__this_cpu_read(code_domain.state) == IN_USER) {
+		__this_cpu_write(code_domain.state, IN_KERNEL);
+		rcu_user_exit();
+	}
+	local_irq_restore(flags);
+}
+
+void code_domain_task_switch(struct task_struct *prev,
+			     struct task_struct *next)
+{
+	if (__this_cpu_read(code_domain.tracking_active)) {
+		clear_tsk_thread_flag(prev, TIF_NOHZ);
+		set_tsk_thread_flag(next, TIF_NOHZ);
+	}
+}
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 318d00e..f6a24cb 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -212,9 +212,6 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 	.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
 	.dynticks = ATOMIC_INIT(1),
-#if defined(CONFIG_RCU_USER_QS) && !defined(CONFIG_RCU_USER_QS_FORCE)
-	.ignore_user_qs = true,
-#endif
 };
 
 static int blimit = 10;		/* Maximum callbacks per rcu_do_batch. */
@@ -448,18 +445,7 @@ EXPORT_SYMBOL_GPL(rcu_idle_enter);
  */
 void rcu_user_enter(void)
 {
-	unsigned long flags;
-	struct rcu_dynticks *rdtp;
-
-	WARN_ON_ONCE(!current->mm);
-
-	local_irq_save(flags);
-	rdtp = &__get_cpu_var(rcu_dynticks);
-	if (!rdtp->ignore_user_qs && !rdtp->in_user) {
-		rdtp->in_user = true;
-		rcu_eqs_enter(1);
-	}
-	local_irq_restore(flags);
+	rcu_eqs_enter(1);
 }
 EXPORT_SYMBOL_GPL(rcu_user_enter);
 
@@ -597,16 +583,7 @@ EXPORT_SYMBOL_GPL(rcu_idle_exit);
  */
 void rcu_user_exit(void)
 {
-	unsigned long flags;
-	struct rcu_dynticks *rdtp;
-
-	local_irq_save(flags);
-	rdtp = &__get_cpu_var(rcu_dynticks);
-	if (rdtp->in_user) {
-		rdtp->in_user = false;
-		rcu_eqs_exit(1);
-	}
-	local_irq_restore(flags);
+	rcu_eqs_exit(1);
 }
 EXPORT_SYMBOL_GPL(rcu_user_exit);
 
@@ -730,21 +707,6 @@ int rcu_is_cpu_idle(void)
 }
 EXPORT_SYMBOL(rcu_is_cpu_idle);
 
-#ifdef CONFIG_RCU_USER_QS
-void rcu_user_hooks_switch(struct task_struct *prev,
-			   struct task_struct *next)
-{
-	struct rcu_dynticks *rdtp;
-
-	/* Interrupts are disabled in context switch */
-	rdtp = &__get_cpu_var(rcu_dynticks);
-	if (!rdtp->ignore_user_qs) {
-		clear_tsk_thread_flag(prev, TIF_NOHZ);
-		set_tsk_thread_flag(next, TIF_NOHZ);
-	}
-}
-#endif /* #ifdef CONFIG_RCU_USER_QS */
-
 #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)
 
 /*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 94a4894..64bb370 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -72,6 +72,7 @@
 #include <linux/slab.h>
 #include <linux/init_task.h>
 #include <linux/binfmts.h>
+#include <linux/code_domain.h>
 
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
@@ -1925,8 +1926,8 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
 #endif
 
+	code_domain_task_switch(prev, next);
 	/* Here we just switch the register state and the stack. */
-	rcu_switch(prev, next);
 	switch_to(prev, next, prev);
 
 	barrier();
@@ -2920,9 +2921,9 @@ EXPORT_SYMBOL(schedule);
 
 asmlinkage void __sched schedule_user(void)
 {
-	rcu_user_exit();
+	user_exit();
 	schedule();
-	rcu_user_enter();
+	user_enter();
 }
 
 /**
@@ -3026,7 +3027,7 @@ asmlinkage void __sched preempt_schedule_irq(void)
 	/* Catch callers which need to be fixed */
 	BUG_ON(ti->preempt_count || !irqs_disabled());
 
-	rcu_user_exit();
+	user_exit();
 	do {
 		add_preempt_count(PREEMPT_ACTIVE);
 		local_irq_enable();
-- 
1.7.5.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists