Merge branch 'sched/cputime' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks into sched/core

Pull cputime changes from Frederic Weisbecker:

  * Generalize exception handling

  * Fix race in context tracking state restore on return from exception
    and irq exit kernel preemption

  * Fix cputime scaling in full dynticks accounting dynamic off-case

  * Fix default Kconfig value

Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/context_tracking.h

@@ -1,31 +1,10 @@
 #ifndef _ASM_X86_CONTEXT_TRACKING_H
 #define _ASM_X86_CONTEXT_TRACKING_H
 
-#ifndef __ASSEMBLY__
-#include <linux/context_tracking.h>
-#include <asm/ptrace.h>
-
-static inline void exception_enter(struct pt_regs *regs)
-{
-	user_exit();
-}
-
-static inline void exception_exit(struct pt_regs *regs)
-{
-#ifdef CONFIG_CONTEXT_TRACKING
-	if (user_mode(regs))
-		user_enter();
-#endif
-}
-
-#else /* __ASSEMBLY__ */
-
 #ifdef CONFIG_CONTEXT_TRACKING
 # define SCHEDULE_USER call schedule_user
 #else
 # define SCHEDULE_USER call schedule
 #endif
 
-#endif /* !__ASSEMBLY__ */
-
 #endif

arch/x86/kernel/kvm.c

@@ -20,6 +20,7 @@
  *   Authors: Anthony Liguori <aliguori@us.ibm.com>
  */
 
+#include <linux/context_tracking.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/kvm_para.h>
@@ -43,7 +44,6 @@
 #include <asm/apicdef.h>
 #include <asm/hypervisor.h>
 #include <asm/kvm_guest.h>
-#include <asm/context_tracking.h>
 
 static int kvmapf = 1;
 
@@ -254,16 +254,18 @@ EXPORT_SYMBOL_GPL(kvm_read_and_reset_pf_reason);
 dotraplinkage void __kprobes
 do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
+	enum ctx_state prev_state;
+
 	switch (kvm_read_and_reset_pf_reason()) {
 	default:
 		do_page_fault(regs, error_code);
 		break;
 	case KVM_PV_REASON_PAGE_NOT_PRESENT:
 		/* page is swapped out by the host. */
-		exception_enter(regs);
+		prev_state = exception_enter();
 		exit_idle();
 		kvm_async_pf_task_wait((u32)read_cr2());
-		exception_exit(regs);
+		exception_exit(prev_state);
 		break;
 	case KVM_PV_REASON_PAGE_READY:
 		rcu_irq_enter();

arch/x86/kernel/traps.c

@@ -12,6 +12,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/context_tracking.h>
 #include <linux/interrupt.h>
 #include <linux/kallsyms.h>
 #include <linux/spinlock.h>
@@ -55,8 +56,6 @@
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
 #include <asm/mce.h>
-#include <asm/context_tracking.h>
-
 #include <asm/mach_traps.h>
 
 #ifdef CONFIG_X86_64
@@ -176,34 +175,38 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
 #define DO_ERROR(trapnr, signr, str, name)				\
 dotraplinkage void do_##name(struct pt_regs *regs, long error_code)	\
 {									\
-	exception_enter(regs);						\
+	enum ctx_state prev_state;					\
+									\
+	prev_state = exception_enter();					\
 	if (notify_die(DIE_TRAP, str, regs, error_code,			\
 			trapnr, signr) == NOTIFY_STOP) {		\
-		exception_exit(regs);					\
+		exception_exit(prev_state);				\
 		return;							\
 	}								\
 	conditional_sti(regs);						\
 	do_trap(trapnr, signr, str, regs, error_code, NULL);		\
-	exception_exit(regs);						\
+	exception_exit(prev_state);					\
 }
 
 #define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr)		\
 dotraplinkage void do_##name(struct pt_regs *regs, long error_code)	\
 {									\
 	siginfo_t info;							\
+	enum ctx_state prev_state;					\
+									\
 	info.si_signo = signr;						\
 	info.si_errno = 0;						\
 	info.si_code = sicode;						\
 	info.si_addr = (void __user *)siaddr;				\
-	exception_enter(regs);						\
+	prev_state = exception_enter();					\
 	if (notify_die(DIE_TRAP, str, regs, error_code,			\
 			trapnr, signr) == NOTIFY_STOP) {		\
-		exception_exit(regs);					\
+		exception_exit(prev_state);				\
 		return;							\
 	}								\
 	conditional_sti(regs);						\
 	do_trap(trapnr, signr, str, regs, error_code, &info);		\
-	exception_exit(regs);						\
+	exception_exit(prev_state);					\
 }
 
 DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV,
@@ -226,14 +229,16 @@ DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check,
 /* Runs on IST stack */
 dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code)
 {
-	exception_enter(regs);
+	enum ctx_state prev_state;
+
+	prev_state = exception_enter();
 	if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
 		       X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) {
 		preempt_conditional_sti(regs);
 		do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
 		preempt_conditional_cli(regs);
 	}
-	exception_exit(regs);
+	exception_exit(prev_state);
 }
 
 dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
@@ -241,7 +246,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 	static const char str[] = "double fault";
 	struct task_struct *tsk = current;
 
-	exception_enter(regs);
+	exception_enter();
 	/* Return not checked because double check cannot be ignored */
 	notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
 
@@ -261,8 +266,9 @@ dotraplinkage void __kprobes
 do_general_protection(struct pt_regs *regs, long error_code)
 {
 	struct task_struct *tsk;
+	enum ctx_state prev_state;
 
-	exception_enter(regs);
+	prev_state = exception_enter();
 	conditional_sti(regs);
 
 #ifdef CONFIG_X86_32
@@ -300,12 +306,14 @@ do_general_protection(struct pt_regs *regs, long error_code)
 
 	force_sig(SIGSEGV, tsk);
 exit:
-	exception_exit(regs);
+	exception_exit(prev_state);
 }
 
 /* May run on IST stack. */
 dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_code)
 {
+	enum ctx_state prev_state;
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 	/*
 	 * ftrace must be first, everything else may cause a recursive crash.
@@ -315,7 +323,7 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co
 	    ftrace_int3_handler(regs))
 		return;
 #endif
-	exception_enter(regs);
+	prev_state = exception_enter();
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
 	if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
 				SIGTRAP) == NOTIFY_STOP)
@@ -336,7 +344,7 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co
 	preempt_conditional_cli(regs);
 	debug_stack_usage_dec();
 exit:
-	exception_exit(regs);
+	exception_exit(prev_state);
 }
 
 #ifdef CONFIG_X86_64
@@ -393,11 +401,12 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
 dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 {
 	struct task_struct *tsk = current;
+	enum ctx_state prev_state;
 	int user_icebp = 0;
 	unsigned long dr6;
 	int si_code;
 
-	exception_enter(regs);
+	prev_state = exception_enter();
 
 	get_debugreg(dr6, 6);
 
@@ -467,7 +476,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 	debug_stack_usage_dec();
 
 exit:
-	exception_exit(regs);
+	exception_exit(prev_state);
 }
 
 /*
@@ -561,17 +570,21 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr)
 
 dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code)
 {
-	exception_enter(regs);
+	enum ctx_state prev_state;
+
+	prev_state = exception_enter();
 	math_error(regs, error_code, X86_TRAP_MF);
-	exception_exit(regs);
+	exception_exit(prev_state);
 }
 
 dotraplinkage void
 do_simd_coprocessor_error(struct pt_regs *regs, long error_code)
 {
-	exception_enter(regs);
+	enum ctx_state prev_state;
+
+	prev_state = exception_enter();
 	math_error(regs, error_code, X86_TRAP_XF);
-	exception_exit(regs);
+	exception_exit(prev_state);
 }
 
 dotraplinkage void
@@ -639,7 +652,9 @@ EXPORT_SYMBOL_GPL(math_state_restore);
 dotraplinkage void __kprobes
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
-	exception_enter(regs);
+	enum ctx_state prev_state;
+
+	prev_state = exception_enter();
 	BUG_ON(use_eager_fpu());
 
 #ifdef CONFIG_MATH_EMULATION
@@ -650,7 +665,7 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 
 		info.regs = regs;
 		math_emulate(&info);
-		exception_exit(regs);
+		exception_exit(prev_state);
 		return;
 	}
 #endif
@@ -658,15 +673,16 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 #ifdef CONFIG_X86_32
 	conditional_sti(regs);
 #endif
-	exception_exit(regs);
+	exception_exit(prev_state);
 }
 
 #ifdef CONFIG_X86_32
 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
 {
 	siginfo_t info;
+	enum ctx_state prev_state;
 
-	exception_enter(regs);
+	prev_state = exception_enter();
 	local_irq_enable();
 
 	info.si_signo = SIGILL;
@@ -678,7 +694,7 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
 		do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
 			&info);
 	}
-	exception_exit(regs);
+	exception_exit(prev_state);
 }
 #endif
 

arch/x86/mm/fault.c

@@ -13,12 +13,12 @@
 #include <linux/perf_event.h>		/* perf_sw_event		*/
 #include <linux/hugetlb.h>		/* hstate_index_to_shift	*/
 #include <linux/prefetch.h>		/* prefetchw			*/
+#include <linux/context_tracking.h>	/* exception_enter(), ...	*/
 
 #include <asm/traps.h>			/* dotraplinkage, ...		*/
 #include <asm/pgalloc.h>		/* pgd_*(), ...			*/
 #include <asm/kmemcheck.h>		/* kmemcheck_*(), ...		*/
 #include <asm/fixmap.h>			/* VSYSCALL_START		*/
-#include <asm/context_tracking.h>	/* exception_enter(), ...	*/
 
 /*
  * Page fault error code bits:
@@ -1222,7 +1222,9 @@ good_area:
 dotraplinkage void __kprobes
 do_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
-	exception_enter(regs);
+	enum ctx_state prev_state;
+
+	prev_state = exception_enter();
 	__do_page_fault(regs, error_code);
-	exception_exit(regs);
+	exception_exit(prev_state);
 }

include/linux/context_tracking.h

@@ -1,9 +1,9 @@
 #ifndef _LINUX_CONTEXT_TRACKING_H
 #define _LINUX_CONTEXT_TRACKING_H
 
-#ifdef CONFIG_CONTEXT_TRACKING
 #include <linux/sched.h>
 #include <linux/percpu.h>
+#include <asm/ptrace.h>
 
 struct context_tracking {
 	/*
@@ -13,12 +13,13 @@ struct context_tracking {
 	 * may be further optimized using static keys.
 	 */
 	bool active;
-	enum {
+	enum ctx_state {
 		IN_KERNEL = 0,
 		IN_USER,
 	} state;
 };
 
+#ifdef CONFIG_CONTEXT_TRACKING
 DECLARE_PER_CPU(struct context_tracking, context_tracking);
 
 static inline bool context_tracking_in_user(void)
@@ -33,12 +34,31 @@ static inline bool context_tracking_active(void)
 
 extern void user_enter(void);
 extern void user_exit(void);
+
+static inline enum ctx_state exception_enter(void)
+{
+	enum ctx_state prev_ctx;
+
+	prev_ctx = this_cpu_read(context_tracking.state);
+	user_exit();
+
+	return prev_ctx;
+}
+
+static inline void exception_exit(enum ctx_state prev_ctx)
+{
+	if (prev_ctx == IN_USER)
+		user_enter();
+}
+
 extern void context_tracking_task_switch(struct task_struct *prev,
 					 struct task_struct *next);
 #else
 static inline bool context_tracking_in_user(void) { return false; }
 static inline void user_enter(void) { }
 static inline void user_exit(void) { }
+static inline enum ctx_state exception_enter(void) { return 0; }
+static inline void exception_exit(enum ctx_state prev_ctx) { }
 static inline void context_tracking_task_switch(struct task_struct *prev,
 						struct task_struct *next) { }
 #endif /* !CONFIG_CONTEXT_TRACKING */

include/linux/sched.h

@@ -558,7 +558,7 @@ struct signal_struct {
 	cputime_t utime, stime, cutime, cstime;
 	cputime_t gtime;
 	cputime_t cgtime;
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	struct cputime prev_cputime;
 #endif
 	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
@@ -1158,7 +1158,7 @@ struct task_struct {
 
 	cputime_t utime, stime, utimescaled, stimescaled;
 	cputime_t gtime;
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	struct cputime prev_cputime;
 #endif
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN

init/Kconfig

@@ -509,6 +509,7 @@ config RCU_USER_QS
 config CONTEXT_TRACKING_FORCE
 	bool "Force context tracking"
 	depends on CONTEXT_TRACKING
+	default CONTEXT_TRACKING
 	help
 	  Probe on user/kernel boundaries by default in order to
 	  test the features that rely on it such as userspace RCU extended

kernel/fork.c

@@ -1230,7 +1230,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	p->utime = p->stime = p->gtime = 0;
 	p->utimescaled = p->stimescaled = 0;
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	p->prev_cputime.utime = p->prev_cputime.stime = 0;
 #endif
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN

kernel/sched/core.c

@@ -3082,11 +3082,13 @@ EXPORT_SYMBOL(preempt_schedule);
 asmlinkage void __sched preempt_schedule_irq(void)
 {
 	struct thread_info *ti = current_thread_info();
+	enum ctx_state prev_state;
 
 	/* Catch callers which need to be fixed */
 	BUG_ON(ti->preempt_count || !irqs_disabled());
 
-	user_exit();
+	prev_state = exception_enter();
+
 	do {
 		add_preempt_count(PREEMPT_ACTIVE);
 		local_irq_enable();
@@ -3100,6 +3102,8 @@ asmlinkage void __sched preempt_schedule_irq(void)
 		 */
 		barrier();
 	} while (need_resched());
+
+	exception_exit(prev_state);
 }
 
 #endif /* CONFIG_PREEMPT */

kernel/sched/cputime.c

@@ -388,82 +388,10 @@ static inline void irqtime_account_process_tick(struct task_struct *p, int user_
 						struct rq *rq) {}
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-/*
- * Account a single tick of cpu time.
- * @p: the process that the cpu time gets accounted to
- * @user_tick: indicates if the tick is a user or a system tick
- */
-void account_process_tick(struct task_struct *p, int user_tick)
-{
-	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
-	struct rq *rq = this_rq();
-
-	if (vtime_accounting_enabled())
-		return;
-
-	if (sched_clock_irqtime) {
-		irqtime_account_process_tick(p, user_tick, rq);
-		return;
-	}
-
-	if (steal_account_process_tick())
-		return;
-
-	if (user_tick)
-		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
-	else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
-		account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy,
-				    one_jiffy_scaled);
-	else
-		account_idle_time(cputime_one_jiffy);
-}
-
-/*
- * Account multiple ticks of steal time.
- * @p: the process from which the cpu time has been stolen
- * @ticks: number of stolen ticks
- */
-void account_steal_ticks(unsigned long ticks)
-{
-	account_steal_time(jiffies_to_cputime(ticks));
-}
-
-/*
- * Account multiple ticks of idle time.
- * @ticks: number of stolen ticks
- */
-void account_idle_ticks(unsigned long ticks)
-{
-
-	if (sched_clock_irqtime) {
-		irqtime_account_idle_ticks(ticks);
-		return;
-	}
-
-	account_idle_time(jiffies_to_cputime(ticks));
-}
-#endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
-
 /*
  * Use precise platform statistics if available:
  */
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
-void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
-{
-	*ut = p->utime;
-	*st = p->stime;
-}
-
-void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
-{
-	struct task_cputime cputime;
-
-	thread_group_cputime(p, &cputime);
-
-	*ut = cputime.utime;
-	*st = cputime.stime;
-}
 
 #ifndef __ARCH_HAS_VTIME_TASK_SWITCH
 void vtime_task_switch(struct task_struct *prev)
@@ -518,8 +446,80 @@ void vtime_account_irq_enter(struct task_struct *tsk)
 }
 EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
 #endif /* __ARCH_HAS_VTIME_ACCOUNT */
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
 
-#else /* !CONFIG_VIRT_CPU_ACCOUNTING */
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+	*ut = p->utime;
+	*st = p->stime;
+}
+
+void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+	struct task_cputime cputime;
+
+	thread_group_cputime(p, &cputime);
+
+	*ut = cputime.utime;
+	*st = cputime.stime;
+}
+#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
+/*
+ * Account a single tick of cpu time.
+ * @p: the process that the cpu time gets accounted to
+ * @user_tick: indicates if the tick is a user or a system tick
+ */
+void account_process_tick(struct task_struct *p, int user_tick)
+{
+	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+	struct rq *rq = this_rq();
+
+	if (vtime_accounting_enabled())
+		return;
+
+	if (sched_clock_irqtime) {
+		irqtime_account_process_tick(p, user_tick, rq);
+		return;
+	}
+
+	if (steal_account_process_tick())
+		return;
+
+	if (user_tick)
+		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+	else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
+		account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy,
+				    one_jiffy_scaled);
+	else
+		account_idle_time(cputime_one_jiffy);
+}
+
+/*
+ * Account multiple ticks of steal time.
+ * @p: the process from which the cpu time has been stolen
+ * @ticks: number of stolen ticks
+ */
+void account_steal_ticks(unsigned long ticks)
+{
+	account_steal_time(jiffies_to_cputime(ticks));
+}
+
+/*
+ * Account multiple ticks of idle time.
+ * @ticks: number of stolen ticks
+ */
+void account_idle_ticks(unsigned long ticks)
+{
+
+	if (sched_clock_irqtime) {
+		irqtime_account_idle_ticks(ticks);
+		return;
+	}
+
+	account_idle_time(jiffies_to_cputime(ticks));
+}
 
 static cputime_t scale_stime(cputime_t stime, cputime_t rtime, cputime_t total)
 {
@@ -545,6 +545,12 @@ static void cputime_adjust(struct task_cputime *curr,
 {
 	cputime_t rtime, stime, total;
 
+	if (vtime_accounting_enabled()) {
+		*ut = curr->utime;
+		*st = curr->stime;
+		return;
+	}
+
 	stime = curr->stime;
 	total = stime + curr->utime;
 
@@ -597,7 +603,7 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime
 	thread_group_cputime(p, &cputime);
 	cputime_adjust(&cputime, &p->signal->prev_cputime, ut, st);
 }
-#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */
+#endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 static unsigned long long vtime_delta(struct task_struct *tsk)