Merge branch 'rcu/idle' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/rcu

Pull the RCU adaptive-idle feature from Paul E. McKenney:

 "This series adds RCU APIs that allow non-idle tasks to
  enter RCU idle mode and provides x86 code to make use of them, allowing
  RCU to treat user-mode execution as an extended quiescent state when the
  new RCU_USER_QS kernel configuration parameter is specified.  Work is
  in progress to port this to a few other architectures, but is not part
  of this series."

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

8 files changed, 131 insertions, 52 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 50a1d1f9b6d3..20c49b8450b8 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -97,6 +97,7 @@ 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
 
 config INSTRUCTION_DECODER
 	def_bool (KPROBES || PERF_EVENTS || UPROBES)
diff --git a/arch/x86/include/asm/rcu.h b/arch/x86/include/asm/rcu.h
new file mode 100644
index 000000000000..d1ac07a23979
--- /dev/null
+++ b/arch/x86/include/asm/rcu.h
@@ -0,0 +1,32 @@
+#ifndef _ASM_X86_RCU_H
+#define _ASM_X86_RCU_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/rcupdate.h>
+#include <asm/ptrace.h>
+
+static inline void exception_enter(struct pt_regs *regs)
+{
+	rcu_user_exit();
+}
+
+static inline void exception_exit(struct pt_regs *regs)
+{
+#ifdef CONFIG_RCU_USER_QS
+	if (user_mode(regs))
+		rcu_user_enter();
+#endif
+}
+
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_RCU_USER_QS
+# define SCHEDULE_USER call schedule_user
+#else
+# define SCHEDULE_USER call schedule
+#endif
+
+#endif /* !__ASSEMBLY__ */
+
+#endif
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 89f794f007ec..c535d847e3b5 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -89,6 +89,7 @@ struct thread_info {
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
 #define TIF_IA32		17	/* IA32 compatibility process */
 #define TIF_FORK		18	/* ret_from_fork */
+#define TIF_NOHZ		19	/* in adaptive nohz mode */
 #define TIF_MEMDIE		20	/* is terminating due to OOM killer */
 #define TIF_DEBUG		21	/* uses debug registers */
 #define TIF_IO_BITMAP		22	/* uses I/O bitmap */
@@ -114,6 +115,7 @@ struct thread_info {
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
 #define _TIF_FORK		(1 << TIF_FORK)
+#define _TIF_NOHZ		(1 << TIF_NOHZ)
 #define _TIF_DEBUG		(1 << TIF_DEBUG)
 #define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
 #define _TIF_FORCED_TF		(1 << TIF_FORCED_TF)
@@ -126,12 +128,13 @@ struct thread_info {
 /* work to do in syscall_trace_enter() */
 #define _TIF_WORK_SYSCALL_ENTRY	\
 	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_AUDIT |	\
-	 _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT)
+	 _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT |	\
+	 _TIF_NOHZ)
 
 /* work to do in syscall_trace_leave() */
 #define _TIF_WORK_SYSCALL_EXIT	\
 	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP |	\
-	 _TIF_SYSCALL_TRACEPOINT)
+	 _TIF_SYSCALL_TRACEPOINT | _TIF_NOHZ)
 
 /* work to do on interrupt/exception return */
 #define _TIF_WORK_MASK							\
@@ -141,7 +144,8 @@ struct thread_info {
 
 /* work to do on any return to user space */
 #define _TIF_ALLWORK_MASK						\
-	((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT)
+	((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT |	\
+	_TIF_NOHZ)
 
 /* Only used for 64 bit */
 #define _TIF_DO_NOTIFY_MASK						\
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 69babd8c834f..1a8f3cbb6ee3 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -56,6 +56,7 @@
 #include <asm/ftrace.h>
 #include <asm/percpu.h>
 #include <asm/asm.h>
+#include <asm/rcu.h>
 #include <linux/err.h>
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
@@ -565,7 +566,7 @@ sysret_careful:
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	pushq_cfi %rdi
-	call schedule
+	SCHEDULE_USER
 	popq_cfi %rdi
 	jmp sysret_check
 
@@ -678,7 +679,7 @@ int_careful:
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	pushq_cfi %rdi
-	call schedule
+	SCHEDULE_USER
 	popq_cfi %rdi
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
@@ -974,7 +975,7 @@ retint_careful:
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	pushq_cfi %rdi
-	call  schedule
+	SCHEDULE_USER
 	popq_cfi %rdi
 	GET_THREAD_INFO(%rcx)
 	DISABLE_INTERRUPTS(CLBR_NONE)
@@ -1449,7 +1450,7 @@ paranoid_userspace:
 paranoid_schedule:
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_ANY)
-	call schedule
+	SCHEDULE_USER
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
 	jmp paranoid_userspace
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index c4c6a5c2bf0f..9f94f8ec26e4 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -21,6 +21,7 @@
 #include <linux/signal.h>
 #include <linux/perf_event.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/rcupdate.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -1463,6 +1464,8 @@ long syscall_trace_enter(struct pt_regs *regs)
 {
 	long ret = 0;
 
+	rcu_user_exit();
+
 	/*
 	 * If we stepped into a sysenter/syscall insn, it trapped in
 	 * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP.
@@ -1526,4 +1529,6 @@ void syscall_trace_leave(struct pt_regs *regs)
 			!test_thread_flag(TIF_SYSCALL_EMU);
 	if (step || test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, step);
+
+	rcu_user_enter();
 }
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index b280908a376e..bca0ab903e57 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -779,6 +779,8 @@ 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();
+
 #ifdef CONFIG_X86_MCE
 	/* notify userspace of pending MCEs */
 	if (thread_info_flags & _TIF_MCE_NOTIFY)
@@ -804,6 +806,8 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 #ifdef CONFIG_X86_32
 	clear_thread_flag(TIF_IRET);
 #endif /* CONFIG_X86_32 */
+
+	rcu_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 b481341c9369..378967578f22 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -55,6 +55,7 @@
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
 #include <asm/mce.h>
+#include <asm/rcu.h>
 
 #include <asm/mach_traps.h>
 
@@ -180,11 +181,15 @@ vm86_trap:
 #define DO_ERROR(trapnr, signr, str, name)				\
 dotraplinkage void do_##name(struct pt_regs *regs, long error_code)	\
 {									\
-	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr)	\
-							== NOTIFY_STOP)	\
+	exception_enter(regs);						\
+	if (notify_die(DIE_TRAP, str, regs, error_code,			\
+			trapnr, signr) == NOTIFY_STOP) {		\
+		exception_exit(regs);					\
 		return;							\
+	}								\
 	conditional_sti(regs);						\
 	do_trap(trapnr, signr, str, regs, error_code, NULL);		\
+	exception_exit(regs);						\
 }
 
 #define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr)		\
@@ -195,11 +200,15 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code)	\
 	info.si_errno = 0;						\
 	info.si_code = sicode;						\
 	info.si_addr = (void __user *)siaddr;				\
-	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr)	\
-							== NOTIFY_STOP)	\
+	exception_enter(regs);						\
+	if (notify_die(DIE_TRAP, str, regs, error_code,			\
+			trapnr, signr) == NOTIFY_STOP) {		\
+		exception_exit(regs);					\
 		return;							\
+	}								\
 	conditional_sti(regs);						\
 	do_trap(trapnr, signr, str, regs, error_code, &info);		\
+	exception_exit(regs);						\
 }
 
 DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV,
@@ -222,12 +231,14 @@ 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);
 	if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
-			X86_TRAP_SS, SIGBUS) == NOTIFY_STOP)
-		return;
-	preempt_conditional_sti(regs);
-	do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
-	preempt_conditional_cli(regs);
+		       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);
 }
 
 dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
@@ -235,6 +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);
 	/* Return not checked because double check cannot be ignored */
 	notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
 
@@ -255,16 +267,29 @@ do_general_protection(struct pt_regs *regs, long error_code)
 {
 	struct task_struct *tsk;
 
+	exception_enter(regs);
 	conditional_sti(regs);
 
 #ifdef CONFIG_X86_32
-	if (regs->flags & X86_VM_MASK)
-		goto gp_in_vm86;
+	if (regs->flags & X86_VM_MASK) {
+		local_irq_enable();
+		handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code);
+		goto exit;
+	}
 #endif
 
 	tsk = current;
-	if (!user_mode(regs))
-		goto gp_in_kernel;
+	if (!user_mode(regs)) {
+		if (fixup_exception(regs))
+			goto exit;
+
+		tsk->thread.error_code = error_code;
+		tsk->thread.trap_nr = X86_TRAP_GP;
+		if (notify_die(DIE_GPF, "general protection fault", regs, error_code,
+			       X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP)
+			die("general protection fault", regs, error_code);
+		goto exit;
+	}
 
 	tsk->thread.error_code = error_code;
 	tsk->thread.trap_nr = X86_TRAP_GP;
@@ -279,25 +304,8 @@ do_general_protection(struct pt_regs *regs, long error_code)
 	}
 
 	force_sig(SIGSEGV, tsk);
-	return;
-
-#ifdef CONFIG_X86_32
-gp_in_vm86:
-	local_irq_enable();
-	handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code);
-	return;
-#endif
-
-gp_in_kernel:
-	if (fixup_exception(regs))
-		return;
-
-	tsk->thread.error_code = error_code;
-	tsk->thread.trap_nr = X86_TRAP_GP;
-	if (notify_die(DIE_GPF, "general protection fault", regs, error_code,
-			X86_TRAP_GP, SIGSEGV) == NOTIFY_STOP)
-		return;
-	die("general protection fault", regs, error_code);
+exit:
+	exception_exit(regs);
 }
 
 /* May run on IST stack. */
@@ -312,15 +320,16 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co
 	    ftrace_int3_handler(regs))
 		return;
 #endif
+	exception_enter(regs);
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
 	if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
 				SIGTRAP) == NOTIFY_STOP)
-		return;
+		goto exit;
 #endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */
 
 	if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
 			SIGTRAP) == NOTIFY_STOP)
-		return;
+		goto exit;
 
 	/*
 	 * Let others (NMI) know that the debug stack is in use
@@ -331,6 +340,8 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co
 	do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
 	preempt_conditional_cli(regs);
 	debug_stack_usage_dec();
+exit:
+	exception_exit(regs);
 }
 
 #ifdef CONFIG_X86_64
@@ -391,6 +402,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 	unsigned long dr6;
 	int si_code;
 
+	exception_enter(regs);
+
 	get_debugreg(dr6, 6);
 
 	/* Filter out all the reserved bits which are preset to 1 */
@@ -406,7 +419,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 
 	/* Catch kmemcheck conditions first of all! */
 	if ((dr6 & DR_STEP) && kmemcheck_trap(regs))
-		return;
+		goto exit;
 
 	/* DR6 may or may not be cleared by the CPU */
 	set_debugreg(0, 6);
@@ -421,7 +434,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 
 	if (notify_die(DIE_DEBUG, "debug", regs, PTR_ERR(&dr6), error_code,
 							SIGTRAP) == NOTIFY_STOP)
-		return;
+		goto exit;
 
 	/*
 	 * Let others (NMI) know that the debug stack is in use
@@ -437,7 +450,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 					X86_TRAP_DB);
 		preempt_conditional_cli(regs);
 		debug_stack_usage_dec();
-		return;
+		goto exit;
 	}
 
 	/*
@@ -458,7 +471,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 	preempt_conditional_cli(regs);
 	debug_stack_usage_dec();
 
-	return;
+exit:
+	exception_exit(regs);
 }
 
 /*
@@ -555,14 +569,17 @@ dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code)
 #ifdef CONFIG_X86_32
 	ignore_fpu_irq = 1;
 #endif
-
+	exception_enter(regs);
 	math_error(regs, error_code, X86_TRAP_MF);
+	exception_exit(regs);
 }
 
 dotraplinkage void
 do_simd_coprocessor_error(struct pt_regs *regs, long error_code)
 {
+	exception_enter(regs);
 	math_error(regs, error_code, X86_TRAP_XF);
+	exception_exit(regs);
 }
 
 dotraplinkage void
@@ -629,6 +646,7 @@ EXPORT_SYMBOL_GPL(math_state_restore);
 dotraplinkage void __kprobes
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
+	exception_enter(regs);
 #ifdef CONFIG_MATH_EMULATION
 	if (read_cr0() & X86_CR0_EM) {
 		struct math_emu_info info = { };
@@ -637,6 +655,7 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 
 		info.regs = regs;
 		math_emulate(&info);
+		exception_exit(regs);
 		return;
 	}
 #endif
@@ -644,12 +663,15 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 #ifdef CONFIG_X86_32
 	conditional_sti(regs);
 #endif
+	exception_exit(regs);
 }
 
 #ifdef CONFIG_X86_32
 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
 {
 	siginfo_t info;
+
+	exception_enter(regs);
 	local_irq_enable();
 
 	info.si_signo = SIGILL;
@@ -657,10 +679,11 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
 	info.si_code = ILL_BADSTK;
 	info.si_addr = NULL;
 	if (notify_die(DIE_TRAP, "iret exception", regs, error_code,
-			X86_TRAP_IRET, SIGILL) == NOTIFY_STOP)
-		return;
-	do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
-		&info);
+			X86_TRAP_IRET, SIGILL) != NOTIFY_STOP) {
+		do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
+			&info);
+	}
+	exception_exit(regs);
 }
 #endif
 
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 76dcd9d8e0bc..7dde46d68a25 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -18,6 +18,7 @@
 #include <asm/pgalloc.h>		/* pgd_*(), ...			*/
 #include <asm/kmemcheck.h>		/* kmemcheck_*(), ...		*/
 #include <asm/fixmap.h>			/* VSYSCALL_START		*/
+#include <asm/rcu.h>			/* exception_enter(), ...	*/
 
 /*
  * Page fault error code bits:
@@ -1000,8 +1001,8 @@ static int fault_in_kernel_space(unsigned long address)
  * and the problem, and then passes it off to one of the appropriate
  * routines.
  */
-dotraplinkage void __kprobes
-do_page_fault(struct pt_regs *regs, unsigned long error_code)
+static void __kprobes
+__do_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
@@ -1209,3 +1210,11 @@ good_area:
 
 	up_read(&mm->mmap_sem);
 }
+
+dotraplinkage void __kprobes
+do_page_fault(struct pt_regs *regs, unsigned long error_code)
+{
+	exception_enter(regs);
+	__do_page_fault(regs, error_code);
+	exception_exit(regs);
+}